Automatic Intention Recognition in Conversation Processing

ERIC Educational Resources Information Center

Holtgraves, Thomas

2008-01-01

A fundamental assumption of many theories of conversation is that comprehension of a speaker's utterance involves recognition of the speaker's intention in producing that remark. However, the nature of intention recognition is not clear. One approach is to conceptualize a speaker's intention in terms of speech acts [Searle, J. (1969). "Speech…

"Who" is saying "what"? Brain-based decoding of human voice and speech.

PubMed

Formisano, Elia; De Martino, Federico; Bonte, Milene; Goebel, Rainer

2008-11-07

Can we decipher speech content ("what" is being said) and speaker identity ("who" is saying it) from observations of brain activity of a listener? Here, we combine functional magnetic resonance imaging with a data-mining algorithm and retrieve what and whom a person is listening to from the neural fingerprints that speech and voice signals elicit in the listener's auditory cortex. These cortical fingerprints are spatially distributed and insensitive to acoustic variations of the input so as to permit the brain-based recognition of learned speech from unknown speakers and of learned voices from previously unheard utterances. Our findings unravel the detailed cortical layout and computational properties of the neural populations at the basis of human speech recognition and speaker identification.

Difficulties in Automatic Speech Recognition of Dysarthric Speakers and Implications for Speech-Based Applications Used by the Elderly: A Literature Review

ERIC Educational Resources Information Center

Young, Victoria; Mihailidis, Alex

2010-01-01

Despite their growing presence in home computer applications and various telephony services, commercial automatic speech recognition technologies are still not easily employed by everyone; especially individuals with speech disorders. In addition, relatively little research has been conducted on automatic speech recognition performance with older…

A Method for Determining the Timing of Displaying the Speaker's Face and Captions for a Real-Time Speech-to-Caption System

NASA Astrophysics Data System (ADS)

Kuroki, Hayato; Ino, Shuichi; Nakano, Satoko; Hori, Kotaro; Ifukube, Tohru

The authors of this paper have been studying a real-time speech-to-caption system using speech recognition technology with a “repeat-speaking” method. In this system, they used a “repeat-speaker” who listens to a lecturer's voice and then speaks back the lecturer's speech utterances into a speech recognition computer. The througoing system showed that the accuracy of the captions is about 97% in Japanese-Japanese conversion and the conversion time from voices to captions is about 4 seconds in English-English conversion in some international conferences. Of course it required a lot of costs to achieve these high performances. In human communications, speech understanding depends not only on verbal information but also on non-verbal information such as speaker's gestures, and face and mouth movements. So the authors found the idea to display information of captions and speaker's face movement images with a suitable way to achieve a higher comprehension after storing information once into a computer briefly. In this paper, we investigate the relationship of the display sequence and display timing between captions that have speech recognition errors and the speaker's face movement images. The results show that the sequence “to display the caption before the speaker's face image” improves the comprehension of the captions. The sequence “to display both simultaneously” shows an improvement only a few percent higher than the question sentence, and the sequence “to display the speaker's face image before the caption” shows almost no change. In addition, the sequence “to display the caption 1 second before the speaker's face shows the most significant improvement of all the conditions.

Connected word recognition using a cascaded neuro-computational model

NASA Astrophysics Data System (ADS)

Hoya, Tetsuya; van Leeuwen, Cees

2016-10-01

We propose a novel framework for processing a continuous speech stream that contains a varying number of words, as well as non-speech periods. Speech samples are segmented into word-tokens and non-speech periods. An augmented version of an earlier-proposed, cascaded neuro-computational model is used for recognising individual words within the stream. Simulation studies using both a multi-speaker-dependent and speaker-independent digit string database show that the proposed method yields a recognition performance comparable to that obtained by a benchmark approach using hidden Markov models with embedded training.

Functional Connectivity between Face-Movement and Speech-Intelligibility Areas during Auditory-Only Speech Perception

PubMed Central

Schall, Sonja; von Kriegstein, Katharina

2014-01-01

It has been proposed that internal simulation of the talking face of visually-known speakers facilitates auditory speech recognition. One prediction of this view is that brain areas involved in auditory-only speech comprehension interact with visual face-movement sensitive areas, even under auditory-only listening conditions. Here, we test this hypothesis using connectivity analyses of functional magnetic resonance imaging (fMRI) data. Participants (17 normal participants, 17 developmental prosopagnosics) first learned six speakers via brief voice-face or voice-occupation training (<2 min/speaker). This was followed by an auditory-only speech recognition task and a control task (voice recognition) involving the learned speakers’ voices in the MRI scanner. As hypothesized, we found that, during speech recognition, familiarity with the speaker’s face increased the functional connectivity between the face-movement sensitive posterior superior temporal sulcus (STS) and an anterior STS region that supports auditory speech intelligibility. There was no difference between normal participants and prosopagnosics. This was expected because previous findings have shown that both groups use the face-movement sensitive STS to optimize auditory-only speech comprehension. Overall, the present findings indicate that learned visual information is integrated into the analysis of auditory-only speech and that this integration results from the interaction of task-relevant face-movement and auditory speech-sensitive areas. PMID:24466026

Robust Recognition of Loud and Lombard speech in the Fighter Cockpit Environment

DTIC Science & Technology

1988-08-01

the latter as inter-speaker variability. According to Zue [Z85j, inter-speaker variabilities can be attributed to sociolinguistic background, dialect...34 Journal of the Acoustical Society of America , Vol 50, 1971. [At74I B. S. Atal, "Linear prediction for speaker identification," Journal of the Acoustical...Society of America , Vol 55, 1974. [B771 B. Beek, E. P. Neuberg, and D. C. Hodge, "An Assessment of the Technology of Automatic Speech Recognition for

Robust Speech Processing & Recognition: Speaker ID, Language ID, Speech Recognition/Keyword Spotting, Diarization/Co-Channel/Environmental Characterization, Speaker State Assessment

DTIC Science & Technology

2015-10-01

Scoring, Gaussian Backend , etc.) as shown in Fig. 39. The methods in this domain also emphasized the ability to perform data purification for both...investigation using the same infrastructure was undertaken to explore Lombard effect “flavor” detection for improved speaker ID. The study The presence of...dimension selection and compared to a common N-gram frequency based selection. 2.1.2: Exploration on NN/DBN backend : Since Deep Neural Networks (DNN) have

Speech-on-speech masking with variable access to the linguistic content of the masker speech for native and non-native speakers of English

PubMed Central

Calandruccio, Lauren; Bradlow, Ann R.; Dhar, Sumitrajit

2013-01-01

Background Masking release for an English sentence-recognition task in the presence of foreign-accented English speech compared to native-accented English speech was reported in Calandruccio, Dhar and Bradlow (2010). The masking release appeared to increase as the masker intelligibility decreased. However, it could not be ruled out that spectral differences between the speech maskers were influencing the significant differences observed. Purpose The purpose of the current experiment was to minimize spectral differences between speech maskers to determine how various amounts of linguistic information within competing speech affect masking release. Research Design A mixed model design with within- (four two-talker speech maskers) and between-subject (listener group) factors was conducted. Speech maskers included native-accented English speech, and high-intelligibility, moderate-intelligibility and low-intelligibility Mandarin-accented English. Normalizing the long-term average speech spectra of the maskers to each other minimized spectral differences between the masker conditions. Study Sample Three listener groups were tested including monolingual English speakers with normal hearing, non-native speakers of English with normal hearing, and monolingual speakers of English with hearing loss. The non-native speakers of English were from various native-language backgrounds, not including Mandarin (or any other Chinese dialect). Listeners with hearing loss had symmetrical, mild sloping to moderate sensorineural hearing loss. Data Collection and Analysis Listeners were asked to repeat back sentences that were presented in the presence of four different two-talker speech maskers. Responses were scored based on the keywords within the sentences (100 keywords/masker condition). A mixed-model regression analysis was used to analyze the difference in performance scores between the masker conditions and the listener groups. Results Monolingual speakers of English with normal hearing benefited when the competing speech signal was foreign-accented compared to native-accented allowing for improved speech recognition. Various levels of intelligibility across the foreign-accented speech maskers did not influence results. Neither the non-native English listeners with normal hearing, nor the monolingual English speakers with hearing loss benefited from masking release when the masker was changed from native-accented to foreign-accented English. Conclusions Slight modifications between the target and the masker speech allowed monolingual speakers of English with normal hearing to improve their recognition of native-accented English even when the competing speech was highly intelligible. Further research is needed to determine which modifications within the competing speech signal caused the Mandarin-accented English to be less effective with respect to masking. Determining the influences within the competing speech that make it less effective as a masker, or determining why monolingual normal-hearing listeners can take advantage of these differences could help improve speech recognition for those with hearing loss in the future. PMID:25126683

Towards Contactless Silent Speech Recognition Based on Detection of Active and Visible Articulators Using IR-UWB Radar.

PubMed

Shin, Young Hoon; Seo, Jiwon

2016-10-29

People with hearing or speaking disabilities are deprived of the benefits of conventional speech recognition technology because it is based on acoustic signals. Recent research has focused on silent speech recognition systems that are based on the motions of a speaker's vocal tract and articulators. Because most silent speech recognition systems use contact sensors that are very inconvenient to users or optical systems that are susceptible to environmental interference, a contactless and robust solution is hence required. Toward this objective, this paper presents a series of signal processing algorithms for a contactless silent speech recognition system using an impulse radio ultra-wide band (IR-UWB) radar. The IR-UWB radar is used to remotely and wirelessly detect motions of the lips and jaw. In order to extract the necessary features of lip and jaw motions from the received radar signals, we propose a feature extraction algorithm. The proposed algorithm noticeably improved speech recognition performance compared to the existing algorithm during our word recognition test with five speakers. We also propose a speech activity detection algorithm to automatically select speech segments from continuous input signals. Thus, speech recognition processing is performed only when speech segments are detected. Our testbed consists of commercial off-the-shelf radar products, and the proposed algorithms are readily applicable without designing specialized radar hardware for silent speech processing.

Current trends in small vocabulary speech recognition for equipment control

NASA Astrophysics Data System (ADS)

Doukas, Nikolaos; Bardis, Nikolaos G.

2017-09-01

Speech recognition systems allow human - machine communication to acquire an intuitive nature that approaches the simplicity of inter - human communication. Small vocabulary speech recognition is a subset of the overall speech recognition problem, where only a small number of words need to be recognized. Speaker independent small vocabulary recognition can find significant applications in field equipment used by military personnel. Such equipment may typically be controlled by a small number of commands that need to be given quickly and accurately, under conditions where delicate manual operations are difficult to achieve. This type of application could hence significantly benefit by the use of robust voice operated control components, as they would facilitate the interaction with their users and render it much more reliable in times of crisis. This paper presents current challenges involved in attaining efficient and robust small vocabulary speech recognition. These challenges concern feature selection, classification techniques, speaker diversity and noise effects. A state machine approach is presented that facilitates the voice guidance of different equipment in a variety of situations.

[Perception of emotional intonation of noisy speech signal with different acoustic parameters by adults of different age and gender].

PubMed

Dmitrieva, E S; Gel'man, V Ia

2011-01-01

The listener-distinctive features of recognition of different emotional intonations (positive, negative and neutral) of male and female speakers in the presence or absence of background noise were studied in 49 adults aged 20-79 years. In all the listeners noise produced the most pronounced decrease in recognition accuracy for positive emotional intonation ("joy") as compared to other intonations, whereas it did not influence the recognition accuracy of "anger" in 65-79-year-old listeners. The higher emotion recognition rates of a noisy signal were observed for speech emotional intonations expressed by female speakers. Acoustic characteristics of noisy and clear speech signals underlying perception of speech emotional prosody were found for adult listeners of different age and gender.

Increase in Speech Recognition Due to Linguistic Mismatch between Target and Masker Speech: Monolingual and Simultaneous Bilingual Performance

ERIC Educational Resources Information Center

Calandruccio, Lauren; Zhou, Haibo

2014-01-01

Purpose: To examine whether improved speech recognition during linguistically mismatched target-masker experiments is due to linguistic unfamiliarity of the masker speech or linguistic dissimilarity between the target and masker speech. Method: Monolingual English speakers (n = 20) and English-Greek simultaneous bilinguals (n = 20) listened to…

Experimental study on GMM-based speaker recognition

NASA Astrophysics Data System (ADS)

Ye, Wenxing; Wu, Dapeng; Nucci, Antonio

2010-04-01

Speaker recognition plays a very important role in the field of biometric security. In order to improve the recognition performance, many pattern recognition techniques have be explored in the literature. Among these techniques, the Gaussian Mixture Model (GMM) is proved to be an effective statistic model for speaker recognition and is used in most state-of-the-art speaker recognition systems. The GMM is used to represent the 'voice print' of a speaker through modeling the spectral characteristic of speech signals of the speaker. In this paper, we implement a speaker recognition system, which consists of preprocessing, Mel-Frequency Cepstrum Coefficients (MFCCs) based feature extraction, and GMM based classification. We test our system with TIDIGITS data set (325 speakers) and our own recordings of more than 200 speakers; our system achieves 100% correct recognition rate. Moreover, we also test our system under the scenario that training samples are from one language but test samples are from a different language; our system also achieves 100% correct recognition rate, which indicates that our system is language independent.

Discriminative analysis of lip motion features for speaker identification and speech-reading.

PubMed

Cetingül, H Ertan; Yemez, Yücel; Erzin, Engin; Tekalp, A Murat

2006-10-01

There have been several studies that jointly use audio, lip intensity, and lip geometry information for speaker identification and speech-reading applications. This paper proposes using explicit lip motion information, instead of or in addition to lip intensity and/or geometry information, for speaker identification and speech-reading within a unified feature selection and discrimination analysis framework, and addresses two important issues: 1) Is using explicit lip motion information useful, and, 2) if so, what are the best lip motion features for these two applications? The best lip motion features for speaker identification are considered to be those that result in the highest discrimination of individual speakers in a population, whereas for speech-reading, the best features are those providing the highest phoneme/word/phrase recognition rate. Several lip motion feature candidates have been considered including dense motion features within a bounding box about the lip, lip contour motion features, and combination of these with lip shape features. Furthermore, a novel two-stage, spatial, and temporal discrimination analysis is introduced to select the best lip motion features for speaker identification and speech-reading applications. Experimental results using an hidden-Markov-model-based recognition system indicate that using explicit lip motion information provides additional performance gains in both applications, and lip motion features prove more valuable in the case of speech-reading application.

Sound Processing Features for Speaker-Dependent and Phrase-Independent Emotion Recognition in Berlin Database

NASA Astrophysics Data System (ADS)

Anagnostopoulos, Christos Nikolaos; Vovoli, Eftichia

An emotion recognition framework based on sound processing could improve services in human-computer interaction. Various quantitative speech features obtained from sound processing of acting speech were tested, as to whether they are sufficient or not to discriminate between seven emotions. Multilayered perceptrons were trained to classify gender and emotions on the basis of a 24-input vector, which provide information about the prosody of the speaker over the entire sentence using statistics of sound features. Several experiments were performed and the results were presented analytically. Emotion recognition was successful when speakers and utterances were “known” to the classifier. However, severe misclassifications occurred during the utterance-independent framework. At least, the proposed feature vector achieved promising results for utterance-independent recognition of high- and low-arousal emotions.

Effective Prediction of Errors by Non-native Speakers Using Decision Tree for Speech Recognition-Based CALL System

NASA Astrophysics Data System (ADS)

Wang, Hongcui; Kawahara, Tatsuya

CALL (Computer Assisted Language Learning) systems using ASR (Automatic Speech Recognition) for second language learning have received increasing interest recently. However, it still remains a challenge to achieve high speech recognition performance, including accurate detection of erroneous utterances by non-native speakers. Conventionally, possible error patterns, based on linguistic knowledge, are added to the lexicon and language model, or the ASR grammar network. However, this approach easily falls in the trade-off of coverage of errors and the increase of perplexity. To solve the problem, we propose a method based on a decision tree to learn effective prediction of errors made by non-native speakers. An experimental evaluation with a number of foreign students learning Japanese shows that the proposed method can effectively generate an ASR grammar network, given a target sentence, to achieve both better coverage of errors and smaller perplexity, resulting in significant improvement in ASR accuracy.

On the Development of Speech Resources for the Mixtec Language

PubMed Central

2013-01-01

The Mixtec language is one of the main native languages in Mexico. In general, due to urbanization, discrimination, and limited attempts to promote the culture, the native languages are disappearing. Most of the information available about the Mixtec language is in written form as in dictionaries which, although including examples about how to pronounce the Mixtec words, are not as reliable as listening to the correct pronunciation from a native speaker. Formal acoustic resources, as speech corpora, are almost non-existent for the Mixtec, and no speech technologies are known to have been developed for it. This paper presents the development of the following resources for the Mixtec language: (1) a speech database of traditional narratives of the Mixtec culture spoken by a native speaker (labelled at the phonetic and orthographic levels by means of spectral analysis) and (2) a native speaker-adaptive automatic speech recognition (ASR) system (trained with the speech database) integrated with a Mixtec-to-Spanish/Spanish-to-Mixtec text translator. The speech database, although small and limited to a single variant, was reliable enough to build the multiuser speech application which presented a mean recognition/translation performance up to 94.36% in experiments with non-native speakers (the target users). PMID:23710134

Audiovisual cues benefit recognition of accented speech in noise but not perceptual adaptation.

PubMed

Banks, Briony; Gowen, Emma; Munro, Kevin J; Adank, Patti

2015-01-01

Perceptual adaptation allows humans to recognize different varieties of accented speech. We investigated whether perceptual adaptation to accented speech is facilitated if listeners can see a speaker's facial and mouth movements. In Study 1, participants listened to sentences in a novel accent and underwent a period of training with audiovisual or audio-only speech cues, presented in quiet or in background noise. A control group also underwent training with visual-only (speech-reading) cues. We observed no significant difference in perceptual adaptation between any of the groups. To address a number of remaining questions, we carried out a second study using a different accent, speaker and experimental design, in which participants listened to sentences in a non-native (Japanese) accent with audiovisual or audio-only cues, without separate training. Participants' eye gaze was recorded to verify that they looked at the speaker's face during audiovisual trials. Recognition accuracy was significantly better for audiovisual than for audio-only stimuli; however, no statistical difference in perceptual adaptation was observed between the two modalities. Furthermore, Bayesian analysis suggested that the data supported the null hypothesis. Our results suggest that although the availability of visual speech cues may be immediately beneficial for recognition of unfamiliar accented speech in noise, it does not improve perceptual adaptation.

Multilevel Analysis in Analyzing Speech Data

ERIC Educational Resources Information Center

Guddattu, Vasudeva; Krishna, Y.

2011-01-01

The speech produced by human vocal tract is a complex acoustic signal, with diverse applications in phonetics, speech synthesis, automatic speech recognition, speaker identification, communication aids, speech pathology, speech perception, machine translation, hearing research, rehabilitation and assessment of communication disorders and many…

Automatic speech recognition and training for severely dysarthric users of assistive technology: the STARDUST project.

PubMed

Parker, Mark; Cunningham, Stuart; Enderby, Pam; Hawley, Mark; Green, Phil

2006-01-01

The STARDUST project developed robust computer speech recognizers for use by eight people with severe dysarthria and concomitant physical disability to access assistive technologies. Independent computer speech recognizers trained with normal speech are of limited functional use by those with severe dysarthria due to limited and inconsistent proximity to "normal" articulatory patterns. Severe dysarthric output may also be characterized by a small mass of distinguishable phonetic tokens making the acoustic differentiation of target words difficult. Speaker dependent computer speech recognition using Hidden Markov Models was achieved by the identification of robust phonetic elements within the individual speaker output patterns. A new system of speech training using computer generated visual and auditory feedback reduced the inconsistent production of key phonetic tokens over time.

The Development of the Speaker Independent ARM Continuous Speech Recognition System

DTIC Science & Technology

1992-01-01

spokeTi airborne reconnaissance reports u-ing a speech recognition system based on phoneme-level hidden Markov models (HMMs). Previous versions of the ARM...will involve automatic selection from multiple model sets, corresponding to different speaker types, and that the most rudimen- tary partition of a...The vocabulary size for the ARM task is 497 words. These words are related to the phoneme-level symbols corresponding to the models in the model set

Emotionally conditioning the target-speech voice enhances recognition of the target speech under "cocktail-party" listening conditions.

PubMed

Lu, Lingxi; Bao, Xiaohan; Chen, Jing; Qu, Tianshu; Wu, Xihong; Li, Liang

2018-05-01

Under a noisy "cocktail-party" listening condition with multiple people talking, listeners can use various perceptual/cognitive unmasking cues to improve recognition of the target speech against informational speech-on-speech masking. One potential unmasking cue is the emotion expressed in a speech voice, by means of certain acoustical features. However, it was unclear whether emotionally conditioning a target-speech voice that has none of the typical acoustical features of emotions (i.e., an emotionally neutral voice) can be used by listeners for enhancing target-speech recognition under speech-on-speech masking conditions. In this study we examined the recognition of target speech against a two-talker speech masker both before and after the emotionally neutral target voice was paired with a loud female screaming sound that has a marked negative emotional valence. The results showed that recognition of the target speech (especially the first keyword in a target sentence) was significantly improved by emotionally conditioning the target speaker's voice. Moreover, the emotional unmasking effect was independent of the unmasking effect of the perceived spatial separation between the target speech and the masker. Also, (skin conductance) electrodermal responses became stronger after emotional learning when the target speech and masker were perceptually co-located, suggesting an increase of listening efforts when the target speech was informationally masked. These results indicate that emotionally conditioning the target speaker's voice does not change the acoustical parameters of the target-speech stimuli, but the emotionally conditioned vocal features can be used as cues for unmasking target speech.

Recognition of speaker-dependent continuous speech with KEAL

NASA Astrophysics Data System (ADS)

Mercier, G.; Bigorgne, D.; Miclet, L.; Le Guennec, L.; Querre, M.

1989-04-01

A description of the speaker-dependent continuous speech recognition system KEAL is given. An unknown utterance, is recognized by means of the followng procedures: acoustic analysis, phonetic segmentation and identification, word and sentence analysis. The combination of feature-based, speaker-independent coarse phonetic segmentation with speaker-dependent statistical classification techniques is one of the main design features of the acoustic-phonetic decoder. The lexical access component is essentially based on a statistical dynamic programming technique which aims at matching a phonemic lexical entry containing various phonological forms, against a phonetic lattice. Sentence recognition is achieved by use of a context-free grammar and a parsing algorithm derived from Earley's parser. A speaker adaptation module allows some of the system parameters to be adjusted by matching known utterances with their acoustical representation. The task to be performed, described by its vocabulary and its grammar, is given as a parameter of the system. Continuously spoken sentences extracted from a 'pseudo-Logo' language are analyzed and results are presented.

Speaker Recognition Using Real vs. Synthetic Parallel Data for DNN Channel Compensation

DTIC Science & Technology

2016-08-18

Speaker Recognition Using Real vs Synthetic Parallel Data for DNN Channel Compensation Fred Richardson, Michael Brandstein, Jennifer Melot and...de- noising DNNs has been demonstrated for several speech tech- nologies such as ASR and speaker recognition. This paper com- pares the use of real ...AVG and POOL min DCFs). In all cases, the telephone channel per- formance on SRE10 is improved by the denoising DNNs with the real Mixer 1 and 2

Speaker Recognition Using Real vs Synthetic Parallel Data for DNN Channel Compensation

DTIC Science & Technology

2016-09-08

Speaker Recognition Using Real vs Synthetic Parallel Data for DNN Channel Compensation Fred Richardson, Michael Brandstein, Jennifer Melot and...de- noising DNNs has been demonstrated for several speech tech- nologies such as ASR and speaker recognition. This paper com- pares the use of real ...AVG and POOL min DCFs). In all cases, the telephone channel per- formance on SRE10 is improved by the denoising DNNs with the real Mixer 1 and 2

A multi-views multi-learners approach towards dysarthric speech recognition using multi-nets artificial neural networks.

PubMed

Shahamiri, Seyed Reza; Salim, Siti Salwah Binti

2014-09-01

Automatic speech recognition (ASR) can be very helpful for speakers who suffer from dysarthria, a neurological disability that damages the control of motor speech articulators. Although a few attempts have been made to apply ASR technologies to sufferers of dysarthria, previous studies show that such ASR systems have not attained an adequate level of performance. In this study, a dysarthric multi-networks speech recognizer (DM-NSR) model is provided using a realization of multi-views multi-learners approach called multi-nets artificial neural networks, which tolerates variability of dysarthric speech. In particular, the DM-NSR model employs several ANNs (as learners) to approximate the likelihood of ASR vocabulary words and to deal with the complexity of dysarthric speech. The proposed DM-NSR approach was presented as both speaker-dependent and speaker-independent paradigms. In order to highlight the performance of the proposed model over legacy models, multi-views single-learner models of the DM-NSRs were also provided and their efficiencies were compared in detail. Moreover, a comparison among the prominent dysarthric ASR methods and the proposed one is provided. The results show that the DM-NSR recorded improved recognition rate by up to 24.67% and the error rate was reduced by up to 8.63% over the reference model.

Interactive voice technology: Variations in the vocal utterances of speakers performing a stress-inducing task

NASA Astrophysics Data System (ADS)

Mosko, J. D.; Stevens, K. N.; Griffin, G. R.

1983-08-01

Acoustical analyses were conducted of words produced by four speakers in a motion stress-inducing situation. The aim of the analyses was to document the kinds of changes that occur in the vocal utterances of speakers who are exposed to motion stress and to comment on the implications of these results for the design and development of voice interactive systems. The speakers differed markedly in the types and magnitudes of the changes that occurred in their speech. For some speakers, the stress-inducing experimental condition caused an increase in fundamental frequency, changes in the pattern of vocal fold vibration, shifts in vowel production and changes in the relative amplitudes of sounds containing turbulence noise. All speakers showed greater variability in the experimental condition than in more relaxed control situation. The variability was manifested in the acoustical characteristics of individual phonetic elements, particularly in speech sound variability observed serve to unstressed syllables. The kinds of changes and variability observed serve to emphasize the limitations of speech recognition systems based on template matching of patterns that are stored in the system during a training phase. There is need for a better understanding of these phonetic modifications and for developing ways of incorporating knowledge about these changes within a speech recognition system.

When speaker identity is unavoidable: Neural processing of speaker identity cues in natural speech.

PubMed

Tuninetti, Alba; Chládková, Kateřina; Peter, Varghese; Schiller, Niels O; Escudero, Paola

2017-11-01

Speech sound acoustic properties vary largely across speakers and accents. When perceiving speech, adult listeners normally disregard non-linguistic variation caused by speaker or accent differences, in order to comprehend the linguistic message, e.g. to correctly identify a speech sound or a word. Here we tested whether the process of normalizing speaker and accent differences, facilitating the recognition of linguistic information, is found at the level of neural processing, and whether it is modulated by the listeners' native language. In a multi-deviant oddball paradigm, native and nonnative speakers of Dutch were exposed to naturally-produced Dutch vowels varying in speaker, sex, accent, and phoneme identity. Unexpectedly, the analysis of mismatch negativity (MMN) amplitudes elicited by each type of change shows a large degree of early perceptual sensitivity to non-linguistic cues. This finding on perception of naturally-produced stimuli contrasts with previous studies examining the perception of synthetic stimuli wherein adult listeners automatically disregard acoustic cues to speaker identity. The present finding bears relevance to speech normalization theories, suggesting that at an unattended level of processing, listeners are indeed sensitive to changes in fundamental frequency in natural speech tokens. Copyright © 2017 Elsevier Inc. All rights reserved.

Speaker emotion recognition: from classical classifiers to deep neural networks

NASA Astrophysics Data System (ADS)

Mezghani, Eya; Charfeddine, Maha; Nicolas, Henri; Ben Amar, Chokri

2018-04-01

Speaker emotion recognition is considered among the most challenging tasks in recent years. In fact, automatic systems for security, medicine or education can be improved when considering the speech affective state. In this paper, a twofold approach for speech emotion classification is proposed. At the first side, a relevant set of features is adopted, and then at the second one, numerous supervised training techniques, involving classic methods as well as deep learning, are experimented. Experimental results indicate that deep architecture can improve classification performance on two affective databases, the Berlin Dataset of Emotional Speech and the SAVEE Dataset Surrey Audio-Visual Expressed Emotion.

Methods and apparatus for non-acoustic speech characterization and recognition

DOEpatents

Holzrichter, John F.

1999-01-01

By simultaneously recording EM wave reflections and acoustic speech information, the positions and velocities of the speech organs as speech is articulated can be defined for each acoustic speech unit. Well defined time frames and feature vectors describing the speech, to the degree required, can be formed. Such feature vectors can uniquely characterize the speech unit being articulated each time frame. The onset of speech, rejection of external noise, vocalized pitch periods, articulator conditions, accurate timing, the identification of the speaker, acoustic speech unit recognition, and organ mechanical parameters can be determined.

Methods and apparatus for non-acoustic speech characterization and recognition

DOE Office of Scientific and Technical Information (OSTI.GOV)

Holzrichter, J.F.

By simultaneously recording EM wave reflections and acoustic speech information, the positions and velocities of the speech organs as speech is articulated can be defined for each acoustic speech unit. Well defined time frames and feature vectors describing the speech, to the degree required, can be formed. Such feature vectors can uniquely characterize the speech unit being articulated each time frame. The onset of speech, rejection of external noise, vocalized pitch periods, articulator conditions, accurate timing, the identification of the speaker, acoustic speech unit recognition, and organ mechanical parameters can be determined.

Voice technology and BBN

NASA Technical Reports Server (NTRS)

Wolf, Jared J.

1977-01-01

The following research was discussed: (1) speech signal processing; (2) automatic speech recognition; (3) continuous speech understanding; (4) speaker recognition; (5) speech compression; (6) subjective and objective evaluation of speech communication system; (7) measurement of the intelligibility and quality of speech when degraded by noise or other masking stimuli; (8) speech synthesis; (9) instructional aids for second-language learning and for training of the deaf; and (10) investigation of speech correlates of psychological stress. Experimental psychology, control systems, and human factors engineering, which are often relevant to the proper design and operation of speech systems are described.

Speaker Recognition by Combining MFCC and Phase Information in Noisy Conditions

NASA Astrophysics Data System (ADS)

Wang, Longbiao; Minami, Kazue; Yamamoto, Kazumasa; Nakagawa, Seiichi

In this paper, we investigate the effectiveness of phase for speaker recognition in noisy conditions and combine the phase information with mel-frequency cepstral coefficients (MFCCs). To date, almost speaker recognition methods are based on MFCCs even in noisy conditions. For MFCCs which dominantly capture vocal tract information, only the magnitude of the Fourier Transform of time-domain speech frames is used and phase information has been ignored. High complement of the phase information and MFCCs is expected because the phase information includes rich voice source information. Furthermore, some researches have reported that phase based feature was robust to noise. In our previous study, a phase information extraction method that normalizes the change variation in the phase depending on the clipping position of the input speech was proposed, and the performance of the combination of the phase information and MFCCs was remarkably better than that of MFCCs. In this paper, we evaluate the robustness of the proposed phase information for speaker identification in noisy conditions. Spectral subtraction, a method skipping frames with low energy/Signal-to-Noise (SN) and noisy speech training models are used to analyze the effect of the phase information and MFCCs in noisy conditions. The NTT database and the JNAS (Japanese Newspaper Article Sentences) database added with stationary/non-stationary noise were used to evaluate our proposed method. MFCCs outperformed the phase information for clean speech. On the other hand, the degradation of the phase information was significantly smaller than that of MFCCs for noisy speech. The individual result of the phase information was even better than that of MFCCs in many cases by clean speech training models. By deleting unreliable frames (frames having low energy/SN), the speaker identification performance was improved significantly. By integrating the phase information with MFCCs, the speaker identification error reduction rate was about 30%-60% compared with the standard MFCC-based method.

A speech-controlled environmental control system for people with severe dysarthria.

PubMed

Hawley, Mark S; Enderby, Pam; Green, Phil; Cunningham, Stuart; Brownsell, Simon; Carmichael, James; Parker, Mark; Hatzis, Athanassios; O'Neill, Peter; Palmer, Rebecca

2007-06-01

Automatic speech recognition (ASR) can provide a rapid means of controlling electronic assistive technology. Off-the-shelf ASR systems function poorly for users with severe dysarthria because of the increased variability of their articulations. We have developed a limited vocabulary speaker dependent speech recognition application which has greater tolerance to variability of speech, coupled with a computerised training package which assists dysarthric speakers to improve the consistency of their vocalisations and provides more data for recogniser training. These applications, and their implementation as the interface for a speech-controlled environmental control system (ECS), are described. The results of field trials to evaluate the training program and the speech-controlled ECS are presented. The user-training phase increased the recognition rate from 88.5% to 95.4% (p<0.001). Recognition rates were good for people with even the most severe dysarthria in everyday usage in the home (mean word recognition rate 86.9%). Speech-controlled ECS were less accurate (mean task completion accuracy 78.6% versus 94.8%) but were faster to use than switch-scanning systems, even taking into account the need to repeat unsuccessful operations (mean task completion time 7.7s versus 16.9s, p<0.001). It is concluded that a speech-controlled ECS is a viable alternative to switch-scanning systems for some people with severe dysarthria and would lead, in many cases, to more efficient control of the home.

It doesn't matter what you say: FMRI correlates of voice learning and recognition independent of speech content.

PubMed

Zäske, Romi; Awwad Shiekh Hasan, Bashar; Belin, Pascal

2017-09-01

Listeners can recognize newly learned voices from previously unheard utterances, suggesting the acquisition of high-level speech-invariant voice representations during learning. Using functional magnetic resonance imaging (fMRI) we investigated the anatomical basis underlying the acquisition of voice representations for unfamiliar speakers independent of speech, and their subsequent recognition among novel voices. Specifically, listeners studied voices of unfamiliar speakers uttering short sentences and subsequently classified studied and novel voices as "old" or "new" in a recognition test. To investigate "pure" voice learning, i.e., independent of sentence meaning, we presented German sentence stimuli to non-German speaking listeners. To disentangle stimulus-invariant and stimulus-dependent learning, during the test phase we contrasted a "same sentence" condition in which listeners heard speakers repeating the sentences from the preceding study phase, with a "different sentence" condition. Voice recognition performance was above chance in both conditions although, as expected, performance was higher for same than for different sentences. During study phases activity in the left inferior frontal gyrus (IFG) was related to subsequent voice recognition performance and same versus different sentence condition, suggesting an involvement of the left IFG in the interactive processing of speaker and speech information during learning. Importantly, at test reduced activation for voices correctly classified as "old" compared to "new" emerged in a network of brain areas including temporal voice areas (TVAs) of the right posterior superior temporal gyrus (pSTG), as well as the right inferior/middle frontal gyrus (IFG/MFG), the right medial frontal gyrus, and the left caudate. This effect of voice novelty did not interact with sentence condition, suggesting a role of temporal voice-selective areas and extra-temporal areas in the explicit recognition of learned voice identity, independent of speech content. Copyright © 2017 Elsevier Ltd. All rights reserved.

Robust recognition of loud and Lombard speech in the fighter cockpit environment

NASA Astrophysics Data System (ADS)

Stanton, Bill J., Jr.

1988-08-01

There are a number of challenges associated with incorporating speech recognition technology into the fighter cockpit. One of the major problems is the wide range of variability in the pilot's voice. That can result from changing levels of stress and workload. Increasing the training set to include abnormal speech is not an attractive option because of the innumerable conditions that would have to be represented and the inordinate amount of time to collect such a training set. A more promising approach is to study subsets of abnormal speech that have been produced under controlled cockpit conditions with the purpose of characterizing reliable shifts that occur relative to normal speech. Such was the initiative of this research. Analyses were conducted for 18 features on 17671 phoneme tokens across eight speakers for normal, loud, and Lombard speech. It was discovered that there was a consistent migration of energy in the sonorants. This discovery of reliable energy shifts led to the development of a method to reduce or eliminate these shifts in the Euclidean distances between LPC log magnitude spectra. This combination significantly improved recognition performance of loud and Lombard speech. Discrepancies in recognition error rates between normal and abnormal speech were reduced by approximately 50 percent for all eight speakers combined.

Speech processing using maximum likelihood continuity mapping

DOEpatents

Hogden, John E.

2000-01-01

Speech processing is obtained that, given a probabilistic mapping between static speech sounds and pseudo-articulator positions, allows sequences of speech sounds to be mapped to smooth sequences of pseudo-articulator positions. In addition, a method for learning a probabilistic mapping between static speech sounds and pseudo-articulator position is described. The method for learning the mapping between static speech sounds and pseudo-articulator position uses a set of training data composed only of speech sounds. The said speech processing can be applied to various speech analysis tasks, including speech recognition, speaker recognition, speech coding, speech synthesis, and voice mimicry.

Speech processing using maximum likelihood continuity mapping

DOE Office of Scientific and Technical Information (OSTI.GOV)

Hogden, J.E.

Speech processing is obtained that, given a probabilistic mapping between static speech sounds and pseudo-articulator positions, allows sequences of speech sounds to be mapped to smooth sequences of pseudo-articulator positions. In addition, a method for learning a probabilistic mapping between static speech sounds and pseudo-articulator position is described. The method for learning the mapping between static speech sounds and pseudo-articulator position uses a set of training data composed only of speech sounds. The said speech processing can be applied to various speech analysis tasks, including speech recognition, speaker recognition, speech coding, speech synthesis, and voice mimicry.

Implementation of support vector machine for classification of speech marked hijaiyah letters based on Mel frequency cepstrum coefficient feature extraction

NASA Astrophysics Data System (ADS)

Adhi Pradana, Wisnu; Adiwijaya; Novia Wisesty, Untari

2018-03-01

Support Vector Machine or commonly called SVM is one method that can be used to process the classification of a data. SVM classifies data from 2 different classes with hyperplane. In this study, the system was built using SVM to develop Arabic Speech Recognition. In the development of the system, there are 2 kinds of speakers that have been tested that is dependent speakers and independent speakers. The results from this system is an accuracy of 85.32% for speaker dependent and 61.16% for independent speakers.

Effects of emotional and perceptual-motor stress on a voice recognition system's accuracy: An applied investigation

NASA Astrophysics Data System (ADS)

Poock, G. K.; Martin, B. J.

1984-02-01

This was an applied investigation examining the ability of a speech recognition system to recognize speakers' inputs when the speakers were under different stress levels. Subjects were asked to speak to a voice recognition system under three conditions: (1) normal office environment, (2) emotional stress, and (3) perceptual-motor stress. Results indicate a definite relationship between voice recognition system performance and the type of low stress reference patterns used to achieve recognition.

A study of voice production characteristics of astronuat speech during Apollo 11 for speaker modeling in space.

PubMed

Yu, Chengzhu; Hansen, John H L

2017-03-01

Human physiology has evolved to accommodate environmental conditions, including temperature, pressure, and air chemistry unique to Earth. However, the environment in space varies significantly compared to that on Earth and, therefore, variability is expected in astronauts' speech production mechanism. In this study, the variations of astronaut voice characteristics during the NASA Apollo 11 mission are analyzed. Specifically, acoustical features such as fundamental frequency and phoneme formant structure that are closely related to the speech production system are studied. For a further understanding of astronauts' vocal tract spectrum variation in space, a maximum likelihood frequency warping based analysis is proposed to detect the vocal tract spectrum displacement during space conditions. The results from fundamental frequency, formant structure, as well as vocal spectrum displacement indicate that astronauts change their speech production mechanism when in space. Moreover, the experimental results for astronaut voice identification tasks indicate that current speaker recognition solutions are highly vulnerable to astronaut voice production variations in space conditions. Future recommendations from this study suggest that successful applications of speaker recognition during extended space missions require robust speaker modeling techniques that could effectively adapt to voice production variation caused by diverse space conditions.

SAM: speech-aware applications in medicine to support structured data entry.

PubMed Central

Wormek, A. K.; Ingenerf, J.; Orthner, H. F.

1997-01-01

In the last two years, improvement in speech recognition technology has directed the medical community's interest to porting and using such innovations in clinical systems. The acceptance of speech recognition systems in clinical domains increases with recognition speed, large medical vocabulary, high accuracy, continuous speech recognition, and speaker independence. Although some commercial speech engines approach these requirements, the greatest benefit can be achieved in adapting a speech recognizer to a specific medical application. The goals of our work are first, to develop a speech-aware core component which is able to establish connections to speech recognition engines of different vendors. This is realized in SAM. Second, with applications based on SAM we want to support the physician in his/her routine clinical care activities. Within the STAMP project (STAndardized Multimedia report generator in Pathology), we extend SAM by combining a structured data entry approach with speech recognition technology. Another speech-aware application in the field of Diabetes care is connected to a terminology server. The server delivers a controlled vocabulary which can be used for speech recognition. PMID:9357730

Inferring Speaker Affect in Spoken Natural Language Communication

ERIC Educational Resources Information Center

Pon-Barry, Heather Roberta

2013-01-01

The field of spoken language processing is concerned with creating computer programs that can understand human speech and produce human-like speech. Regarding the problem of understanding human speech, there is currently growing interest in moving beyond speech recognition (the task of transcribing the words in an audio stream) and towards…

Advancements in robust algorithm formulation for speaker identification of whispered speech

NASA Astrophysics Data System (ADS)

Fan, Xing

Whispered speech is an alternative speech production mode from neutral speech, which is used by talkers intentionally in natural conversational scenarios to protect privacy and to avoid certain content from being overheard/made public. Due to the profound differences between whispered and neutral speech in production mechanism and the absence of whispered adaptation data, the performance of speaker identification systems trained with neutral speech degrades significantly. This dissertation therefore focuses on developing a robust closed-set speaker recognition system for whispered speech by using no or limited whispered adaptation data from non-target speakers. This dissertation proposes the concept of "High''/"Low'' performance whispered data for the purpose of speaker identification. A variety of acoustic properties are identified that contribute to the quality of whispered data. An acoustic analysis is also conducted to compare the phoneme/speaker dependency of the differences between whispered and neutral data in the feature domain. The observations from those acoustic analysis are new in this area and also serve as a guidance for developing robust speaker identification systems for whispered speech. This dissertation further proposes two systems for speaker identification of whispered speech. One system focuses on front-end processing. A two-dimensional feature space is proposed to search for "Low''-quality performance based whispered utterances and separate feature mapping functions are applied to vowels and consonants respectively in order to retain the speaker's information shared between whispered and neutral speech. The other system focuses on speech-mode-independent model training. The proposed method generates pseudo whispered features from neutral features by using the statistical information contained in a whispered Universal Background model (UBM) trained from extra collected whispered data from non-target speakers. Four modeling methods are proposed for the transformation estimation in order to generate the pseudo whispered features. Both of the above two systems demonstrate a significant improvement over the baseline system on the evaluation data. This dissertation has therefore contributed to providing a scientific understanding of the differences between whispered and neutral speech as well as improved front-end processing and modeling method for speaker identification of whispered speech. Such advancements will ultimately contribute to improve the robustness of speech processing systems.

Alternative Speech Communication System for Persons with Severe Speech Disorders

NASA Astrophysics Data System (ADS)

Selouani, Sid-Ahmed; Sidi Yakoub, Mohammed; O'Shaughnessy, Douglas

2009-12-01

Assistive speech-enabled systems are proposed to help both French and English speaking persons with various speech disorders. The proposed assistive systems use automatic speech recognition (ASR) and speech synthesis in order to enhance the quality of communication. These systems aim at improving the intelligibility of pathologic speech making it as natural as possible and close to the original voice of the speaker. The resynthesized utterances use new basic units, a new concatenating algorithm and a grafting technique to correct the poorly pronounced phonemes. The ASR responses are uttered by the new speech synthesis system in order to convey an intelligible message to listeners. Experiments involving four American speakers with severe dysarthria and two Acadian French speakers with sound substitution disorders (SSDs) are carried out to demonstrate the efficiency of the proposed methods. An improvement of the Perceptual Evaluation of the Speech Quality (PESQ) value of 5% and more than 20% is achieved by the speech synthesis systems that deal with SSD and dysarthria, respectively.

Speech recognition: Acoustic-phonetic knowledge acquisition and representation

NASA Astrophysics Data System (ADS)

Zue, Victor W.

1988-09-01

The long-term research goal is to develop and implement speaker-independent continuous speech recognition systems. It is believed that the proper utilization of speech-specific knowledge is essential for such advanced systems. This research is thus directed toward the acquisition, quantification, and representation, of acoustic-phonetic and lexical knowledge, and the application of this knowledge to speech recognition algorithms. In addition, we are exploring new speech recognition alternatives based on artificial intelligence and connectionist techniques. We developed a statistical model for predicting the acoustic realization of stop consonants in various positions in the syllable template. A unification-based grammatical formalism was developed for incorporating this model into the lexical access algorithm. We provided an information-theoretic justification for the hierarchical structure of the syllable template. We analyzed segmented duration for vowels and fricatives in continuous speech. Based on contextual information, we developed durational models for vowels and fricatives that account for over 70 percent of the variance, using data from multiple, unknown speakers. We rigorously evaluated the ability of human spectrogram readers to identify stop consonants spoken by many talkers and in a variety of phonetic contexts. Incorporating the declarative knowledge used by the readers, we developed a knowledge-based system for stop identification. We achieved comparable system performance to that to the readers.

The influence of lexical characteristics and talker accent on the recognition of English words by speakers of Japanese.

PubMed

Yoneyama, Kiyoko; Munson, Benjamin

2017-02-01

Whether or not the influence of listeners' language proficiency on L2 speech recognition was affected by the structure of the lexicon was examined. This specific experiment examined the effect of word frequency (WF) and phonological neighborhood density (PND) on word recognition in native speakers of English and second-language (L2) speakers of English whose first language was Japanese. The stimuli included English words produced by a native speaker of English and English words produced by a native speaker of Japanese (i.e., with Japanese-accented English). The experiment was inspired by the finding of Imai, Flege, and Walley [(2005). J. Acoust. Soc. Am. 117, 896-907] that the influence of talker accent on speech intelligibility for L2 learners of English whose L1 is Spanish varies as a function of words' PND. In the currently study, significant interactions between stimulus accentedness and listener group on the accuracy and speed of spoken word recognition were found, as were significant effects of PND and WF on word-recognition accuracy. However, no significant three-way interaction among stimulus talker, listener group, and PND on either measure was found. Results are discussed in light of recent findings on cross-linguistic differences in the nature of the effects of PND on L2 phonological and lexical processing.

Parametric Representation of the Speaker's Lips for Multimodal Sign Language and Speech Recognition

NASA Astrophysics Data System (ADS)

Ryumin, D.; Karpov, A. A.

2017-05-01

In this article, we propose a new method for parametric representation of human's lips region. The functional diagram of the method is described and implementation details with the explanation of its key stages and features are given. The results of automatic detection of the regions of interest are illustrated. A speed of the method work using several computers with different performances is reported. This universal method allows applying parametrical representation of the speaker's lipsfor the tasks of biometrics, computer vision, machine learning, and automatic recognition of face, elements of sign languages, and audio-visual speech, including lip-reading.

An automatic speech recognition system with speaker-independent identification support

NASA Astrophysics Data System (ADS)

Caranica, Alexandru; Burileanu, Corneliu

2015-02-01

The novelty of this work relies on the application of an open source research software toolkit (CMU Sphinx) to train, build and evaluate a speech recognition system, with speaker-independent support, for voice-controlled hardware applications. Moreover, we propose to use the trained acoustic model to successfully decode offline voice commands on embedded hardware, such as an ARMv6 low-cost SoC, Raspberry PI. This type of single-board computer, mainly used for educational and research activities, can serve as a proof-of-concept software and hardware stack for low cost voice automation systems.

A preliminary analysis of human factors affecting the recognition accuracy of a discrete word recognizer for C3 systems

NASA Astrophysics Data System (ADS)

Yellen, H. W.

1983-03-01

Literature pertaining to Voice Recognition abounds with information relevant to the assessment of transitory speech recognition devices. In the past, engineering requirements have dictated the path this technology followed. But, other factors do exist that influence recognition accuracy. This thesis explores the impact of Human Factors on the successful recognition of speech, principally addressing the differences or variability among users. A Threshold Technology T-600 was used for a 100 utterance vocubalary to test 44 subjects. A statistical analysis was conducted on 5 generic categories of Human Factors: Occupational, Operational, Psychological, Physiological and Personal. How the equipment is trained and the experience level of the speaker were found to be key characteristics influencing recognition accuracy. To a lesser extent computer experience, time or week, accent, vital capacity and rate of air flow, speaker cooperativeness and anxiety were found to affect overall error rates.

Crossmodal and incremental perception of audiovisual cues to emotional speech.

PubMed

Barkhuysen, Pashiera; Krahmer, Emiel; Swerts, Marc

2010-01-01

In this article we report on two experiments about the perception of audiovisual cues to emotional speech. The article addresses two questions: 1) how do visual cues from a speaker's face to emotion relate to auditory cues, and (2) what is the recognition speed for various facial cues to emotion? Both experiments reported below are based on tests with video clips of emotional utterances collected via a variant of the well-known Velten method. More specifically, we recorded speakers who displayed positive or negative emotions, which were congruent or incongruent with the (emotional) lexical content of the uttered sentence. In order to test this, we conducted two experiments. The first experiment is a perception experiment in which Czech participants, who do not speak Dutch, rate the perceived emotional state of Dutch speakers in a bimodal (audiovisual) or a unimodal (audio- or vision-only) condition. It was found that incongruent emotional speech leads to significantly more extreme perceived emotion scores than congruent emotional speech, where the difference between congruent and incongruent emotional speech is larger for the negative than for the positive conditions. Interestingly, the largest overall differences between congruent and incongruent emotions were found for the audio-only condition, which suggests that posing an incongruent emotion has a particularly strong effect on the spoken realization of emotions. The second experiment uses a gating paradigm to test the recognition speed for various emotional expressions from a speaker's face. In this experiment participants were presented with the same clips as experiment I, but this time presented vision-only. The clips were shown in successive segments (gates) of increasing duration. Results show that participants are surprisingly accurate in their recognition of the various emotions, as they already reach high recognition scores in the first gate (after only 160 ms). Interestingly, the recognition scores raise faster for positive than negative conditions. Finally, the gating results suggest that incongruent emotions are perceived as more intense than congruent emotions, as the former get more extreme recognition scores than the latter, already after a short period of exposure.

Tone classification of syllable-segmented Thai speech based on multilayer perception

NASA Astrophysics Data System (ADS)

Satravaha, Nuttavudh; Klinkhachorn, Powsiri; Lass, Norman

2002-05-01

Thai is a monosyllabic tonal language that uses tone to convey lexical information about the meaning of a syllable. Thus to completely recognize a spoken Thai syllable, a speech recognition system not only has to recognize a base syllable but also must correctly identify a tone. Hence, tone classification of Thai speech is an essential part of a Thai speech recognition system. Thai has five distinctive tones (``mid,'' ``low,'' ``falling,'' ``high,'' and ``rising'') and each tone is represented by a single fundamental frequency (F0) pattern. However, several factors, including tonal coarticulation, stress, intonation, and speaker variability, affect the F0 pattern of a syllable in continuous Thai speech. In this study, an efficient method for tone classification of syllable-segmented Thai speech, which incorporates the effects of tonal coarticulation, stress, and intonation, as well as a method to perform automatic syllable segmentation, were developed. Acoustic parameters were used as the main discriminating parameters. The F0 contour of a segmented syllable was normalized by using a z-score transformation before being presented to a tone classifier. The proposed system was evaluated on 920 test utterances spoken by 8 speakers. A recognition rate of 91.36% was achieved by the proposed system.

Using Automatic Speech Recognition Technology with Elicited Oral Response Testing

ERIC Educational Resources Information Center

Cox, Troy L.; Davies, Randall S.

2012-01-01

This study examined the use of automatic speech recognition (ASR) scored elicited oral response (EOR) tests to assess the speaking ability of English language learners. It also examined the relationship between ASR-scored EOR and other language proficiency measures and the ability of the ASR to rate speakers without bias to gender or native…

Speech coding, reconstruction and recognition using acoustics and electromagnetic waves

DOEpatents

Holzrichter, J.F.; Ng, L.C.

1998-03-17

The use of EM radiation in conjunction with simultaneously recorded acoustic speech information enables a complete mathematical coding of acoustic speech. The methods include the forming of a feature vector for each pitch period of voiced speech and the forming of feature vectors for each time frame of unvoiced, as well as for combined voiced and unvoiced speech. The methods include how to deconvolve the speech excitation function from the acoustic speech output to describe the transfer function each time frame. The formation of feature vectors defining all acoustic speech units over well defined time frames can be used for purposes of speech coding, speech compression, speaker identification, language-of-speech identification, speech recognition, speech synthesis, speech translation, speech telephony, and speech teaching. 35 figs.

Speech coding, reconstruction and recognition using acoustics and electromagnetic waves

DOEpatents

Holzrichter, John F.; Ng, Lawrence C.

1998-01-01

The use of EM radiation in conjunction with simultaneously recorded acoustic speech information enables a complete mathematical coding of acoustic speech. The methods include the forming of a feature vector for each pitch period of voiced speech and the forming of feature vectors for each time frame of unvoiced, as well as for combined voiced and unvoiced speech. The methods include how to deconvolve the speech excitation function from the acoustic speech output to describe the transfer function each time frame. The formation of feature vectors defining all acoustic speech units over well defined time frames can be used for purposes of speech coding, speech compression, speaker identification, language-of-speech identification, speech recognition, speech synthesis, speech translation, speech telephony, and speech teaching.

Capturing patient information at nursing shift changes: methodological evaluation of speech recognition and information extraction

PubMed Central

Suominen, Hanna; Johnson, Maree; Zhou, Liyuan; Sanchez, Paula; Sirel, Raul; Basilakis, Jim; Hanlen, Leif; Estival, Dominique; Dawson, Linda; Kelly, Barbara

2015-01-01

Objective We study the use of speech recognition and information extraction to generate drafts of Australian nursing-handover documents. Methods Speech recognition correctness and clinicians’ preferences were evaluated using 15 recorder–microphone combinations, six documents, three speakers, Dragon Medical 11, and five survey/interview participants. Information extraction correctness evaluation used 260 documents, six-class classification for each word, two annotators, and the CRF++ conditional random field toolkit. Results A noise-cancelling lapel-microphone with a digital voice recorder gave the best correctness (79%). This microphone was also the most preferred option by all but one participant. Although the participants liked the small size of this recorder, their preference was for tablets that can also be used for document proofing and sign-off, among other tasks. Accented speech was harder to recognize than native language and a male speaker was detected better than a female speaker. Information extraction was excellent in filtering out irrelevant text (85% F1) and identifying text relevant to two classes (87% and 70% F1). Similarly to the annotators’ disagreements, there was confusion between the remaining three classes, which explains the modest 62% macro-averaged F1. Discussion We present evidence for the feasibility of speech recognition and information extraction to support clinicians’ in entering text and unlock its content for computerized decision-making and surveillance in healthcare. Conclusions The benefits of this automation include storing all information; making the drafts available and accessible almost instantly to everyone with authorized access; and avoiding information loss, delays, and misinterpretations inherent to using a ward clerk or transcription services. PMID:25336589

Statistical Evaluation of Biometric Evidence in Forensic Automatic Speaker Recognition

NASA Astrophysics Data System (ADS)

Drygajlo, Andrzej

Forensic speaker recognition is the process of determining if a specific individual (suspected speaker) is the source of a questioned voice recording (trace). This paper aims at presenting forensic automatic speaker recognition (FASR) methods that provide a coherent way of quantifying and presenting recorded voice as biometric evidence. In such methods, the biometric evidence consists of the quantified degree of similarity between speaker-dependent features extracted from the trace and speaker-dependent features extracted from recorded speech of a suspect. The interpretation of recorded voice as evidence in the forensic context presents particular challenges, including within-speaker (within-source) variability and between-speakers (between-sources) variability. Consequently, FASR methods must provide a statistical evaluation which gives the court an indication of the strength of the evidence given the estimated within-source and between-sources variabilities. This paper reports on the first ENFSI evaluation campaign through a fake case, organized by the Netherlands Forensic Institute (NFI), as an example, where an automatic method using the Gaussian mixture models (GMMs) and the Bayesian interpretation (BI) framework were implemented for the forensic speaker recognition task.

Increase in Speech Recognition due to Linguistic Mismatch Between Target and Masker Speech: Monolingual and Simultaneous Bilingual Performance

PubMed Central

Calandruccio, Lauren; Zhou, Haibo

2014-01-01

Purpose To examine whether improved speech recognition during linguistically mismatched target–masker experiments is due to linguistic unfamiliarity of the masker speech or linguistic dissimilarity between the target and masker speech. Method Monolingual English speakers (n = 20) and English–Greek simultaneous bilinguals (n = 20) listened to English sentences in the presence of competing English and Greek speech. Data were analyzed using mixed-effects regression models to determine differences in English recogition performance between the 2 groups and 2 masker conditions. Results Results indicated that English sentence recognition for monolinguals and simultaneous English–Greek bilinguals improved when the masker speech changed from competing English to competing Greek speech. Conclusion The improvement in speech recognition that has been observed for linguistically mismatched target–masker experiments cannot be simply explained by the masker language being linguistically unknown or unfamiliar to the listeners. Listeners can improve their speech recognition in linguistically mismatched target–masker experiments even when the listener is able to obtain meaningful linguistic information from the masker speech. PMID:24167230

Liberated Learning: Analysis of University Students' Perceptions and Experiences with Continuous Automated Speech Recognition

ERIC Educational Resources Information Center

Ryba, Ken; McIvor, Tom; Shakir, Maha; Paez, Di

2006-01-01

This study examined continuous automated speech recognition in the university lecture theatre. The participants were both native speakers of English (L1) and English as a second language students (L2) enrolled in an information systems course (Total N=160). After an initial training period, an L2 lecturer in information systems delivered three…

Speech coding, reconstruction and recognition using acoustics and electromagnetic waves

DOE Office of Scientific and Technical Information (OSTI.GOV)

Holzrichter, J.F.; Ng, L.C.

The use of EM radiation in conjunction with simultaneously recorded acoustic speech information enables a complete mathematical coding of acoustic speech. The methods include the forming of a feature vector for each pitch period of voiced speech and the forming of feature vectors for each time frame of unvoiced, as well as for combined voiced and unvoiced speech. The methods include how to deconvolve the speech excitation function from the acoustic speech output to describe the transfer function each time frame. The formation of feature vectors defining all acoustic speech units over well defined time frames can be used formore » purposes of speech coding, speech compression, speaker identification, language-of-speech identification, speech recognition, speech synthesis, speech translation, speech telephony, and speech teaching. 35 figs.« less

A language-familiarity effect for speaker discrimination without comprehension.

PubMed

Fleming, David; Giordano, Bruno L; Caldara, Roberto; Belin, Pascal

2014-09-23

The influence of language familiarity upon speaker identification is well established, to such an extent that it has been argued that "Human voice recognition depends on language ability" [Perrachione TK, Del Tufo SN, Gabrieli JDE (2011) Science 333(6042):595]. However, 7-mo-old infants discriminate speakers of their mother tongue better than they do foreign speakers [Johnson EK, Westrek E, Nazzi T, Cutler A (2011) Dev Sci 14(5):1002-1011] despite their limited speech comprehension abilities, suggesting that speaker discrimination may rely on familiarity with the sound structure of one's native language rather than the ability to comprehend speech. To test this hypothesis, we asked Chinese and English adult participants to rate speaker dissimilarity in pairs of sentences in English or Mandarin that were first time-reversed to render them unintelligible. Even in these conditions a language-familiarity effect was observed: Both Chinese and English listeners rated pairs of native-language speakers as more dissimilar than foreign-language speakers, despite their inability to understand the material. Our data indicate that the language familiarity effect is not based on comprehension but rather on familiarity with the phonology of one's native language. This effect may stem from a mechanism analogous to the "other-race" effect in face recognition.

Speech Recognition Scores of White and Black Student-Teacher Listeners for Black and White First Grade Speakers. Final Technical Report.

ERIC Educational Resources Information Center

Nober, E. Harris; Seymour, Harry N.

In order to investigate the possible consequences of dialectical differences in the classroom setting relative to the low income black and white first grade child and the prospective white middle-class teacher, 25 black and 25 white university listeners yielded speech recognition scores for 48 black and 48 white five-year-old urban school-children…

Speaker diarization system on the 2007 NIST rich transcription meeting recognition evaluation

NASA Astrophysics Data System (ADS)

Sun, Hanwu; Nwe, Tin Lay; Koh, Eugene Chin Wei; Bin, Ma; Li, Haizhou

2007-09-01

This paper presents a speaker diarization system developed at the Institute for Infocomm Research (I2R) for NIST Rich Transcription 2007 (RT-07) evaluation task. We describe in details our primary approaches for the speaker diarization on the Multiple Distant Microphones (MDM) conditions in conference room scenario. Our proposed system consists of six modules: 1). Least-mean squared (NLMS) adaptive filter for the speaker direction estimate via Time Difference of Arrival (TDOA), 2). An initial speaker clustering via two-stage TDOA histogram distribution quantization approach, 3). Multiple microphone speaker data alignment via GCC-PHAT Time Delay Estimate (TDE) among all the distant microphone channel signals, 4). A speaker clustering algorithm based on GMM modeling approach, 5). Non-speech removal via speech/non-speech verification mechanism and, 6). Silence removal via "Double-Layer Windowing"(DLW) method. We achieves error rate of 31.02% on the 2006 Spring (RT-06s) MDM evaluation task and a competitive overall error rate of 15.32% for the NIST Rich Transcription 2007 (RT-07) MDM evaluation task.

Towards Contactless Silent Speech Recognition Based on Detection of Active and Visible Articulators Using IR-UWB Radar

PubMed Central

Shin, Young Hoon; Seo, Jiwon

2016-01-01

People with hearing or speaking disabilities are deprived of the benefits of conventional speech recognition technology because it is based on acoustic signals. Recent research has focused on silent speech recognition systems that are based on the motions of a speaker’s vocal tract and articulators. Because most silent speech recognition systems use contact sensors that are very inconvenient to users or optical systems that are susceptible to environmental interference, a contactless and robust solution is hence required. Toward this objective, this paper presents a series of signal processing algorithms for a contactless silent speech recognition system using an impulse radio ultra-wide band (IR-UWB) radar. The IR-UWB radar is used to remotely and wirelessly detect motions of the lips and jaw. In order to extract the necessary features of lip and jaw motions from the received radar signals, we propose a feature extraction algorithm. The proposed algorithm noticeably improved speech recognition performance compared to the existing algorithm during our word recognition test with five speakers. We also propose a speech activity detection algorithm to automatically select speech segments from continuous input signals. Thus, speech recognition processing is performed only when speech segments are detected. Our testbed consists of commercial off-the-shelf radar products, and the proposed algorithms are readily applicable without designing specialized radar hardware for silent speech processing. PMID:27801867

Evaluating deep learning architectures for Speech Emotion Recognition.

PubMed

Fayek, Haytham M; Lech, Margaret; Cavedon, Lawrence

2017-08-01

Speech Emotion Recognition (SER) can be regarded as a static or dynamic classification problem, which makes SER an excellent test bed for investigating and comparing various deep learning architectures. We describe a frame-based formulation to SER that relies on minimal speech processing and end-to-end deep learning to model intra-utterance dynamics. We use the proposed SER system to empirically explore feed-forward and recurrent neural network architectures and their variants. Experiments conducted illuminate the advantages and limitations of these architectures in paralinguistic speech recognition and emotion recognition in particular. As a result of our exploration, we report state-of-the-art results on the IEMOCAP database for speaker-independent SER and present quantitative and qualitative assessments of the models' performances. Copyright © 2017 Elsevier Ltd. All rights reserved.

Did you or I say pretty, rude or brief? An ERP study of the effects of speaker's identity on emotional word processing.

PubMed

Pinheiro, Ana P; Rezaii, Neguine; Nestor, Paul G; Rauber, Andréia; Spencer, Kevin M; Niznikiewicz, Margaret

2016-02-01

During speech comprehension, multiple cues need to be integrated at a millisecond speed, including semantic information, as well as voice identity and affect cues. A processing advantage has been demonstrated for self-related stimuli when compared with non-self stimuli, and for emotional relative to neutral stimuli. However, very few studies investigated self-other speech discrimination and, in particular, how emotional valence and voice identity interactively modulate speech processing. In the present study we probed how the processing of words' semantic valence is modulated by speaker's identity (self vs. non-self voice). Sixteen healthy subjects listened to 420 prerecorded adjectives differing in voice identity (self vs. non-self) and semantic valence (neutral, positive and negative), while electroencephalographic data were recorded. Participants were instructed to decide whether the speech they heard was their own (self-speech condition), someone else's (non-self speech), or if they were unsure. The ERP results demonstrated interactive effects of speaker's identity and emotional valence on both early (N1, P2) and late (Late Positive Potential - LPP) processing stages: compared with non-self speech, self-speech with neutral valence elicited more negative N1 amplitude, self-speech with positive valence elicited more positive P2 amplitude, and self-speech with both positive and negative valence elicited more positive LPP. ERP differences between self and non-self speech occurred in spite of similar accuracy in the recognition of both types of stimuli. Together, these findings suggest that emotion and speaker's identity interact during speech processing, in line with observations of partially dependent processing of speech and speaker information. Copyright © 2016. Published by Elsevier Inc.

Automatic speech recognition research at NASA-Ames Research Center

NASA Technical Reports Server (NTRS)

Coler, Clayton R.; Plummer, Robert P.; Huff, Edward M.; Hitchcock, Myron H.

1977-01-01

A trainable acoustic pattern recognizer manufactured by Scope Electronics is presented. The voice command system VCS encodes speech by sampling 16 bandpass filters with center frequencies in the range from 200 to 5000 Hz. Variations in speaking rate are compensated for by a compression algorithm that subdivides each utterance into eight subintervals in such a way that the amount of spectral change within each subinterval is the same. The recorded filter values within each subinterval are then reduced to a 15-bit representation, giving a 120-bit encoding for each utterance. The VCS incorporates a simple recognition algorithm that utilizes five training samples of each word in a vocabulary of up to 24 words. The recognition rate of approximately 85 percent correct for untrained speakers and 94 percent correct for trained speakers was not considered adequate for flight systems use. Therefore, the built-in recognition algorithm was disabled, and the VCS was modified to transmit 120-bit encodings to an external computer for recognition.

I Hear You Eat and Speak: Automatic Recognition of Eating Condition and Food Type, Use-Cases, and Impact on ASR Performance

PubMed Central

Hantke, Simone; Weninger, Felix; Kurle, Richard; Ringeval, Fabien; Batliner, Anton; Mousa, Amr El-Desoky; Schuller, Björn

2016-01-01

We propose a new recognition task in the area of computational paralinguistics: automatic recognition of eating conditions in speech, i. e., whether people are eating while speaking, and what they are eating. To this end, we introduce the audio-visual iHEARu-EAT database featuring 1.6 k utterances of 30 subjects (mean age: 26.1 years, standard deviation: 2.66 years, gender balanced, German speakers), six types of food (Apple, Nectarine, Banana, Haribo Smurfs, Biscuit, and Crisps), and read as well as spontaneous speech, which is made publicly available for research purposes. We start with demonstrating that for automatic speech recognition (ASR), it pays off to know whether speakers are eating or not. We also propose automatic classification both by brute-forcing of low-level acoustic features as well as higher-level features related to intelligibility, obtained from an Automatic Speech Recogniser. Prediction of the eating condition was performed with a Support Vector Machine (SVM) classifier employed in a leave-one-speaker-out evaluation framework. Results show that the binary prediction of eating condition (i. e., eating or not eating) can be easily solved independently of the speaking condition; the obtained average recalls are all above 90%. Low-level acoustic features provide the best performance on spontaneous speech, which reaches up to 62.3% average recall for multi-way classification of the eating condition, i. e., discriminating the six types of food, as well as not eating. The early fusion of features related to intelligibility with the brute-forced acoustic feature set improves the performance on read speech, reaching a 66.4% average recall for the multi-way classification task. Analysing features and classifier errors leads to a suitable ordinal scale for eating conditions, on which automatic regression can be performed with up to 56.2% determination coefficient. PMID:27176486

Ongoing slow oscillatory phase modulates speech intelligibility in cooperation with motor cortical activity.

PubMed

Onojima, Takayuki; Kitajo, Keiichi; Mizuhara, Hiroaki

2017-01-01

Neural oscillation is attracting attention as an underlying mechanism for speech recognition. Speech intelligibility is enhanced by the synchronization of speech rhythms and slow neural oscillation, which is typically observed as human scalp electroencephalography (EEG). In addition to the effect of neural oscillation, it has been proposed that speech recognition is enhanced by the identification of a speaker's motor signals, which are used for speech production. To verify the relationship between the effect of neural oscillation and motor cortical activity, we measured scalp EEG, and simultaneous EEG and functional magnetic resonance imaging (fMRI) during a speech recognition task in which participants were required to recognize spoken words embedded in noise sound. We proposed an index to quantitatively evaluate the EEG phase effect on behavioral performance. The results showed that the delta and theta EEG phase before speech inputs modulated the participant's response time when conducting speech recognition tasks. The simultaneous EEG-fMRI experiment showed that slow EEG activity was correlated with motor cortical activity. These results suggested that the effect of the slow oscillatory phase was associated with the activity of the motor cortex during speech recognition.

Speech to Text Translation for Malay Language

NASA Astrophysics Data System (ADS)

Al-khulaidi, Rami Ali; Akmeliawati, Rini

2017-11-01

The speech recognition system is a front end and a back-end process that receives an audio signal uttered by a speaker and converts it into a text transcription. The speech system can be used in several fields including: therapeutic technology, education, social robotics and computer entertainments. In most cases in control tasks, which is the purpose of proposing our system, wherein the speed of performance and response concern as the system should integrate with other controlling platforms such as in voiced controlled robots. Therefore, the need for flexible platforms, that can be easily edited to jibe with functionality of the surroundings, came to the scene; unlike other software programs that require recording audios and multiple training for every entry such as MATLAB and Phoenix. In this paper, a speech recognition system for Malay language is implemented using Microsoft Visual Studio C#. 90 (ninety) Malay phrases were tested by 10 (ten) speakers from both genders in different contexts. The result shows that the overall accuracy (calculated from Confusion Matrix) is satisfactory as it is 92.69%.

Recognizing speech in a novel accent: the motor theory of speech perception reframed.

PubMed

Moulin-Frier, Clément; Arbib, Michael A

2013-08-01

The motor theory of speech perception holds that we perceive the speech of another in terms of a motor representation of that speech. However, when we have learned to recognize a foreign accent, it seems plausible that recognition of a word rarely involves reconstruction of the speech gestures of the speaker rather than the listener. To better assess the motor theory and this observation, we proceed in three stages. Part 1 places the motor theory of speech perception in a larger framework based on our earlier models of the adaptive formation of mirror neurons for grasping, and for viewing extensions of that mirror system as part of a larger system for neuro-linguistic processing, augmented by the present consideration of recognizing speech in a novel accent. Part 2 then offers a novel computational model of how a listener comes to understand the speech of someone speaking the listener's native language with a foreign accent. The core tenet of the model is that the listener uses hypotheses about the word the speaker is currently uttering to update probabilities linking the sound produced by the speaker to phonemes in the native language repertoire of the listener. This, on average, improves the recognition of later words. This model is neutral regarding the nature of the representations it uses (motor vs. auditory). It serve as a reference point for the discussion in Part 3, which proposes a dual-stream neuro-linguistic architecture to revisits claims for and against the motor theory of speech perception and the relevance of mirror neurons, and extracts some implications for the reframing of the motor theory.

V2S: Voice to Sign Language Translation System for Malaysian Deaf People

NASA Astrophysics Data System (ADS)

Mean Foong, Oi; Low, Tang Jung; La, Wai Wan

The process of learning and understand the sign language may be cumbersome to some, and therefore, this paper proposes a solution to this problem by providing a voice (English Language) to sign language translation system using Speech and Image processing technique. Speech processing which includes Speech Recognition is the study of recognizing the words being spoken, regardless of whom the speaker is. This project uses template-based recognition as the main approach in which the V2S system first needs to be trained with speech pattern based on some generic spectral parameter set. These spectral parameter set will then be stored as template in a database. The system will perform the recognition process through matching the parameter set of the input speech with the stored templates to finally display the sign language in video format. Empirical results show that the system has 80.3% recognition rate.

A new time-adaptive discrete bionic wavelet transform for enhancing speech from adverse noise environment

NASA Astrophysics Data System (ADS)

Palaniswamy, Sumithra; Duraisamy, Prakash; Alam, Mohammad Showkat; Yuan, Xiaohui

2012-04-01

Automatic speech processing systems are widely used in everyday life such as mobile communication, speech and speaker recognition, and for assisting the hearing impaired. In speech communication systems, the quality and intelligibility of speech is of utmost importance for ease and accuracy of information exchange. To obtain an intelligible speech signal and one that is more pleasant to listen, noise reduction is essential. In this paper a new Time Adaptive Discrete Bionic Wavelet Thresholding (TADBWT) scheme is proposed. The proposed technique uses Daubechies mother wavelet to achieve better enhancement of speech from additive non- stationary noises which occur in real life such as street noise and factory noise. Due to the integration of human auditory system model into the wavelet transform, bionic wavelet transform (BWT) has great potential for speech enhancement which may lead to a new path in speech processing. In the proposed technique, at first, discrete BWT is applied to noisy speech to derive TADBWT coefficients. Then the adaptive nature of the BWT is captured by introducing a time varying linear factor which updates the coefficients at each scale over time. This approach has shown better performance than the existing algorithms at lower input SNR due to modified soft level dependent thresholding on time adaptive coefficients. The objective and subjective test results confirmed the competency of the TADBWT technique. The effectiveness of the proposed technique is also evaluated for speaker recognition task under noisy environment. The recognition results show that the TADWT technique yields better performance when compared to alternate methods specifically at lower input SNR.

Development of equally intelligible Telugu sentence-lists to test speech recognition in noise.

PubMed

Tanniru, Kishore; Narne, Vijaya Kumar; Jain, Chandni; Konadath, Sreeraj; Singh, Niraj Kumar; Sreenivas, K J Ramadevi; K, Anusha

2017-09-01

To develop sentence lists in the Telugu language for the assessment of speech recognition threshold (SRT) in the presence of background noise through identification of the mean signal-to-noise ratio required to attain a 50% sentence recognition score (SRTn). This study was conducted in three phases. The first phase involved the selection and recording of Telugu sentences. In the second phase, 20 lists, each consisting of 10 sentences with equal intelligibility, were formulated using a numerical optimisation procedure. In the third phase, the SRTn of the developed lists was estimated using adaptive procedures on individuals with normal hearing. A total of 68 native Telugu speakers with normal hearing participated in the study. Of these, 18 (including the speakers) performed on various subjective measures in first phase, 20 performed on sentence/word recognition in noise for second phase and 30 participated in the list equivalency procedures in third phase. In all, 15 lists of comparable difficulty were formulated as test material. The mean SRTn across these lists corresponded to -2.74 (SD = 0.21). The developed sentence lists provided a valid and reliable tool to measure SRTn in Telugu native speakers.

Open-set speaker identification with diverse-duration speech data

NASA Astrophysics Data System (ADS)

Karadaghi, Rawande; Hertlein, Heinz; Ariyaeeinia, Aladdin

2015-05-01

The concern in this paper is an important category of applications of open-set speaker identification in criminal investigation, which involves operating with short and varied duration speech. The study presents investigations into the adverse effects of such an operating condition on the accuracy of open-set speaker identification, based on both GMMUBM and i-vector approaches. The experiments are conducted using a protocol developed for the identification task, based on the NIST speaker recognition evaluation corpus of 2008. In order to closely cover the real-world operating conditions in the considered application area, the study includes experiments with various combinations of training and testing data duration. The paper details the characteristics of the experimental investigations conducted and provides a thorough analysis of the results obtained.

Robust Speaker Authentication Based on Combined Speech and Voiceprint Recognition

NASA Astrophysics Data System (ADS)

Malcangi, Mario

2009-08-01

Personal authentication is becoming increasingly important in many applications that have to protect proprietary data. Passwords and personal identification numbers (PINs) prove not to be robust enough to ensure that unauthorized people do not use them. Biometric authentication technology may offer a secure, convenient, accurate solution but sometimes fails due to its intrinsically fuzzy nature. This research aims to demonstrate that combining two basic speech processing methods, voiceprint identification and speech recognition, can provide a very high degree of robustness, especially if fuzzy decision logic is used.

Talker and accent variability effects on spoken word recognition

NASA Astrophysics Data System (ADS)

Nyang, Edna E.; Rogers, Catherine L.; Nishi, Kanae

2003-04-01

A number of studies have shown that words in a list are recognized less accurately in noise and with longer response latencies when they are spoken by multiple talkers, rather than a single talker. These results have been interpreted as support for an exemplar-based model of speech perception, in which it is assumed that detailed information regarding the speaker's voice is preserved in memory and used in recognition, rather than being eliminated via normalization. In the present study, the effects of varying both accent and talker are investigated using lists of words spoken by (a) a single native English speaker, (b) six native English speakers, (c) three native English speakers and three Japanese-accented English speakers. Twelve /hVd/ words were mixed with multi-speaker babble at three signal-to-noise ratios (+10, +5, and 0 dB) to create the word lists. Native English-speaking listeners' percent-correct recognition for words produced by native English speakers across the three talker conditions (single talker native, multi-talker native, and multi-talker mixed native and non-native) and three signal-to-noise ratios will be compared to determine whether sources of speaker variability other than voice alone add to the processing demands imposed by simple (i.e., single accent) speaker variability in spoken word recognition.

An articulatorily constrained, maximum entropy approach to speech recognition and speech coding

DOE Office of Scientific and Technical Information (OSTI.GOV)

Hogden, J.

Hidden Markov models (HMM`s) are among the most popular tools for performing computer speech recognition. One of the primary reasons that HMM`s typically outperform other speech recognition techniques is that the parameters used for recognition are determined by the data, not by preconceived notions of what the parameters should be. This makes HMM`s better able to deal with intra- and inter-speaker variability despite the limited knowledge of how speech signals vary and despite the often limited ability to correctly formulate rules describing variability and invariance in speech. In fact, it is often the case that when HMM parameter values aremore » constrained using the limited knowledge of speech, recognition performance decreases. However, the structure of an HMM has little in common with the mechanisms underlying speech production. Here, the author argues that by using probabilistic models that more accurately embody the process of speech production, he can create models that have all the advantages of HMM`s, but that should more accurately capture the statistical properties of real speech samples--presumably leading to more accurate speech recognition. The model he will discuss uses the fact that speech articulators move smoothly and continuously. Before discussing how to use articulatory constraints, he will give a brief description of HMM`s. This will allow him to highlight the similarities and differences between HMM`s and the proposed technique.« less

Improving language models for radiology speech recognition.

PubMed

Paulett, John M; Langlotz, Curtis P

2009-02-01

Speech recognition systems have become increasingly popular as a means to produce radiology reports, for reasons both of efficiency and of cost. However, the suboptimal recognition accuracy of these systems can affect the productivity of the radiologists creating the text reports. We analyzed a database of over two million de-identified radiology reports to determine the strongest determinants of word frequency. Our results showed that body site and imaging modality had a similar influence on the frequency of words and of three-word phrases as did the identity of the speaker. These findings suggest that the accuracy of speech recognition systems could be significantly enhanced by further tailoring their language models to body site and imaging modality, which are readily available at the time of report creation.

DARPA TIMIT acoustic-phonetic continous speech corpus CD-ROM. NIST speech disc 1-1.1

NASA Astrophysics Data System (ADS)

Garofolo, J. S.; Lamel, L. F.; Fisher, W. M.; Fiscus, J. G.; Pallett, D. S.

1993-02-01

The Texas Instruments/Massachusetts Institute of Technology (TIMIT) corpus of read speech has been designed to provide speech data for the acquisition of acoustic-phonetic knowledge and for the development and evaluation of automatic speech recognition systems. TIMIT contains speech from 630 speakers representing 8 major dialect divisions of American English, each speaking 10 phonetically-rich sentences. The TIMIT corpus includes time-aligned orthographic, phonetic, and word transcriptions, as well as speech waveform data for each spoken sentence. The release of TIMIT contains several improvements over the Prototype CD-ROM released in December, 1988: (1) full 630-speaker corpus, (2) checked and corrected transcriptions, (3) word-alignment transcriptions, (4) NIST SPHERE-headered waveform files and header manipulation software, (5) phonemic dictionary, (6) new test and training subsets balanced for dialectal and phonetic coverage, and (7) more extensive documentation.

Seeing a singer helps comprehension of the song's lyrics.

PubMed

Jesse, Alexandra; Massaro, Dominic W

2010-06-01

When listening to speech, we often benefit when also seeing the speaker's face. If this advantage is not domain specific for speech, the recognition of sung lyrics should also benefit from seeing the singer's face. By independently varying the sight and sound of the lyrics, we found a substantial comprehension benefit of seeing a singer. This benefit was robust across participants, lyrics, and repetition of the test materials. This benefit was much larger than the benefit for sung lyrics obtained in previous research, which had not provided the visual information normally present in singing. Given that the comprehension of sung lyrics benefits from seeing the singer, just like speech comprehension benefits from seeing the speaker, both speech and music perception appear to be multisensory processes.

Free Field Word recognition test in the presence of noise in normal hearing adults.

PubMed

Almeida, Gleide Viviani Maciel; Ribas, Angela; Calleros, Jorge

In ideal listening situations, subjects with normal hearing can easily understand speech, as can many subjects who have a hearing loss. To present the validation of the Word Recognition Test in a Free Field in the Presence of Noise in normal-hearing adults. Sample consisted of 100 healthy adults over 18 years of age with normal hearing. After pure tone audiometry, a speech recognition test was applied in free field condition with monosyllables and disyllables, with standardized material in three listening situations: optimal listening condition (no noise), with a signal to noise ratio of 0dB and a signal to noise ratio of -10dB. For these tests, an environment in calibrated free field was arranged where speech was presented to the subject being tested from two speakers located at 45°, and noise from a third speaker, located at 180°. All participants had speech audiometry results in the free field between 88% and 100% in the three listening situations. Word Recognition Test in Free Field in the Presence of Noise proved to be easy to be organized and applied. The results of the test validation suggest that individuals with normal hearing should get between 88% and 100% of the stimuli correct. The test can be an important tool in measuring noise interference on the speech perception abilities. Copyright © 2016 Associação Brasileira de Otorrinolaringologia e Cirurgia Cérvico-Facial. Published by Elsevier Editora Ltda. All rights reserved.

Watch what you say, your computer might be listening: A review of automated speech recognition

NASA Technical Reports Server (NTRS)

Degennaro, Stephen V.

1991-01-01

Spoken language is the most convenient and natural means by which people interact with each other and is, therefore, a promising candidate for human-machine interactions. Speech also offers an additional channel for hands-busy applications, complementing the use of motor output channels for control. Current speech recognition systems vary considerably across a number of important characteristics, including vocabulary size, speaking mode, training requirements for new speakers, robustness to acoustic environments, and accuracy. Algorithmically, these systems range from rule-based techniques through more probabilistic or self-learning approaches such as hidden Markov modeling and neural networks. This tutorial begins with a brief summary of the relevant features of current speech recognition systems and the strengths and weaknesses of the various algorithmic approaches.

Visual speech influences speech perception immediately but not automatically.

PubMed

Mitterer, Holger; Reinisch, Eva

2017-02-01

Two experiments examined the time course of the use of auditory and visual speech cues to spoken word recognition using an eye-tracking paradigm. Results of the first experiment showed that the use of visual speech cues from lipreading is reduced if concurrently presented pictures require a division of attentional resources. This reduction was evident even when listeners' eye gaze was on the speaker rather than the (static) pictures. Experiment 2 used a deictic hand gesture to foster attention to the speaker. At the same time, the visual processing load was reduced by keeping the visual display constant over a fixed number of successive trials. Under these conditions, the visual speech cues from lipreading were used. Moreover, the eye-tracking data indicated that visual information was used immediately and even earlier than auditory information. In combination, these data indicate that visual speech cues are not used automatically, but if they are used, they are used immediately.

From Birdsong to Human Speech Recognition: Bayesian Inference on a Hierarchy of Nonlinear Dynamical Systems

PubMed Central

Yildiz, Izzet B.; von Kriegstein, Katharina; Kiebel, Stefan J.

2013-01-01

Our knowledge about the computational mechanisms underlying human learning and recognition of sound sequences, especially speech, is still very limited. One difficulty in deciphering the exact means by which humans recognize speech is that there are scarce experimental findings at a neuronal, microscopic level. Here, we show that our neuronal-computational understanding of speech learning and recognition may be vastly improved by looking at an animal model, i.e., the songbird, which faces the same challenge as humans: to learn and decode complex auditory input, in an online fashion. Motivated by striking similarities between the human and songbird neural recognition systems at the macroscopic level, we assumed that the human brain uses the same computational principles at a microscopic level and translated a birdsong model into a novel human sound learning and recognition model with an emphasis on speech. We show that the resulting Bayesian model with a hierarchy of nonlinear dynamical systems can learn speech samples such as words rapidly and recognize them robustly, even in adverse conditions. In addition, we show that recognition can be performed even when words are spoken by different speakers and with different accents—an everyday situation in which current state-of-the-art speech recognition models often fail. The model can also be used to qualitatively explain behavioral data on human speech learning and derive predictions for future experiments. PMID:24068902

From birdsong to human speech recognition: bayesian inference on a hierarchy of nonlinear dynamical systems.

PubMed

Yildiz, Izzet B; von Kriegstein, Katharina; Kiebel, Stefan J

2013-01-01

Our knowledge about the computational mechanisms underlying human learning and recognition of sound sequences, especially speech, is still very limited. One difficulty in deciphering the exact means by which humans recognize speech is that there are scarce experimental findings at a neuronal, microscopic level. Here, we show that our neuronal-computational understanding of speech learning and recognition may be vastly improved by looking at an animal model, i.e., the songbird, which faces the same challenge as humans: to learn and decode complex auditory input, in an online fashion. Motivated by striking similarities between the human and songbird neural recognition systems at the macroscopic level, we assumed that the human brain uses the same computational principles at a microscopic level and translated a birdsong model into a novel human sound learning and recognition model with an emphasis on speech. We show that the resulting Bayesian model with a hierarchy of nonlinear dynamical systems can learn speech samples such as words rapidly and recognize them robustly, even in adverse conditions. In addition, we show that recognition can be performed even when words are spoken by different speakers and with different accents-an everyday situation in which current state-of-the-art speech recognition models often fail. The model can also be used to qualitatively explain behavioral data on human speech learning and derive predictions for future experiments.

Embedding speech into virtual realities

NASA Technical Reports Server (NTRS)

Bohn, Christian-Arved; Krueger, Wolfgang

1993-01-01

In this work a speaker-independent speech recognition system is presented, which is suitable for implementation in Virtual Reality applications. The use of an artificial neural network in connection with a special compression of the acoustic input leads to a system, which is robust, fast, easy to use and needs no additional hardware, beside a common VR-equipment.

Noise-immune multisensor transduction of speech

NASA Astrophysics Data System (ADS)

Viswanathan, Vishu R.; Henry, Claudia M.; Derr, Alan G.; Roucos, Salim; Schwartz, Richard M.

1986-08-01

Two types of configurations of multiple sensors were developed, tested and evaluated in speech recognition application for robust performance in high levels of acoustic background noise: One type combines the individual sensor signals to provide a single speech signal input, and the other provides several parallel inputs. For single-input systems, several configurations of multiple sensors were developed and tested. Results from formal speech intelligibility and quality tests in simulated fighter aircraft cockpit noise show that each of the two-sensor configurations tested outperforms the constituent individual sensors in high noise. Also presented are results comparing the performance of two-sensor configurations and individual sensors in speaker-dependent, isolated-word speech recognition tests performed using a commercial recognizer (Verbex 4000) in simulated fighter aircraft cockpit noise.

MARTI: man-machine animation real-time interface

NASA Astrophysics Data System (ADS)

Jones, Christian M.; Dlay, Satnam S.

1997-05-01

The research introduces MARTI (man-machine animation real-time interface) for the realization of natural human-machine interfacing. The system uses simple vocal sound-tracks of human speakers to provide lip synchronization of computer graphical facial models. We present novel research in a number of engineering disciplines, which include speech recognition, facial modeling, and computer animation. This interdisciplinary research utilizes the latest, hybrid connectionist/hidden Markov model, speech recognition system to provide very accurate phone recognition and timing for speaker independent continuous speech, and expands on knowledge from the animation industry in the development of accurate facial models and automated animation. The research has many real-world applications which include the provision of a highly accurate and 'natural' man-machine interface to assist user interactions with computer systems and communication with one other using human idiosyncrasies; a complete special effects and animation toolbox providing automatic lip synchronization without the normal constraints of head-sets, joysticks, and skilled animators; compression of video data to well below standard telecommunication channel bandwidth for video communications and multi-media systems; assisting speech training and aids for the handicapped; and facilitating player interaction for 'video gaming' and 'virtual worlds.' MARTI has introduced a new level of realism to man-machine interfacing and special effect animation which has been previously unseen.

Working memory capacity may influence perceived effort during aided speech recognition in noise.

PubMed

Rudner, Mary; Lunner, Thomas; Behrens, Thomas; Thorén, Elisabet Sundewall; Rönnberg, Jerker

2012-09-01

Recently there has been interest in using subjective ratings as a measure of perceived effort during speech recognition in noise. Perceived effort may be an indicator of cognitive load. Thus, subjective effort ratings during speech recognition in noise may covary both with signal-to-noise ratio (SNR) and individual cognitive capacity. The present study investigated the relation between subjective ratings of the effort involved in listening to speech in noise, speech recognition performance, and individual working memory (WM) capacity in hearing impaired hearing aid users. In two experiments, participants with hearing loss rated perceived effort during aided speech perception in noise. Noise type and SNR were manipulated in both experiments, and in the second experiment hearing aid compression release settings were also manipulated. Speech recognition performance was measured along with WM capacity. There were 46 participants in all with bilateral mild to moderate sloping hearing loss. In Experiment 1 there were 16 native Danish speakers (eight women and eight men) with a mean age of 63.5 yr (SD = 12.1) and average pure tone (PT) threshold of 47. 6 dB (SD = 9.8). In Experiment 2 there were 30 native Swedish speakers (19 women and 11 men) with a mean age of 70 yr (SD = 7.8) and average PT threshold of 45.8 dB (SD = 6.6). A visual analog scale (VAS) was used for effort rating in both experiments. In Experiment 1, effort was rated at individually adapted SNRs while in Experiment 2 it was rated at fixed SNRs. Speech recognition in noise performance was measured using adaptive procedures in both experiments with Dantale II sentences in Experiment 1 and Hagerman sentences in Experiment 2. WM capacity was measured using a letter-monitoring task in Experiment 1 and the reading span task in Experiment 2. In both experiments, there was a strong and significant relation between rated effort and SNR that was independent of individual WM capacity, whereas the relation between rated effort and noise type seemed to be influenced by individual WM capacity. Experiment 2 showed that hearing aid compression setting influenced rated effort. Subjective ratings of the effort involved in speech recognition in noise reflect SNRs, and individual cognitive capacity seems to influence relative rating of noise type. American Academy of Audiology.

Automatic speech recognition (ASR) based approach for speech therapy of aphasic patients: A review

NASA Astrophysics Data System (ADS)

Jamal, Norezmi; Shanta, Shahnoor; Mahmud, Farhanahani; Sha'abani, MNAH

2017-09-01

This paper reviews the state-of-the-art an automatic speech recognition (ASR) based approach for speech therapy of aphasic patients. Aphasia is a condition in which the affected person suffers from speech and language disorder resulting from a stroke or brain injury. Since there is a growing body of evidence indicating the possibility of improving the symptoms at an early stage, ASR based solutions are increasingly being researched for speech and language therapy. ASR is a technology that transfers human speech into transcript text by matching with the system's library. This is particularly useful in speech rehabilitation therapies as they provide accurate, real-time evaluation for speech input from an individual with speech disorder. ASR based approaches for speech therapy recognize the speech input from the aphasic patient and provide real-time feedback response to their mistakes. However, the accuracy of ASR is dependent on many factors such as, phoneme recognition, speech continuity, speaker and environmental differences as well as our depth of knowledge on human language understanding. Hence, the review examines recent development of ASR technologies and its performance for individuals with speech and language disorders.

How Accurately Can the Google Web Speech API Recognize and Transcribe Japanese L2 English Learners' Oral Production?

ERIC Educational Resources Information Center

Ashwell, Tim; Elam, Jesse R.

2017-01-01

The ultimate aim of our research project was to use the Google Web Speech API to automate scoring of elicited imitation (EI) tests. However, in order to achieve this goal, we had to take a number of preparatory steps. We needed to assess how accurate this speech recognition tool is in recognizing native speakers' production of the test items; we…

Voice input/output capabilities at Perception Technology Corporation

NASA Technical Reports Server (NTRS)

Ferber, Leon A.

1977-01-01

Condensed resumes of key company personnel at the Perception Technology Corporation are presented. The staff possesses recognition, speech synthesis, speaker authentication, and language identification. Hardware and software engineers' capabilities are included.

Multimedia Classifier

NASA Astrophysics Data System (ADS)

Costache, G. N.; Gavat, I.

2004-09-01

Along with the aggressive growing of the amount of digital data available (text, audio samples, digital photos and digital movies joined all in the multimedia domain) the need for classification, recognition and retrieval of this kind of data became very important. In this paper will be presented a system structure to handle multimedia data based on a recognition perspective. The main processing steps realized for the interesting multimedia objects are: first, the parameterization, by analysis, in order to obtain a description based on features, forming the parameter vector; second, a classification, generally with a hierarchical structure to make the necessary decisions. For audio signals, both speech and music, the derived perceptual features are the melcepstral (MFCC) and the perceptual linear predictive (PLP) coefficients. For images, the derived features are the geometric parameters of the speaker mouth. The hierarchical classifier consists generally in a clustering stage, based on the Kohonnen Self-Organizing Maps (SOM) and a final stage, based on a powerful classification algorithm called Support Vector Machines (SVM). The system, in specific variants, is applied with good results in two tasks: the first, is a bimodal speech recognition which uses features obtained from speech signal fused to features obtained from speaker's image and the second is a music retrieval from large music database.

Sensory Intelligence for Extraction of an Abstract Auditory Rule: A Cross-Linguistic Study.

PubMed

Guo, Xiao-Tao; Wang, Xiao-Dong; Liang, Xiu-Yuan; Wang, Ming; Chen, Lin

2018-02-21

In a complex linguistic environment, while speech sounds can greatly vary, some shared features are often invariant. These invariant features constitute so-called abstract auditory rules. Our previous study has shown that with auditory sensory intelligence, the human brain can automatically extract the abstract auditory rules in the speech sound stream, presumably serving as the neural basis for speech comprehension. However, whether the sensory intelligence for extraction of abstract auditory rules in speech is inherent or experience-dependent remains unclear. To address this issue, we constructed a complex speech sound stream using auditory materials in Mandarin Chinese, in which syllables had a flat lexical tone but differed in other acoustic features to form an abstract auditory rule. This rule was occasionally and randomly violated by the syllables with the rising, dipping or falling tone. We found that both Chinese and foreign speakers detected the violations of the abstract auditory rule in the speech sound stream at a pre-attentive stage, as revealed by the whole-head recordings of mismatch negativity (MMN) in a passive paradigm. However, MMNs peaked earlier in Chinese speakers than in foreign speakers. Furthermore, Chinese speakers showed different MMN peak latencies for the three deviant types, which paralleled recognition points. These findings indicate that the sensory intelligence for extraction of abstract auditory rules in speech sounds is innate but shaped by language experience. Copyright © 2018 IBRO. Published by Elsevier Ltd. All rights reserved.

Effects of various electrode configurations on music perception, intonation and speaker gender identification.

PubMed

Landwehr, Markus; Fürstenberg, Dirk; Walger, Martin; von Wedel, Hasso; Meister, Hartmut

2014-01-01

Advances in speech coding strategies and electrode array designs for cochlear implants (CIs) predominantly aim at improving speech perception. Current efforts are also directed at transmitting appropriate cues of the fundamental frequency (F0) to the auditory nerve with respect to speech quality, prosody, and music perception. The aim of this study was to examine the effects of various electrode configurations and coding strategies on speech intonation identification, speaker gender identification, and music quality rating. In six MED-EL CI users electrodes were selectively deactivated in order to simulate different insertion depths and inter-electrode distances when using the high definition continuous interleaved sampling (HDCIS) and fine structure processing (FSP) speech coding strategies. Identification of intonation and speaker gender was determined and music quality rating was assessed. For intonation identification HDCIS was robust against the different electrode configurations, whereas fine structure processing showed significantly worse results when a short electrode depth was simulated. In contrast, speaker gender recognition was not affected by electrode configuration or speech coding strategy. Music quality rating was sensitive to electrode configuration. In conclusion, the three experiments revealed different outcomes, even though they all addressed the reception of F0 cues. Rapid changes in F0, as seen with intonation, were the most sensitive to electrode configurations and coding strategies. In contrast, electrode configurations and coding strategies did not show large effects when F0 information was available over a longer time period, as seen with speaker gender. Music quality relies on additional spectral cues other than F0, and was poorest when a shallow insertion was simulated.

Adaptation to nonlinear frequency compression in normal-hearing adults: a comparison of training approaches.

PubMed

Dickinson, Ann-Marie; Baker, Richard; Siciliano, Catherine; Munro, Kevin J

2014-10-01

To identify which training approach, if any, is most effective for improving perception of frequency-compressed speech. A between-subject design using repeated measures. Forty young adults with normal hearing were randomly allocated to one of four groups: a training group (sentence or consonant) or a control group (passive exposure or test-only). Test and training material differed in terms of material and speaker. On average, sentence training and passive exposure led to significantly improved sentence recognition (11.0% and 11.7%, respectively) compared with the consonant training group (2.5%) and test-only group (0.4%), whilst, consonant training led to significantly improved consonant recognition (8.8%) compared with the sentence training group (1.9%), passive exposure group (2.8%), and test-only group (0.8%). Sentence training led to improved sentence recognition, whilst consonant training led to improved consonant recognition. This suggests learning transferred between speakers and material but not stimuli. Passive exposure to sentence material led to an improvement in sentence recognition that was equivalent to gains from active training. This suggests that it may be possible to adapt passively to frequency-compressed speech.

The impact of compression of speech signal, background noise and acoustic disturbances on the effectiveness of speaker identification

NASA Astrophysics Data System (ADS)

Kamiński, K.; Dobrowolski, A. P.

2017-04-01

The paper presents the architecture and the results of optimization of selected elements of the Automatic Speaker Recognition (ASR) system that uses Gaussian Mixture Models (GMM) in the classification process. Optimization was performed on the process of selection of individual characteristics using the genetic algorithm and the parameters of Gaussian distributions used to describe individual voices. The system that was developed was tested in order to evaluate the impact of different compression methods used, among others, in landline, mobile, and VoIP telephony systems, on effectiveness of the speaker identification. Also, the results were presented of effectiveness of speaker identification at specific levels of noise with the speech signal and occurrence of other disturbances that could appear during phone calls, which made it possible to specify the spectrum of applications of the presented ASR system.

Constraints on the Transfer of Perceptual Learning in Accented Speech

PubMed Central

Eisner, Frank; Melinger, Alissa; Weber, Andrea

2013-01-01

The perception of speech sounds can be re-tuned through a mechanism of lexically driven perceptual learning after exposure to instances of atypical speech production. This study asked whether this re-tuning is sensitive to the position of the atypical sound within the word. We investigated perceptual learning using English voiced stop consonants, which are commonly devoiced in word-final position by Dutch learners of English. After exposure to a Dutch learner’s productions of devoiced stops in word-final position (but not in any other positions), British English (BE) listeners showed evidence of perceptual learning in a subsequent cross-modal priming task, where auditory primes with devoiced final stops (e.g., “seed”, pronounced [si:th]), facilitated recognition of visual targets with voiced final stops (e.g., SEED). In Experiment 1, this learning effect generalized to test pairs where the critical contrast was in word-initial position, e.g., auditory primes such as “town” facilitated recognition of visual targets like DOWN. Control listeners, who had not heard any stops by the speaker during exposure, showed no learning effects. The generalization to word-initial position did not occur when participants had also heard correctly voiced, word-initial stops during exposure (Experiment 2), and when the speaker was a native BE speaker who mimicked the word-final devoicing (Experiment 3). The readiness of the perceptual system to generalize a previously learned adjustment to other positions within the word thus appears to be modulated by distributional properties of the speech input, as well as by the perceived sociophonetic characteristics of the speaker. The results suggest that the transfer of pre-lexical perceptual adjustments that occur through lexically driven learning can be affected by a combination of acoustic, phonological, and sociophonetic factors. PMID:23554598

Assessment of Severe Apnoea through Voice Analysis, Automatic Speech, and Speaker Recognition Techniques

NASA Astrophysics Data System (ADS)

Fernández Pozo, Rubén; Blanco Murillo, Jose Luis; Hernández Gómez, Luis; López Gonzalo, Eduardo; Alcázar Ramírez, José; Toledano, Doroteo T.

2009-12-01

This study is part of an ongoing collaborative effort between the medical and the signal processing communities to promote research on applying standard Automatic Speech Recognition (ASR) techniques for the automatic diagnosis of patients with severe obstructive sleep apnoea (OSA). Early detection of severe apnoea cases is important so that patients can receive early treatment. Effective ASR-based detection could dramatically cut medical testing time. Working with a carefully designed speech database of healthy and apnoea subjects, we describe an acoustic search for distinctive apnoea voice characteristics. We also study abnormal nasalization in OSA patients by modelling vowels in nasal and nonnasal phonetic contexts using Gaussian Mixture Model (GMM) pattern recognition on speech spectra. Finally, we present experimental findings regarding the discriminative power of GMMs applied to severe apnoea detection. We have achieved an 81% correct classification rate, which is very promising and underpins the interest in this line of inquiry.

Speaker identification for the improvement of the security communication between law enforcement units

NASA Astrophysics Data System (ADS)

Tovarek, Jaromir; Partila, Pavol

2017-05-01

This article discusses the speaker identification for the improvement of the security communication between law enforcement units. The main task of this research was to develop the text-independent speaker identification system which can be used for real-time recognition. This system is designed for identification in the open set. It means that the unknown speaker can be anyone. Communication itself is secured, but we have to check the authorization of the communication parties. We have to decide if the unknown speaker is the authorized for the given action. The calls are recorded by IP telephony server and then these recordings are evaluate using classification If the system evaluates that the speaker is not authorized, it sends a warning message to the administrator. This message can detect, for example a stolen phone or other unusual situation. The administrator then performs the appropriate actions. Our novel proposal system uses multilayer neural network for classification and it consists of three layers (input layer, hidden layer, and output layer). A number of neurons in input layer corresponds with the length of speech features. Output layer then represents classified speakers. Artificial Neural Network classifies speech signal frame by frame, but the final decision is done over the complete record. This rule substantially increases accuracy of the classification. Input data for the neural network are a thirteen Mel-frequency cepstral coefficients, which describe the behavior of the vocal tract. These parameters are the most used for speaker recognition. Parameters for training, testing and validation were extracted from recordings of authorized users. Recording conditions for training data correspond with the real traffic of the system (sampling frequency, bit rate). The main benefit of the research is the system developed for text-independent speaker identification which is applied to secure communication between law enforcement units.

Evaluation of speech reception threshold in noise in young Cochlear™ Nucleus® system 6 implant recipients using two different digital remote microphone technologies and a speech enhancement sound processing algorithm.

PubMed

Razza, Sergio; Zaccone, Monica; Meli, Aannalisa; Cristofari, Eliana

2017-12-01

Children affected by hearing loss can experience difficulties in challenging and noisy environments even when deafness is corrected by Cochlear implant (CI) devices. These patients have a selective attention deficit in multiple listening conditions. At present, the most effective ways to improve the performance of speech recognition in noise consists of providing CI processors with noise reduction algorithms and of providing patients with bilateral CIs. The aim of this study was to compare speech performances in noise, across increasing noise levels, in CI recipients using two kinds of wireless remote-microphone radio systems that use digital radio frequency transmission: the Roger Inspiro accessory and the Cochlear Wireless Mini Microphone accessory. Eleven Nucleus Cochlear CP910 CI young user subjects were studied. The signal/noise ratio, at a speech reception threshold (SRT) value of 50%, was measured in different conditions for each patient: with CI only, with the Roger or with the MiniMic accessory. The effect of the application of the SNR-noise reduction algorithm in each of these conditions was also assessed. The tests were performed with the subject positioned in front of the main speaker, at a distance of 2.5 m. Another two speakers were positioned at 3.50 m. The main speaker at 65 dB issued disyllabic words. Babble noise signal was delivered through the other speakers, with variable intensity. The use of both wireless remote microphones improved the SRT results. Both systems improved gain of speech performances. The gain was higher with the Mini Mic system (SRT = -4.76) than the Roger system (SRT = -3.01). The addition of the NR algorithm did not statistically further improve the results. There is significant improvement in speech recognition results with both wireless digital remote microphone accessories, in particular with the Mini Mic system when used with the CP910 processor. The use of a remote microphone accessory surpasses the benefit of application of NR algorithm. Copyright © 2017. Published by Elsevier B.V.

Pitch-Based Segregation of Reverberant Speech

DTIC Science & Technology

2005-02-01

speaker recognition in real environments, audio information retrieval and hearing prosthesis. Second, although binaural listening improves the...intelligibility of target speech under anechoic conditions (Bronkhorst, 2000), this binaural advantage is largely eliminated by reverberation (Plomp, 1976...Brown and Cooke, 1994; Wang and Brown, 1999; Hu and Wang, 2004) as well as in binaural separation (e.g., Roman et al., 2003; Palomaki et al., 2004

Crossmodal and Incremental Perception of Audiovisual Cues to Emotional Speech

ERIC Educational Resources Information Center

Barkhuysen, Pashiera; Krahmer, Emiel; Swerts, Marc

2010-01-01

In this article we report on two experiments about the perception of audiovisual cues to emotional speech. The article addresses two questions: (1) how do visual cues from a speaker's face to emotion relate to auditory cues, and (2) what is the recognition speed for various facial cues to emotion? Both experiments reported below are based on tests…

Early Detection of Severe Apnoea through Voice Analysis and Automatic Speaker Recognition Techniques

NASA Astrophysics Data System (ADS)

Fernández, Ruben; Blanco, Jose Luis; Díaz, David; Hernández, Luis A.; López, Eduardo; Alcázar, José

This study is part of an on-going collaborative effort between the medical and the signal processing communities to promote research on applying voice analysis and Automatic Speaker Recognition techniques (ASR) for the automatic diagnosis of patients with severe obstructive sleep apnoea (OSA). Early detection of severe apnoea cases is important so that patients can receive early treatment. Effective ASR-based diagnosis could dramatically cut medical testing time. Working with a carefully designed speech database of healthy and apnoea subjects, we present and discuss the possibilities of using generative Gaussian Mixture Models (GMMs), generally used in ASR systems, to model distinctive apnoea voice characteristics (i.e. abnormal nasalization). Finally, we present experimental findings regarding the discriminative power of speaker recognition techniques applied to severe apnoea detection. We have achieved an 81.25 % correct classification rate, which is very promising and underpins the interest in this line of inquiry.

Severity-Based Adaptation with Limited Data for ASR to Aid Dysarthric Speakers

PubMed Central

Mustafa, Mumtaz Begum; Salim, Siti Salwah; Mohamed, Noraini; Al-Qatab, Bassam; Siong, Chng Eng

2014-01-01

Automatic speech recognition (ASR) is currently used in many assistive technologies, such as helping individuals with speech impairment in their communication ability. One challenge in ASR for speech-impaired individuals is the difficulty in obtaining a good speech database of impaired speakers for building an effective speech acoustic model. Because there are very few existing databases of impaired speech, which are also limited in size, the obvious solution to build a speech acoustic model of impaired speech is by employing adaptation techniques. However, issues that have not been addressed in existing studies in the area of adaptation for speech impairment are as follows: (1) identifying the most effective adaptation technique for impaired speech; and (2) the use of suitable source models to build an effective impaired-speech acoustic model. This research investigates the above-mentioned two issues on dysarthria, a type of speech impairment affecting millions of people. We applied both unimpaired and impaired speech as the source model with well-known adaptation techniques like the maximum likelihood linear regression (MLLR) and the constrained-MLLR(C-MLLR). The recognition accuracy of each impaired speech acoustic model is measured in terms of word error rate (WER), with further assessments, including phoneme insertion, substitution and deletion rates. Unimpaired speech when combined with limited high-quality speech-impaired data improves performance of ASR systems in recognising severely impaired dysarthric speech. The C-MLLR adaptation technique was also found to be better than MLLR in recognising mildly and moderately impaired speech based on the statistical analysis of the WER. It was found that phoneme substitution was the biggest contributing factor in WER in dysarthric speech for all levels of severity. The results show that the speech acoustic models derived from suitable adaptation techniques improve the performance of ASR systems in recognising impaired speech with limited adaptation data. PMID:24466004

Human phoneme recognition depending on speech-intrinsic variability.

PubMed

Meyer, Bernd T; Jürgens, Tim; Wesker, Thorsten; Brand, Thomas; Kollmeier, Birger

2010-11-01

The influence of different sources of speech-intrinsic variation (speaking rate, effort, style and dialect or accent) on human speech perception was investigated. In listening experiments with 16 listeners, confusions of consonant-vowel-consonant (CVC) and vowel-consonant-vowel (VCV) sounds in speech-weighted noise were analyzed. Experiments were based on the OLLO logatome speech database, which was designed for a man-machine comparison. It contains utterances spoken by 50 speakers from five dialect/accent regions and covers several intrinsic variations. By comparing results depending on intrinsic and extrinsic variations (i.e., different levels of masking noise), the degradation induced by variabilities can be expressed in terms of the SNR. The spectral level distance between the respective speech segment and the long-term spectrum of the masking noise was found to be a good predictor for recognition rates, while phoneme confusions were influenced by the distance to spectrally close phonemes. An analysis based on transmitted information of articulatory features showed that voicing and manner of articulation are comparatively robust cues in the presence of intrinsic variations, whereas the coding of place is more degraded. The database and detailed results have been made available for comparisons between human speech recognition (HSR) and automatic speech recognizers (ASR).

A voice-input voice-output communication aid for people with severe speech impairment.

PubMed

Hawley, Mark S; Cunningham, Stuart P; Green, Phil D; Enderby, Pam; Palmer, Rebecca; Sehgal, Siddharth; O'Neill, Peter

2013-01-01

A new form of augmentative and alternative communication (AAC) device for people with severe speech impairment-the voice-input voice-output communication aid (VIVOCA)-is described. The VIVOCA recognizes the disordered speech of the user and builds messages, which are converted into synthetic speech. System development was carried out employing user-centered design and development methods, which identified and refined key requirements for the device. A novel methodology for building small vocabulary, speaker-dependent automatic speech recognizers with reduced amounts of training data, was applied. Experiments showed that this method is successful in generating good recognition performance (mean accuracy 96%) on highly disordered speech, even when recognition perplexity is increased. The selected message-building technique traded off various factors including speed of message construction and range of available message outputs. The VIVOCA was evaluated in a field trial by individuals with moderate to severe dysarthria and confirmed that they can make use of the device to produce intelligible speech output from disordered speech input. The trial highlighted some issues which limit the performance and usability of the device when applied in real usage situations, with mean recognition accuracy of 67% in these circumstances. These limitations will be addressed in future work.

Implementation of the Intelligent Voice System for Kazakh

NASA Astrophysics Data System (ADS)

Yessenbayev, Zh; Saparkhojayev, N.; Tibeyev, T.

2014-04-01

Modern speech technologies are highly advanced and widely used in day-to-day applications. However, this is mostly concerned with the languages of well-developed countries such as English, German, Japan, Russian, etc. As for Kazakh, the situation is less prominent and research in this field is only starting to evolve. In this research and application-oriented project, we introduce an intelligent voice system for the fast deployment of call-centers and information desks supporting Kazakh speech. The demand on such a system is obvious if the country's large size and small population is considered. The landline and cell phones become the only means of communication for the distant villages and suburbs. The system features Kazakh speech recognition and synthesis modules as well as a web-GUI for efficient dialog management. For speech recognition we use CMU Sphinx engine and for speech synthesis- MaryTTS. The web-GUI is implemented in Java enabling operators to quickly create and manage the dialogs in user-friendly graphical environment. The call routines are handled by Asterisk PBX and JBoss Application Server. The system supports such technologies and protocols as VoIP, VoiceXML, FastAGI, Java SpeechAPI and J2EE. For the speech recognition experiments we compiled and used the first Kazakh speech corpus with the utterances from 169 native speakers. The performance of the speech recognizer is 4.1% WER on isolated word recognition and 6.9% WER on clean continuous speech recognition tasks. The speech synthesis experiments include the training of male and female voices.

Influences of High and Low Variability on Infant Word Recognition

ERIC Educational Resources Information Center

Singh, Leher

2008-01-01

Although infants begin to encode and track novel words in fluent speech by 7.5 months, their ability to recognize words is somewhat limited at this stage. In particular, when the surface form of a word is altered, by changing the gender or affective prosody of the speaker, infants begin to falter at spoken word recognition. Given that natural…

Limited connected speech experiment

NASA Astrophysics Data System (ADS)

Landell, P. B.

1983-03-01

The purpose of this contract was to demonstrate that connected Speech Recognition (CSR) can be performed in real-time on a vocabulary of one hundred words and to test the performance of the CSR system for twenty-five male and twenty-five female speakers. This report describes the contractor's real-time laboratory CSR system, the data base and training software developed in accordance with the contract, and the results of the performance tests.

Social power and recognition of emotional prosody: High power is associated with lower recognition accuracy than low power.

PubMed

Uskul, Ayse K; Paulmann, Silke; Weick, Mario

2016-02-01

Listeners have to pay close attention to a speaker's tone of voice (prosody) during daily conversations. This is particularly important when trying to infer the emotional state of the speaker. Although a growing body of research has explored how emotions are processed from speech in general, little is known about how psychosocial factors such as social power can shape the perception of vocal emotional attributes. Thus, the present studies explored how social power affects emotional prosody recognition. In a correlational study (Study 1) and an experimental study (Study 2), we show that high power is associated with lower accuracy in emotional prosody recognition than low power. These results, for the first time, suggest that individuals experiencing high or low power perceive emotional tone of voice differently. (c) 2016 APA, all rights reserved).

Accent modulates access to word meaning: Evidence for a speaker-model account of spoken word recognition.

PubMed

Cai, Zhenguang G; Gilbert, Rebecca A; Davis, Matthew H; Gaskell, M Gareth; Farrar, Lauren; Adler, Sarah; Rodd, Jennifer M

2017-11-01

Speech carries accent information relevant to determining the speaker's linguistic and social background. A series of web-based experiments demonstrate that accent cues can modulate access to word meaning. In Experiments 1-3, British participants were more likely to retrieve the American dominant meaning (e.g., hat meaning of "bonnet") in a word association task if they heard the words in an American than a British accent. In addition, results from a speeded semantic decision task (Experiment 4) and sentence comprehension task (Experiment 5) confirm that accent modulates on-line meaning retrieval such that comprehension of ambiguous words is easier when the relevant word meaning is dominant in the speaker's dialect. Critically, neutral-accent speech items, created by morphing British- and American-accented recordings, were interpreted in a similar way to accented words when embedded in a context of accented words (Experiment 2). This finding indicates that listeners do not use accent to guide meaning retrieval on a word-by-word basis; instead they use accent information to determine the dialectic identity of a speaker and then use their experience of that dialect to guide meaning access for all words spoken by that person. These results motivate a speaker-model account of spoken word recognition in which comprehenders determine key characteristics of their interlocutor and use this knowledge to guide word meaning access. Copyright © 2017 The Authors. Published by Elsevier Inc. All rights reserved.

Multimodal fusion of polynomial classifiers for automatic person recgonition

NASA Astrophysics Data System (ADS)

Broun, Charles C.; Zhang, Xiaozheng

2001-03-01

With the prevalence of the information age, privacy and personalization are forefront in today's society. As such, biometrics are viewed as essential components of current evolving technological systems. Consumers demand unobtrusive and non-invasive approaches. In our previous work, we have demonstrated a speaker verification system that meets these criteria. However, there are additional constraints for fielded systems. The required recognition transactions are often performed in adverse environments and across diverse populations, necessitating robust solutions. There are two significant problem areas in current generation speaker verification systems. The first is the difficulty in acquiring clean audio signals in all environments without encumbering the user with a head- mounted close-talking microphone. Second, unimodal biometric systems do not work with a significant percentage of the population. To combat these issues, multimodal techniques are being investigated to improve system robustness to environmental conditions, as well as improve overall accuracy across the population. We propose a multi modal approach that builds on our current state-of-the-art speaker verification technology. In order to maintain the transparent nature of the speech interface, we focus on optical sensing technology to provide the additional modality-giving us an audio-visual person recognition system. For the audio domain, we use our existing speaker verification system. For the visual domain, we focus on lip motion. This is chosen, rather than static face or iris recognition, because it provides dynamic information about the individual. In addition, the lip dynamics can aid speech recognition to provide liveness testing. The visual processing method makes use of both color and edge information, combined within Markov random field MRF framework, to localize the lips. Geometric features are extracted and input to a polynomial classifier for the person recognition process. A late integration approach, based on a probabilistic model, is employed to combine the two modalities. The system is tested on the XM2VTS database combined with AWGN in the audio domain over a range of signal-to-noise ratios.

Do Listeners Store in Memory a Speaker's Habitual Utterance-Final Phonation Type?

PubMed Central

Bőhm, Tamás; Shattuck-Hufnagel, Stefanie

2009-01-01

Earlier studies report systematic differences across speakers in the occurrence of utterance-final irregular phonation; the work reported here investigated whether human listeners remember this speaker-specific information and can access it when necessary (a prerequisite for using this cue in speaker recognition). Listeners personally familiar with the voices of the speakers were presented with pairs of speech samples: one with the original and the other with transformed final phonation type. Asked to select the member of the pair that was closer to the talker's voice, most listeners tended to choose the unmanipulated token (even though they judged them to sound essentially equally natural). This suggests that utterance-final pitch period irregularity is part of the mental representation of individual speaker voices, although this may depend on the individual speaker and listener to some extent. PMID:19776665

Can you hear my age? Influences of speech rate and speech spontaneity on estimation of speaker age

PubMed Central

Skoog Waller, Sara; Eriksson, Mårten; Sörqvist, Patrik

2015-01-01

Cognitive hearing science is mainly about the study of how cognitive factors contribute to speech comprehension, but cognitive factors also partake in speech processing to infer non-linguistic information from speech signals, such as the intentions of the talker and the speaker’s age. Here, we report two experiments on age estimation by “naïve” listeners. The aim was to study how speech rate influences estimation of speaker age by comparing the speakers’ natural speech rate with increased or decreased speech rate. In Experiment 1, listeners were presented with audio samples of read speech from three different speaker age groups (young, middle aged, and old adults). They estimated the speakers as younger when speech rate was faster than normal and as older when speech rate was slower than normal. This speech rate effect was slightly greater in magnitude for older (60–65 years) speakers in comparison with younger (20–25 years) speakers, suggesting that speech rate may gain greater importance as a perceptual age cue with increased speaker age. This pattern was more pronounced in Experiment 2, in which listeners estimated age from spontaneous speech. Faster speech rate was associated with lower age estimates, but only for older and middle aged (40–45 years) speakers. Taken together, speakers of all age groups were estimated as older when speech rate decreased, except for the youngest speakers in Experiment 2. The absence of a linear speech rate effect in estimates of younger speakers, for spontaneous speech, implies that listeners use different age estimation strategies or cues (possibly vocabulary) depending on the age of the speaker and the spontaneity of the speech. Potential implications for forensic investigations and other applied domains are discussed. PMID:26236259

Unsupervised real-time speaker identification for daily movies

NASA Astrophysics Data System (ADS)

Li, Ying; Kuo, C.-C. Jay

2002-07-01

The problem of identifying speakers for movie content analysis is addressed in this paper. While most previous work on speaker identification was carried out in a supervised mode using pure audio data, more robust results can be obtained in real-time by integrating knowledge from multiple media sources in an unsupervised mode. In this work, both audio and visual cues will be employed and subsequently combined in a probabilistic framework to identify speakers. Particularly, audio information is used to identify speakers with a maximum likelihood (ML)-based approach while visual information is adopted to distinguish speakers by detecting and recognizing their talking faces based on face detection/recognition and mouth tracking techniques. Moreover, to accommodate for speakers' acoustic variations along time, we update their models on the fly by adapting to their newly contributed speech data. Encouraging results have been achieved through extensive experiments, which shows a promising future of the proposed audiovisual-based unsupervised speaker identification system.

Shhh… I Need Quiet! Children's Understanding of American, British, and Japanese-accented English Speakers.

PubMed

Bent, Tessa; Holt, Rachael Frush

2018-02-01

Children's ability to understand speakers with a wide range of dialects and accents is essential for efficient language development and communication in a global society. Here, the impact of regional dialect and foreign-accent variability on children's speech understanding was evaluated in both quiet and noisy conditions. Five- to seven-year-old children ( n = 90) and adults ( n = 96) repeated sentences produced by three speakers with different accents-American English, British English, and Japanese-accented English-in quiet or noisy conditions. Adults had no difficulty understanding any speaker in quiet conditions. Their performance declined for the nonnative speaker with a moderate amount of noise; their performance only substantially declined for the British English speaker (i.e., below 93% correct) when their understanding of the American English speaker was also impeded. In contrast, although children showed accurate word recognition for the American and British English speakers in quiet conditions, they had difficulty understanding the nonnative speaker even under ideal listening conditions. With a moderate amount of noise, their perception of British English speech declined substantially and their ability to understand the nonnative speaker was particularly poor. These results suggest that although school-aged children can understand unfamiliar native dialects under ideal listening conditions, their ability to recognize words in these dialects may be highly susceptible to the influence of environmental degradation. Fully adult-like word identification for speakers with unfamiliar accents and dialects may exhibit a protracted developmental trajectory.

Speaker-independent phoneme recognition with a binaural auditory image model

NASA Astrophysics Data System (ADS)

Francis, Keith Ivan

1997-09-01

This dissertation presents phoneme recognition techniques based on a binaural fusion of outputs of the auditory image model and subsequent azimuth-selective phoneme recognition in a noisy environment. Background information concerning speech variations, phoneme recognition, current binaural fusion techniques and auditory modeling issues is explained. The research is constrained to sources in the frontal azimuthal plane of a simulated listener. A new method based on coincidence detection of neural activity patterns from the auditory image model of Patterson is used for azimuth-selective phoneme recognition. The method is tested in various levels of noise and the results are reported in contrast to binaural fusion methods based on various forms of correlation to demonstrate the potential of coincidence- based binaural phoneme recognition. This method overcomes smearing of fine speech detail typical of correlation based methods. Nevertheless, coincidence is able to measure similarity of left and right inputs and fuse them into useful feature vectors for phoneme recognition in noise.

Audiovisual cues benefit recognition of accented speech in noise but not perceptual adaptation

PubMed Central

Banks, Briony; Gowen, Emma; Munro, Kevin J.; Adank, Patti

2015-01-01

Perceptual adaptation allows humans to recognize different varieties of accented speech. We investigated whether perceptual adaptation to accented speech is facilitated if listeners can see a speaker’s facial and mouth movements. In Study 1, participants listened to sentences in a novel accent and underwent a period of training with audiovisual or audio-only speech cues, presented in quiet or in background noise. A control group also underwent training with visual-only (speech-reading) cues. We observed no significant difference in perceptual adaptation between any of the groups. To address a number of remaining questions, we carried out a second study using a different accent, speaker and experimental design, in which participants listened to sentences in a non-native (Japanese) accent with audiovisual or audio-only cues, without separate training. Participants’ eye gaze was recorded to verify that they looked at the speaker’s face during audiovisual trials. Recognition accuracy was significantly better for audiovisual than for audio-only stimuli; however, no statistical difference in perceptual adaptation was observed between the two modalities. Furthermore, Bayesian analysis suggested that the data supported the null hypothesis. Our results suggest that although the availability of visual speech cues may be immediately beneficial for recognition of unfamiliar accented speech in noise, it does not improve perceptual adaptation. PMID:26283946

Voice recognition through phonetic features with Punjabi utterances

NASA Astrophysics Data System (ADS)

Kaur, Jasdeep; Juglan, K. C.; Sharma, Vishal; Upadhyay, R. K.

2017-07-01

This paper deals with perception and disorders of speech in view of Punjabi language. Visualizing the importance of voice identification, various parameters of speaker identification has been studied. The speech material was recorded with a tape recorder in their normal and disguised mode of utterances. Out of the recorded speech materials, the utterances free from noise, etc were selected for their auditory and acoustic spectrographic analysis. The comparison of normal and disguised speech of seven subjects is reported. The fundamental frequency (F0) at similar places, Plosive duration at certain phoneme, Amplitude ratio (A1:A2) etc. were compared in normal and disguised speech. It was found that the formant frequency of normal and disguised speech remains almost similar only if it is compared at the position of same vowel quality and quantity. If the vowel is more closed or more open in the disguised utterance the formant frequency will be changed in comparison to normal utterance. The ratio of the amplitude (A1: A2) is found to be speaker dependent. It remains unchanged in the disguised utterance. However, this value may shift in disguised utterance if cross sectioning is not done at the same location.

Scenario-Based Spoken Interaction with Virtual Agents

ERIC Educational Resources Information Center

Morton, Hazel; Jack, Mervyn A.

2005-01-01

This paper describes a CALL approach which integrates software for speaker independent continuous speech recognition with embodied virtual agents and virtual worlds to create an immersive environment in which learners can converse in the target language in contextualised scenarios. The result is a self-access learning package: SPELL (Spoken…

The Downside of Greater Lexical Influences: Selectively Poorer Speech Perception in Noise

PubMed Central

Xie, Zilong; Tessmer, Rachel; Chandrasekaran, Bharath

2017-01-01

Purpose Although lexical information influences phoneme perception, the extent to which reliance on lexical information enhances speech processing in challenging listening environments is unclear. We examined the extent to which individual differences in lexical influences on phonemic processing impact speech processing in maskers containing varying degrees of linguistic information (2-talker babble or pink noise). Method Twenty-nine monolingual English speakers were instructed to ignore the lexical status of spoken syllables (e.g., gift vs. kift) and to only categorize the initial phonemes (/g/ vs. /k/). The same participants then performed speech recognition tasks in the presence of 2-talker babble or pink noise in audio-only and audiovisual conditions. Results Individuals who demonstrated greater lexical influences on phonemic processing experienced greater speech processing difficulties in 2-talker babble than in pink noise. These selective difficulties were present across audio-only and audiovisual conditions. Conclusion Individuals with greater reliance on lexical processes during speech perception exhibit impaired speech recognition in listening conditions in which competing talkers introduce audible linguistic interferences. Future studies should examine the locus of lexical influences/interferences on phonemic processing and speech-in-speech processing. PMID:28586824

Distant Speech Recognition Using a Microphone Array Network

NASA Astrophysics Data System (ADS)

Nakano, Alberto Yoshihiro; Nakagawa, Seiichi; Yamamoto, Kazumasa

In this work, spatial information consisting of the position and orientation angle of an acoustic source is estimated by an artificial neural network (ANN). The estimated position of a speaker in an enclosed space is used to refine the estimated time delays for a delay-and-sum beamformer, thus enhancing the output signal. On the other hand, the orientation angle is used to restrict the lexicon used in the recognition phase, assuming that the speaker faces a particular direction while speaking. To compensate the effect of the transmission channel inside a short frame analysis window, a new cepstral mean normalization (CMN) method based on a Gaussian mixture model (GMM) is investigated and shows better performance than the conventional CMN for short utterances. The performance of the proposed method is evaluated through Japanese digit/command recognition experiments.

Speech endpoint detection with non-language speech sounds for generic speech processing applications

NASA Astrophysics Data System (ADS)

McClain, Matthew; Romanowski, Brian

2009-05-01

Non-language speech sounds (NLSS) are sounds produced by humans that do not carry linguistic information. Examples of these sounds are coughs, clicks, breaths, and filled pauses such as "uh" and "um" in English. NLSS are prominent in conversational speech, but can be a significant source of errors in speech processing applications. Traditionally, these sounds are ignored by speech endpoint detection algorithms, where speech regions are identified in the audio signal prior to processing. The ability to filter NLSS as a pre-processing step can significantly enhance the performance of many speech processing applications, such as speaker identification, language identification, and automatic speech recognition. In order to be used in all such applications, NLSS detection must be performed without the use of language models that provide knowledge of the phonology and lexical structure of speech. This is especially relevant to situations where the languages used in the audio are not known apriori. We present the results of preliminary experiments using data from American and British English speakers, in which segments of audio are classified as language speech sounds (LSS) or NLSS using a set of acoustic features designed for language-agnostic NLSS detection and a hidden-Markov model (HMM) to model speech generation. The results of these experiments indicate that the features and model used are capable of detection certain types of NLSS, such as breaths and clicks, while detection of other types of NLSS such as filled pauses will require future research.

Emotion Analysis of Telephone Complaints from Customer Based on Affective Computing.

PubMed

Gong, Shuangping; Dai, Yonghui; Ji, Jun; Wang, Jinzhao; Sun, Hai

2015-01-01

Customer complaint has been the important feedback for modern enterprises to improve their product and service quality as well as the customer's loyalty. As one of the commonly used manners in customer complaint, telephone communication carries rich emotional information of speeches, which provides valuable resources for perceiving the customer's satisfaction and studying the complaint handling skills. This paper studies the characteristics of telephone complaint speeches and proposes an analysis method based on affective computing technology, which can recognize the dynamic changes of customer emotions from the conversations between the service staff and the customer. The recognition process includes speaker recognition, emotional feature parameter extraction, and dynamic emotion recognition. Experimental results show that this method is effective and can reach high recognition rates of happy and angry states. It has been successfully applied to the operation quality and service administration in telecom and Internet service company.

Emotion Analysis of Telephone Complaints from Customer Based on Affective Computing

PubMed Central

Gong, Shuangping; Ji, Jun; Wang, Jinzhao; Sun, Hai

2015-01-01

Customer complaint has been the important feedback for modern enterprises to improve their product and service quality as well as the customer's loyalty. As one of the commonly used manners in customer complaint, telephone communication carries rich emotional information of speeches, which provides valuable resources for perceiving the customer's satisfaction and studying the complaint handling skills. This paper studies the characteristics of telephone complaint speeches and proposes an analysis method based on affective computing technology, which can recognize the dynamic changes of customer emotions from the conversations between the service staff and the customer. The recognition process includes speaker recognition, emotional feature parameter extraction, and dynamic emotion recognition. Experimental results show that this method is effective and can reach high recognition rates of happy and angry states. It has been successfully applied to the operation quality and service administration in telecom and Internet service company. PMID:26633967

Speech information retrieval: a review

DOE Office of Scientific and Technical Information (OSTI.GOV)

Hafen, Ryan P.; Henry, Michael J.

Audio is an information-rich component of multimedia. Information can be extracted from audio in a number of different ways, and thus there are several established audio signal analysis research fields. These fields include speech recognition, speaker recognition, audio segmentation and classification, and audio finger-printing. The information that can be extracted from tools and methods developed in these fields can greatly enhance multimedia systems. In this paper, we present the current state of research in each of the major audio analysis fields. The goal is to introduce enough back-ground for someone new in the field to quickly gain high-level understanding andmore » to provide direction for further study.« less

Effect of Acting Experience on Emotion Expression and Recognition in Voice: Non-Actors Provide Better Stimuli than Expected.

PubMed

Jürgens, Rebecca; Grass, Annika; Drolet, Matthis; Fischer, Julia

Both in the performative arts and in emotion research, professional actors are assumed to be capable of delivering emotions comparable to spontaneous emotional expressions. This study examines the effects of acting training on vocal emotion depiction and recognition. We predicted that professional actors express emotions in a more realistic fashion than non-professional actors. However, professional acting training may lead to a particular speech pattern; this might account for vocal expressions by actors that are less comparable to authentic samples than the ones by non-professional actors. We compared 80 emotional speech tokens from radio interviews with 80 re-enactments by professional and inexperienced actors, respectively. We analyzed recognition accuracies for emotion and authenticity ratings and compared the acoustic structure of the speech tokens. Both play-acted conditions yielded similar recognition accuracies and possessed more variable pitch contours than the spontaneous recordings. However, professional actors exhibited signs of different articulation patterns compared to non-trained speakers. Our results indicate that for emotion research, emotional expressions by professional actors are not better suited than those from non-actors.

Speech serial control in healthy speakers and speakers with hypokinetic or ataxic dysarthria: effects of sequence length and practice

PubMed Central

Reilly, Kevin J.; Spencer, Kristie A.

2013-01-01

The current study investigated the processes responsible for selection of sounds and syllables during production of speech sequences in 10 adults with hypokinetic dysarthria from Parkinson’s disease, five adults with ataxic dysarthria, and 14 healthy control speakers. Speech production data from a choice reaction time task were analyzed to evaluate the effects of sequence length and practice on speech sound sequencing. Speakers produced sequences that were between one and five syllables in length over five experimental runs of 60 trials each. In contrast to the healthy speakers, speakers with hypokinetic dysarthria demonstrated exaggerated sequence length effects for both inter-syllable intervals (ISIs) and speech error rates. Conversely, speakers with ataxic dysarthria failed to demonstrate a sequence length effect on ISIs and were also the only group that did not exhibit practice-related changes in ISIs and speech error rates over the five experimental runs. The exaggerated sequence length effects in the hypokinetic speakers with Parkinson’s disease are consistent with an impairment of action selection during speech sequence production. The absent length effects observed in the speakers with ataxic dysarthria is consistent with previous findings that indicate a limited capacity to buffer speech sequences in advance of their execution. In addition, the lack of practice effects in these speakers suggests that learning-related improvements in the production rate and accuracy of speech sequences involves processing by structures of the cerebellum. Together, the current findings inform models of serial control for speech in healthy speakers and support the notion that sequencing deficits contribute to speech symptoms in speakers with hypokinetic or ataxic dysarthria. In addition, these findings indicate that speech sequencing is differentially impaired in hypokinetic and ataxic dysarthria. PMID:24137121

Development of a Low-Cost, Noninvasive, Portable Visual Speech Recognition Program.

PubMed

Kohlberg, Gavriel D; Gal, Ya'akov Kobi; Lalwani, Anil K

2016-09-01

Loss of speech following tracheostomy and laryngectomy severely limits communication to simple gestures and facial expressions that are largely ineffective. To facilitate communication in these patients, we seek to develop a low-cost, noninvasive, portable, and simple visual speech recognition program (VSRP) to convert articulatory facial movements into speech. A Microsoft Kinect-based VSRP was developed to capture spatial coordinates of lip movements and translate them into speech. The articulatory speech movements associated with 12 sentences were used to train an artificial neural network classifier. The accuracy of the classifier was then evaluated on a separate, previously unseen set of articulatory speech movements. The VSRP was successfully implemented and tested in 5 subjects. It achieved an accuracy rate of 77.2% (65.0%-87.6% for the 5 speakers) on a 12-sentence data set. The mean time to classify an individual sentence was 2.03 milliseconds (1.91-2.16). We have demonstrated the feasibility of a low-cost, noninvasive, portable VSRP based on Kinect to accurately predict speech from articulation movements in clinically trivial time. This VSRP could be used as a novel communication device for aphonic patients. © The Author(s) 2016.

Speech Prosody Across Stimulus Types for Individuals with Parkinson's Disease.

PubMed

K-Y Ma, Joan; Schneider, Christine B; Hoffmann, Rüdiger; Storch, Alexander

2015-01-01

Up to 89% of the individuals with Parkinson's disease (PD) experience speech problem over the course of the disease. Speech prosody and intelligibility are two of the most affected areas in hypokinetic dysarthria. However, assessment of these areas could potentially be problematic as speech prosody and intelligibility could be affected by the type of speech materials employed. To comparatively explore the effects of different types of speech stimulus on speech prosody and intelligibility in PD speakers. Speech prosody and intelligibility of two groups of individuals with varying degree of dysarthria resulting from PD was compared to that of a group of control speakers using sentence reading, passage reading and monologue. Acoustic analysis including measures on fundamental frequency (F0), intensity and speech rate was used to form a prosodic profile for each individual. Speech intelligibility was measured for the speakers with dysarthria using direct magnitude estimation. Difference in F0 variability between the speakers with dysarthria and control speakers was only observed in sentence reading task. Difference in the average intensity level was observed for speakers with mild dysarthria to that of the control speakers. Additionally, there were stimulus effect on both intelligibility and prosodic profile. The prosodic profile of PD speakers was different from that of the control speakers in the more structured task, and lower intelligibility was found in less structured task. This highlighted the value of both structured and natural stimulus to evaluate speech production in PD speakers.

Speaker-dependent Multipitch Tracking Using Deep Neural Networks

DTIC Science & Technology

2015-01-01

connections through time. Studies have shown that RNNs are good at modeling sequential data like handwriting [12] and speech [26]. We plan to explore RNNs in...Schmidhuber, and S. Fernández, “Unconstrained on-line handwriting recognition with recurrent neural networks,” in Proceedings of NIPS, 2008, pp. 577–584. [13

The Influence of Anticipation of Word Misrecognition on the Likelihood of Stuttering

ERIC Educational Resources Information Center

Brocklehurst, Paul H.; Lickley, Robin J.; Corley, Martin

2012-01-01

This study investigates whether the experience of stuttering can result from the speaker's anticipation of his words being misrecognized. Twelve adults who stutter (AWS) repeated single words into what appeared to be an automatic speech-recognition system. Following each iteration of each word, participants provided a self-rating of whether they…

Audiovisual speech facilitates voice learning.

PubMed

Sheffert, Sonya M; Olson, Elizabeth

2004-02-01

In this research, we investigated the effects of voice and face information on the perceptual learning of talkers and on long-term memory for spoken words. In the first phase, listeners were trained over several days to identify voices from words presented auditorily or audiovisually. The training data showed that visual information about speakers enhanced voice learning, revealing cross-modal connections in talker processing akin to those observed in speech processing. In the second phase, the listeners completed an auditory or audiovisual word recognition memory test in which equal numbers of words were spoken by familiar and unfamiliar talkers. The data showed that words presented by familiar talkers were more likely to be retrieved from episodic memory, regardless of modality. Together, these findings provide new information about the representational code underlying familiar talker recognition and the role of stimulus familiarity in episodic word recognition.

Word recognition materials for native speakers of Taiwan Mandarin.

PubMed

Nissen, Shawn L; Harris, Richard W; Dukes, Alycia

2008-06-01

To select, digitally record, evaluate, and psychometrically equate word recognition materials that can be used to measure the speech perception abilities of native speakers of Taiwan Mandarin in quiet. Frequently used bisyllabic words produced by male and female talkers of Taiwan Mandarin were digitally recorded and subsequently evaluated using 20 native listeners with normal hearing at 10 intensity levels (-5 to 40 dB HL) in increments of 5 dB. Using logistic regression, 200 words with the steepest psychometric slopes were divided into 4 lists and 8 half-lists that were relatively equivalent in psychometric function slope. To increase auditory homogeneity of the lists, the intensity of words in each list was digitally adjusted so that the threshold of each list was equal to the midpoint between the mean thresholds of the male and female half-lists. Digital recordings of the word recognition lists and the associated clinical instructions are available on CD upon request.

Second Language Ability and Emotional Prosody Perception

PubMed Central

Bhatara, Anjali; Laukka, Petri; Boll-Avetisyan, Natalie; Granjon, Lionel; Anger Elfenbein, Hillary; Bänziger, Tanja

2016-01-01

The present study examines the effect of language experience on vocal emotion perception in a second language. Native speakers of French with varying levels of self-reported English ability were asked to identify emotions from vocal expressions produced by American actors in a forced-choice task, and to rate their pleasantness, power, alertness and intensity on continuous scales. Stimuli included emotionally expressive English speech (emotional prosody) and non-linguistic vocalizations (affect bursts), and a baseline condition with Swiss-French pseudo-speech. Results revealed effects of English ability on the recognition of emotions in English speech but not in non-linguistic vocalizations. Specifically, higher English ability was associated with less accurate identification of positive emotions, but not with the interpretation of negative emotions. Moreover, higher English ability was associated with lower ratings of pleasantness and power, again only for emotional prosody. This suggests that second language skills may sometimes interfere with emotion recognition from speech prosody, particularly for positive emotions. PMID:27253326

Long short-term memory for speaker generalization in supervised speech separation

PubMed Central

Chen, Jitong; Wang, DeLiang

2017-01-01

Speech separation can be formulated as learning to estimate a time-frequency mask from acoustic features extracted from noisy speech. For supervised speech separation, generalization to unseen noises and unseen speakers is a critical issue. Although deep neural networks (DNNs) have been successful in noise-independent speech separation, DNNs are limited in modeling a large number of speakers. To improve speaker generalization, a separation model based on long short-term memory (LSTM) is proposed, which naturally accounts for temporal dynamics of speech. Systematic evaluation shows that the proposed model substantially outperforms a DNN-based model on unseen speakers and unseen noises in terms of objective speech intelligibility. Analyzing LSTM internal representations reveals that LSTM captures long-term speech contexts. It is also found that the LSTM model is more advantageous for low-latency speech separation and it, without future frames, performs better than the DNN model with future frames. The proposed model represents an effective approach for speaker- and noise-independent speech separation. PMID:28679261

Non-native Listeners’ Recognition of High-Variability Speech Using PRESTO

PubMed Central

Tamati, Terrin N.; Pisoni, David B.

2015-01-01

Background Natural variability in speech is a significant challenge to robust successful spoken word recognition. In everyday listening environments, listeners must quickly adapt and adjust to multiple sources of variability in both the signal and listening environments. High-variability speech may be particularly difficult to understand for non-native listeners, who have less experience with the second language (L2) phonological system and less detailed knowledge of sociolinguistic variation of the L2. Purpose The purpose of this study was to investigate the effects of high-variability sentences on non-native speech recognition and to explore the underlying sources of individual differences in speech recognition abilities of non-native listeners. Research Design Participants completed two sentence recognition tasks involving high-variability and low-variability sentences. They also completed a battery of behavioral tasks and self-report questionnaires designed to assess their indexical processing skills, vocabulary knowledge, and several core neurocognitive abilities. Study Sample Native speakers of Mandarin (n = 25) living in the United States recruited from the Indiana University community participated in the current study. A native comparison group consisted of scores obtained from native speakers of English (n = 21) in the Indiana University community taken from an earlier study. Data Collection and Analysis Speech recognition in high-variability listening conditions was assessed with a sentence recognition task using sentences from PRESTO (Perceptually Robust English Sentence Test Open-Set) mixed in 6-talker multitalker babble. Speech recognition in low-variability listening conditions was assessed using sentences from HINT (Hearing In Noise Test) mixed in 6-talker multitalker babble. Indexical processing skills were measured using a talker discrimination task, a gender discrimination task, and a forced-choice regional dialect categorization task. Vocabulary knowledge was assessed with the WordFam word familiarity test, and executive functioning was assessed with the BRIEF-A (Behavioral Rating Inventory of Executive Function – Adult Version) self-report questionnaire. Scores from the non-native listeners on behavioral tasks and self-report questionnaires were compared with scores obtained from native listeners tested in a previous study and were examined for individual differences. Results Non-native keyword recognition scores were significantly lower on PRESTO sentences than on HINT sentences. Non-native listeners’ keyword recognition scores were also lower than native listeners’ scores on both sentence recognition tasks. Differences in performance on the sentence recognition tasks between non-native and native listeners were larger on PRESTO than on HINT, although group differences varied by signal-to-noise ratio. The non-native and native groups also differed in the ability to categorize talkers by region of origin and in vocabulary knowledge. Individual non-native word recognition accuracy on PRESTO sentences in multitalker babble at more favorable signal-to-noise ratios was found to be related to several BRIEF-A subscales and composite scores. However, non-native performance on PRESTO was not related to regional dialect categorization, talker and gender discrimination, or vocabulary knowledge. Conclusions High-variability sentences in multitalker babble were particularly challenging for non-native listeners. Difficulty under high-variability testing conditions was related to lack of experience with the L2, especially L2 sociolinguistic information, compared with native listeners. Individual differences among the non-native listeners were related to weaknesses in core neurocognitive abilities affecting behavioral control in everyday life. PMID:25405842

Automated Intelligibility Assessment of Pathological Speech Using Phonological Features

NASA Astrophysics Data System (ADS)

Middag, Catherine; Martens, Jean-Pierre; Van Nuffelen, Gwen; De Bodt, Marc

2009-12-01

It is commonly acknowledged that word or phoneme intelligibility is an important criterion in the assessment of the communication efficiency of a pathological speaker. People have therefore put a lot of effort in the design of perceptual intelligibility rating tests. These tests usually have the drawback that they employ unnatural speech material (e.g., nonsense words) and that they cannot fully exclude errors due to listener bias. Therefore, there is a growing interest in the application of objective automatic speech recognition technology to automate the intelligibility assessment. Current research is headed towards the design of automated methods which can be shown to produce ratings that correspond well with those emerging from a well-designed and well-performed perceptual test. In this paper, a novel methodology that is built on previous work (Middag et al., 2008) is presented. It utilizes phonological features, automatic speech alignment based on acoustic models that were trained on normal speech, context-dependent speaker feature extraction, and intelligibility prediction based on a small model that can be trained on pathological speech samples. The experimental evaluation of the new system reveals that the root mean squared error of the discrepancies between perceived and computed intelligibilities can be as low as 8 on a scale of 0 to 100.

Speech Recognition in Nonnative versus Native English-Speaking College Students in a Virtual Classroom.

PubMed

Neave-DiToro, Dorothy; Rubinstein, Adrienne; Neuman, Arlene C

2017-05-01

Limited attention has been given to the effects of classroom acoustics at the college level. Many studies have reported that nonnative speakers of English are more likely to be affected by poor room acoustics than native speakers. An important question is how classroom acoustics affect speech perception of nonnative college students. The combined effect of noise and reverberation on the speech recognition performance of college students who differ in age of English acquisition was evaluated under conditions simulating classrooms with reverberation times (RTs) close to ANSI recommended RTs. A mixed design was used in this study. Thirty-six native and nonnative English-speaking college students with normal hearing, ages 18-28 yr, participated. Two groups of nine native participants (native monolingual [NM] and native bilingual) and two groups of nine nonnative participants (nonnative early and nonnative late) were evaluated in noise under three reverberant conditions (0.03, 0.06, and 0.08 sec). A virtual test paradigm was used, which represented a signal reaching a student at the back of a classroom. Speech recognition in noise was measured using the Bamford-Kowal-Bench Speech-in-Noise (BKB-SIN) test and signal-to-noise ratio required for correct repetition of 50% of the key words in the stimulus sentences (SNR-50) was obtained for each group in each reverberant condition. A mixed-design analysis of variance was used to determine statistical significance as a function of listener group and RT. SNR-50 was significantly higher for nonnative listeners as compared to native listeners, and a more favorable SNR-50 was needed as RT increased. The most dramatic effect on SNR-50 was found in the group with later acquisition of English, whereas the impact of early introduction of a second language was subtler. At the ANSI standard's maximum recommended RT (0.6 sec), all groups except the NM group exhibited a mild signal-to-noise ratio (SNR) loss. At the 0.8 sec RT, all groups exhibited a mild SNR loss. Acoustics in the classroom are an important consideration for nonnative speakers who are proficient in English and enrolled in college. To address the need for a clearer speech signal by nonnative students (and for all students), universities should follow ANSI recommendations, as well as minimize background noise in occupied classrooms. Behavioral/instructional strategies should be considered to address factors that cannot be compensated for through acoustic design. American Academy of Audiology

[The contribution of different cochlear insertion region to Mandarin speech perception in users of cochlear implant].

PubMed

Qi, Beier; Liu, Bo; Liu, Sha; Liu, Haihong; Dong, Ruijuan; Zhang, Ning; Gong, Shusheng

2011-05-01

To study the effect of cochlear electrode coverage and different insertion region on speech recognition, especially tone perception of cochlear implant users whose native language is Mandarin Chinese. Setting seven test conditions by fitting software. All conditions were created by switching on/off respective channels in order to simulate different insertion position. Then Mandarin CI users received 4 Speech tests, including Vowel Identification test, Consonant Identification test, Tone Identification test-male speaker, Mandarin HINT test (SRS) in quiet and noise. To all test conditions: the average score of vowel identification was significantly different, from 56% to 91% (Rank sum test, P < 0.05). The average score of consonant identification was significantly different, from 72% to 85% (ANOVNA, P < 0.05). The average score of Tone identification was not significantly different (ANOVNA, P > 0.05). However the more channels activated, the higher scores obtained, from 68% to 81%. This study shows that there is a correlation between insertion depth and speech recognition. Because all parts of the basement membrane can help CI users to improve their speech recognition ability, it is very important to enhance verbal communication ability and social interaction ability of CI users by increasing insertion depth and actively stimulating the top region of cochlear.

Evaluation of Mandarin Chinese Speech Recognition in Adults with Cochlear Implants Using the Spectral Ripple Discrimination Test

PubMed Central

Dai, Chuanfu; Zhao, Zeqi; Zhang, Duo; Lei, Guanxiong

2018-01-01

Background The aim of this study was to explore the value of the spectral ripple discrimination test in speech recognition evaluation among a deaf (post-lingual) Mandarin-speaking population in China following cochlear implantation. Material/Methods The study included 23 Mandarin-speaking adult subjects with normal hearing (normal-hearing group) and 17 deaf adults who were former Mandarin-speakers, with cochlear implants (cochlear implantation group). The normal-hearing subjects were divided into men (n=10) and women (n=13). The spectral ripple discrimination thresholds between the groups were compared. The correlation between spectral ripple discrimination thresholds and Mandarin speech recognition rates in the cochlear implantation group were studied. Results Spectral ripple discrimination thresholds did not correlate with age (r=−0.19; p=0.22), and there was no significant difference in spectral ripple discrimination thresholds between the male and female groups (p=0.654). Spectral ripple discrimination thresholds of deaf adults with cochlear implants were significantly correlated with monosyllabic recognition rates (r=0.84; p=0.000). Conclusions In a Mandarin Chinese speaking population, spectral ripple discrimination thresholds of normal-hearing individuals were unaffected by both gender and age. Spectral ripple discrimination thresholds were correlated with Mandarin monosyllabic recognition rates of Mandarin-speaking in post-lingual deaf adults with cochlear implants. The spectral ripple discrimination test is a promising method for speech recognition evaluation in adults following cochlear implantation in China. PMID:29806954

Evaluation of Mandarin Chinese Speech Recognition in Adults with Cochlear Implants Using the Spectral Ripple Discrimination Test.

PubMed

Dai, Chuanfu; Zhao, Zeqi; Shen, Weidong; Zhang, Duo; Lei, Guanxiong; Qiao, Yuehua; Yang, Shiming

2018-05-28

BACKGROUND The aim of this study was to explore the value of the spectral ripple discrimination test in speech recognition evaluation among a deaf (post-lingual) Mandarin-speaking population in China following cochlear implantation. MATERIAL AND METHODS The study included 23 Mandarin-speaking adult subjects with normal hearing (normal-hearing group) and 17 deaf adults who were former Mandarin-speakers, with cochlear implants (cochlear implantation group). The normal-hearing subjects were divided into men (n=10) and women (n=13). The spectral ripple discrimination thresholds between the groups were compared. The correlation between spectral ripple discrimination thresholds and Mandarin speech recognition rates in the cochlear implantation group were studied. RESULTS Spectral ripple discrimination thresholds did not correlate with age (r=-0.19; p=0.22), and there was no significant difference in spectral ripple discrimination thresholds between the male and female groups (p=0.654). Spectral ripple discrimination thresholds of deaf adults with cochlear implants were significantly correlated with monosyllabic recognition rates (r=0.84; p=0.000). CONCLUSIONS In a Mandarin Chinese speaking population, spectral ripple discrimination thresholds of normal-hearing individuals were unaffected by both gender and age. Spectral ripple discrimination thresholds were correlated with Mandarin monosyllabic recognition rates of Mandarin-speaking in post-lingual deaf adults with cochlear implants. The spectral ripple discrimination test is a promising method for speech recognition evaluation in adults following cochlear implantation in China.

Differential Recognition of Pitch Patterns in Discrete and Gliding Stimuli in Congenital Amusia: Evidence from Mandarin Speakers

ERIC Educational Resources Information Center

Liu, Fang; Xu, Yi; Patel, Aniruddh D.; Francart, Tom; Jiang, Cunmei

2012-01-01

This study examined whether "melodic contour deafness" (insensitivity to the direction of pitch movement) in congenital amusia is associated with specific types of pitch patterns (discrete versus gliding pitches) or stimulus types (speech syllables versus complex tones). Thresholds for identification of pitch direction were obtained using discrete…

Neural Network Classifier Architectures for Phoneme Recognition. CRC Technical Note No. CRC-TN-92-001.

ERIC Educational Resources Information Center

Treurniet, William

A study applied artificial neural networks, trained with the back-propagation learning algorithm, to modelling phonemes extracted from the DARPA TIMIT multi-speaker, continuous speech data base. A number of proposed network architectures were applied to the phoneme classification task, ranging from the simple feedforward multilayer network to more…

American or British? L2 Speakers' Recognition and Evaluations of Accent Features in English

ERIC Educational Resources Information Center

Carrie, Erin; McKenzie, Robert M.

2018-01-01

Recent language attitude research has attended to the processes involved in identifying and evaluating spoken language varieties. This article investigates the ability of second-language learners of English in Spain (N = 71) to identify Received Pronunciation (RP) and General American (GenAm) speech and their perceptions of linguistic variation…

[Vocal recognition in dental and oral radiology].

PubMed

La Fianza, A; Giorgetti, S; Marelli, P; Campani, R

1993-10-01

Speech reporting benefits by units which can recognize sentences in any natural language in real time. The use of this method in the everyday practice of radiology departments shows its possible application fields. We used the speech recognition method to report orthopantomographic exams in order to evaluate the advantages the method offers to the management and quality of reporting the exams which are difficult to fit in other closed computed reporting systems. Both speech recognition and the conventional reporting method (tape recording and typewriting) were used to report 760 orthopantomographs. The average time needed to make the report, the legibility (or Flesch) index, as adapted for the Italian language, and finally a clinical index (the subjective opinion of 4 odontostomatologists) were evaluated for each exam, with both techniques. Moreover, errors in speech reporting (crude, human and overall errors) were also evaluated. The advantages of speech reporting consisted in the shorter time needed for the report to become available (2.24 vs 2.99 minutes) (p < 0.0005), in the improved Flesch index (30.62 vs 28.9) and in the clinical index. The data obtained from speech reporting in odontostomatologic radiology were useful not only to reduce the mean reporting time of orthopantomographic exams but also to improve report quality by reducing both grammar and transmission mistakes. However, the basic condition for such results to be obtained is the speaker's skills to make a good report.

Investigating Holistic Measures of Speech Prosody

ERIC Educational Resources Information Center

Cunningham, Dana Aliel

2012-01-01

Speech prosody is a multi-faceted dimension of speech which can be measured and analyzed in a variety of ways. In this study, the speech prosody of Mandarin L1 speakers, English L2 speakers, and English L1 speakers was assessed by trained raters who listened to sound clips of the speakers responding to a graph prompt and reading a short passage.…

Lexical effects on speech production and intelligibility in Parkinson's disease

NASA Astrophysics Data System (ADS)

Chiu, Yi-Fang

Individuals with Parkinson's disease (PD) often have speech deficits that lead to reduced speech intelligibility. Previous research provides a rich database regarding the articulatory deficits associated with PD including restricted vowel space (Skodda, Visser, & Schlegel, 2011) and flatter formant transitions (Tjaden & Wilding, 2004; Walsh & Smith, 2012). However, few studies consider the effect of higher level structural variables of word usage frequency and the number of similar sounding words (i.e. neighborhood density) on lower level articulation or on listeners' perception of dysarthric speech. The purpose of the study is to examine the interaction of lexical properties and speech articulation as measured acoustically in speakers with PD and healthy controls (HC) and the effect of lexical properties on the perception of their speech. Individuals diagnosed with PD and age-matched healthy controls read sentences with words that varied in word frequency and neighborhood density. Acoustic analysis was performed to compare second formant transitions in diphthongs, an indicator of the dynamics of tongue movement during speech production, across different lexical characteristics. Young listeners transcribed the spoken sentences and the transcription accuracy was compared across lexical conditions. The acoustic results indicate that both PD and HC speakers adjusted their articulation based on lexical properties but the PD group had significant reductions in second formant transitions compared to HC. Both groups of speakers increased second formant transitions for words with low frequency and low density, but the lexical effect is diphthong dependent. The change in second formant slope was limited in the PD group when the required formant movement for the diphthong is small. The data from listeners' perception of the speech by PD and HC show that listeners identified high frequency words with greater accuracy suggesting the use of lexical knowledge during the recognition process. The relationship between acoustic results and perceptual accuracy is limited in this study suggesting that listeners incorporate acoustic and non-acoustic information to maximize speech intelligibility.

Speaker Recognition Through NLP and CWT Modeling

DOE Office of Scientific and Technical Information (OSTI.GOV)

Brown-VanHoozer, S.A.; Kercel, S.W.; Tucker, R.W.

The objective of this research is to develop a system capable of identifying speakers on wiretaps from a large database (>500 speakers) with a short search time duration (<30 seconds), and with better than 90% accuracy. Much previous research in speaker recognition has led to algorithms that produced encouraging preliminary results, but were overwhelmed when applied to populations of more than a dozen or so different speakers. The authors are investigating a solution to the "large population" problem by seeking two completely different kinds of characterizing features. These features are he techniques of Neuro-Linguistic Programming (NLP) and the continuous waveletmore » transform (CWT). NLP extracts precise neurological, verbal and non-verbal information, and assimilates the information into useful patterns. These patterns are based on specific cues demonstrated by each individual, and provide ways of determining congruency between verbal and non-verbal cues. The primary NLP modalities are characterized through word spotting (or verbal predicates cues, e.g., see, sound, feel, etc.) while the secondary modalities would be characterized through the speech transcription used by the individual. This has the practical effect of reducing the size of the search space, and greatly speeding up the process of identifying an unknown speaker. The wavelet-based line of investigation concentrates on using vowel phonemes and non-verbal cues, such as tempo. The rationale for concentrating on vowels is there are a limited number of vowels phonemes, and at least one of them usually appears in even the shortest of speech segments. Using the fast, CWT algorithm, the details of both the formant frequency and the glottal excitation characteristics can be easily extracted from voice waveforms. The differences in the glottal excitation waveforms as well as the formant frequency are evident in the CWT output. More significantly, the CWT reveals significant detail of the glottal excitation waveform.« less

Speaker recognition through NLP and CWT modeling.

DOE Office of Scientific and Technical Information (OSTI.GOV)

Brown-VanHoozer, A.; Kercel, S. W.; Tucker, R. W.

The objective of this research is to develop a system capable of identifying speakers on wiretaps from a large database (>500 speakers) with a short search time duration (<30 seconds), and with better than 90% accuracy. Much previous research in speaker recognition has led to algorithms that produced encouraging preliminary results, but were overwhelmed when applied to populations of more than a dozen or so different speakers. The authors are investigating a solution to the ''huge population'' problem by seeking two completely different kinds of characterizing features. These features are extracted using the techniques of Neuro-Linguistic Programming (NLP) and themore » continuous wavelet transform (CWT). NLP extracts precise neurological, verbal and non-verbal information, and assimilates the information into useful patterns. These patterns are based on specific cues demonstrated by each individual, and provide ways of determining congruency between verbal and non-verbal cues. The primary NLP modalities are characterized through word spotting (or verbal predicates cues, e.g., see, sound, feel, etc.) while the secondary modalities would be characterized through the speech transcription used by the individual. This has the practical effect of reducing the size of the search space, and greatly speeding up the process of identifying an unknown speaker. The wavelet-based line of investigation concentrates on using vowel phonemes and non-verbal cues, such as tempo. The rationale for concentrating on vowels is there are a limited number of vowels phonemes, and at least one of them usually appears in even the shortest of speech segments. Using the fast, CWT algorithm, the details of both the formant frequency and the glottal excitation characteristics can be easily extracted from voice waveforms. The differences in the glottal excitation waveforms as well as the formant frequency are evident in the CWT output. More significantly, the CWT reveals significant detail of the glottal excitation waveform.« less

Multisensory speech perception in autism spectrum disorder: From phoneme to whole-word perception.

PubMed

Stevenson, Ryan A; Baum, Sarah H; Segers, Magali; Ferber, Susanne; Barense, Morgan D; Wallace, Mark T

2017-07-01

Speech perception in noisy environments is boosted when a listener can see the speaker's mouth and integrate the auditory and visual speech information. Autistic children have a diminished capacity to integrate sensory information across modalities, which contributes to core symptoms of autism, such as impairments in social communication. We investigated the abilities of autistic and typically-developing (TD) children to integrate auditory and visual speech stimuli in various signal-to-noise ratios (SNR). Measurements of both whole-word and phoneme recognition were recorded. At the level of whole-word recognition, autistic children exhibited reduced performance in both the auditory and audiovisual modalities. Importantly, autistic children showed reduced behavioral benefit from multisensory integration with whole-word recognition, specifically at low SNRs. At the level of phoneme recognition, autistic children exhibited reduced performance relative to their TD peers in auditory, visual, and audiovisual modalities. However, and in contrast to their performance at the level of whole-word recognition, both autistic and TD children showed benefits from multisensory integration for phoneme recognition. In accordance with the principle of inverse effectiveness, both groups exhibited greater benefit at low SNRs relative to high SNRs. Thus, while autistic children showed typical multisensory benefits during phoneme recognition, these benefits did not translate to typical multisensory benefit of whole-word recognition in noisy environments. We hypothesize that sensory impairments in autistic children raise the SNR threshold needed to extract meaningful information from a given sensory input, resulting in subsequent failure to exhibit behavioral benefits from additional sensory information at the level of whole-word recognition. Autism Res 2017. © 2017 International Society for Autism Research, Wiley Periodicals, Inc. Autism Res 2017, 10: 1280-1290. © 2017 International Society for Autism Research, Wiley Periodicals, Inc. © 2017 International Society for Autism Research, Wiley Periodicals, Inc.

Diminutives facilitate word segmentation in natural speech: cross-linguistic evidence.

PubMed

Kempe, Vera; Brooks, Patricia J; Gillis, Steven; Samson, Graham

2007-06-01

Final-syllable invariance is characteristic of diminutives (e.g., doggie), which are a pervasive feature of the child-directed speech registers of many languages. Invariance in word endings has been shown to facilitate word segmentation (Kempe, Brooks, & Gillis, 2005) in an incidental-learning paradigm in which synthesized Dutch pseudonouns were used. To broaden the cross-linguistic evidence for this invariance effect and to increase its ecological validity, adult English speakers (n=276) were exposed to naturally spoken Dutch or Russian pseudonouns presented in sentence contexts. A forced choice test was given to assess target recognition, with foils comprising unfamiliar syllable combinations in Experiments 1 and 2 and syllable combinations straddling word boundaries in Experiment 3. A control group (n=210) received the recognition test with no prior exposure to targets. Recognition performance improved with increasing final-syllable rhyme invariance, with larger increases for the experimental group. This confirms that word ending invariance is a valid segmentation cue in artificial, as well as naturalistic, speech and that diminutives may aid segmentation in a number of languages.

On the Time Course of Vocal Emotion Recognition

PubMed Central

Pell, Marc D.; Kotz, Sonja A.

2011-01-01

How quickly do listeners recognize emotions from a speaker's voice, and does the time course for recognition vary by emotion type? To address these questions, we adapted the auditory gating paradigm to estimate how much vocal information is needed for listeners to categorize five basic emotions (anger, disgust, fear, sadness, happiness) and neutral utterances produced by male and female speakers of English. Semantically-anomalous pseudo-utterances (e.g., The rivix jolled the silling) conveying each emotion were divided into seven gate intervals according to the number of syllables that listeners heard from sentence onset. Participants (n = 48) judged the emotional meaning of stimuli presented at each gate duration interval, in a successive, blocked presentation format. Analyses looked at how recognition of each emotion evolves as an utterance unfolds and estimated the “identification point” for each emotion. Results showed that anger, sadness, fear, and neutral expressions are recognized more accurately at short gate intervals than happiness, and particularly disgust; however, as speech unfolds, recognition of happiness improves significantly towards the end of the utterance (and fear is recognized more accurately than other emotions). When the gate associated with the emotion identification point of each stimulus was calculated, data indicated that fear (M = 517 ms), sadness (M = 576 ms), and neutral (M = 510 ms) expressions were identified from shorter acoustic events than the other emotions. These data reveal differences in the underlying time course for conscious recognition of basic emotions from vocal expressions, which should be accounted for in studies of emotional speech processing. PMID:22087275

Identification and tracking of particular speaker in noisy environment

NASA Astrophysics Data System (ADS)

Sawada, Hideyuki; Ohkado, Minoru

2004-10-01

Human is able to exchange information smoothly using voice under different situations such as noisy environment in a crowd and with the existence of plural speakers. We are able to detect the position of a source sound in 3D space, extract a particular sound from mixed sounds, and recognize who is talking. By realizing this mechanism with a computer, new applications will be presented for recording a sound with high quality by reducing noise, presenting a clarified sound, and realizing a microphone-free speech recognition by extracting particular sound. The paper will introduce a realtime detection and identification of particular speaker in noisy environment using a microphone array based on the location of a speaker and the individual voice characteristics. The study will be applied to develop an adaptive auditory system of a mobile robot which collaborates with a factory worker.

Speech Breathing in Speakers Who Use an Electrolarynx

ERIC Educational Resources Information Center

Bohnenkamp, Todd A.; Stowell, Talena; Hesse, Joy; Wright, Simon

2010-01-01

Speakers who use an electrolarynx following a total laryngectomy no longer require pulmonary support for speech. Subsequently, chest wall movements may be affected; however, chest wall movements in these speakers are not well defined. The purpose of this investigation was to evaluate speech breathing in speakers who use an electrolarynx during…

Facilitating Comprehension of Non-Native English Speakers during Lectures in English with STR-Texts

ERIC Educational Resources Information Center

Shadiev, Rustam; Wu, Ting-Ting; Huang, Yueh-Min

2018-01-01

We provided texts generated by speech-to text-recognition (STR) technology for non-native English speaking students during lectures in English in order to test whether STR-texts were useful for enhancing students' comprehension of lectures. To this end, we carried out an experiment in which 60 participants were randomly assigned to a control group…

Input and Output Mechanisms and Devices. Phase I: Adding Voice Output to a Speaker-Independent Recognition System.

ERIC Educational Resources Information Center

Scott Instruments Corp., Denton, TX.

This project was designed to develop techniques for adding low-cost speech synthesis to educational software. Four tasks were identified for the study: (1) select a microcomputer with a built-in analog-to-digital converter that is currently being used in educational environments; (2) determine the feasibility of implementing expansion and playback…

STS-41 Voice Command System Flight Experiment Report

NASA Technical Reports Server (NTRS)

Salazar, George A.

1981-01-01

This report presents the results of the Voice Command System (VCS) flight experiment on the five-day STS-41 mission. Two mission specialists,Bill Shepherd and Bruce Melnick, used the speaker-dependent system to evaluate the operational effectiveness of using voice to control a spacecraft system. In addition, data was gathered to analyze the effects of microgravity on speech recognition performance.

Masking release due to linguistic and phonetic dissimilarity between the target and masker speech

PubMed Central

Calandruccio, Lauren; Brouwer, Susanne; Van Engen, Kristin J.; Dhar, Sumitrajit; Bradlow, Ann R.

2013-01-01

Purpose To investigate masking release for speech maskers for linguistically and phonetically close (English and Dutch) and distant (English and Mandarin) language pairs. Method Twenty monolingual speakers of English with normal-audiometric thresholds participated. Data are reported for an English sentence recognition task in English, Dutch and Mandarin competing speech maskers (Experiment I) and noise maskers (Experiment II) that were matched either to the long-term-average-speech spectra or to the temporal modulations of the speech maskers from Experiment I. Results Results indicated that listener performance increased as the target-to-masker linguistic distance increased (English-in-English < English-in-Dutch < English-in-Mandarin). Conclusions Spectral differences between maskers can account for some, but not all, of the variation in performance between maskers; however, temporal differences did not seem to play a significant role. PMID:23800811

Formant trajectory characteristics in speakers with dysarthria and homogeneous speech intelligibility scores: Further data

NASA Astrophysics Data System (ADS)

Kim, Yunjung; Weismer, Gary; Kent, Ray D.

2005-09-01

In previous work [J. Acoust. Soc. Am. 117, 2605 (2005)], we reported on formant trajectory characteristics of a relatively large number of speakers with dysarthria and near-normal speech intelligibility. The purpose of that analysis was to begin a documentation of the variability, within relatively homogeneous speech-severity groups, of acoustic measures commonly used to predict across-speaker variation in speech intelligibility. In that study we found that even with near-normal speech intelligibility (90%-100%), many speakers had reduced formant slopes for some words and distributional characteristics of acoustic measures that were different than values obtained from normal speakers. In the current report we extend those findings to a group of speakers with dysarthria with somewhat poorer speech intelligibility than the original group. Results are discussed in terms of the utility of certain acoustic measures as indices of speech intelligibility, and as explanatory data for theories of dysarthria. [Work supported by NIH Award R01 DC00319.

The Role of Native-Language Knowledge in the Perception of Casual Speech in a Second Language

PubMed Central

Mitterer, Holger; Tuinman, Annelie

2012-01-01

Casual speech processes, such as /t/-reduction, make word recognition harder. Additionally, word recognition is also harder in a second language (L2). Combining these challenges, we investigated whether L2 learners have recourse to knowledge from their native language (L1) when dealing with casual speech processes in their L2. In three experiments, production and perception of /t/-reduction was investigated. An initial production experiment showed that /t/-reduction occurred in both languages and patterned similarly in proper nouns but differed when /t/ was a verbal inflection. Two perception experiments compared the performance of German learners of Dutch with that of native speakers for nouns and verbs. Mirroring the production patterns, German learners’ performance strongly resembled that of native Dutch listeners when the reduced /t/ was part of a word stem, but deviated where /t/ was a verbal inflection. These results suggest that a casual speech process in a second language is problematic for learners when the process is not known from the leaner’s native language, similar to what has been observed for phoneme contrasts. PMID:22811675

Words from spontaneous conversational speech can be recognized with human-like accuracy by an error-driven learning algorithm that discriminates between meanings straight from smart acoustic features, bypassing the phoneme as recognition unit.

PubMed

Arnold, Denis; Tomaschek, Fabian; Sering, Konstantin; Lopez, Florence; Baayen, R Harald

2017-01-01

Sound units play a pivotal role in cognitive models of auditory comprehension. The general consensus is that during perception listeners break down speech into auditory words and subsequently phones. Indeed, cognitive speech recognition is typically taken to be computationally intractable without phones. Here we present a computational model trained on 20 hours of conversational speech that recognizes word meanings within the range of human performance (model 25%, native speakers 20-44%), without making use of phone or word form representations. Our model also generates successfully predictions about the speed and accuracy of human auditory comprehension. At the heart of the model is a 'wide' yet sparse two-layer artificial neural network with some hundred thousand input units representing summaries of changes in acoustic frequency bands, and proxies for lexical meanings as output units. We believe that our model holds promise for resolving longstanding theoretical problems surrounding the notion of the phone in linguistic theory.

Development and validation of a smartphone-based digits-in-noise hearing test in South African English.

PubMed

Potgieter, Jenni-Marí; Swanepoel, De Wet; Myburgh, Hermanus Carel; Hopper, Thomas Christopher; Smits, Cas

2015-07-01

The objective of this study was to develop and validate a smartphone-based digits-in-noise hearing test for South African English. Single digits (0-9) were recorded and spoken by a first language English female speaker. Level corrections were applied to create a set of homogeneous digits with steep speech recognition functions. A smartphone application was created to utilize 120 digit-triplets in noise as test material. An adaptive test procedure determined the speech reception threshold (SRT). Experiments were performed to determine headphones effects on the SRT and to establish normative data. Participants consisted of 40 normal-hearing subjects with thresholds ≤15 dB across the frequency spectrum (250-8000 Hz) and 186 subjects with normal-hearing in both ears, or normal-hearing in the better ear. The results show steep speech recognition functions with a slope of 20%/dB for digit-triplets presented in noise using the smartphone application. The results of five headphone types indicate that the smartphone-based hearing test is reliable and can be conducted using standard Android smartphone headphones or clinical headphones. A digits-in-noise hearing test was developed and validated for South Africa. The mean SRT and speech recognition functions correspond to previous developed telephone-based digits-in-noise tests.

Vowel reduction across tasks for male speakers of American English.

PubMed

Kuo, Christina; Weismer, Gary

2016-07-01

This study examined acoustic variation of vowels within speakers across speech tasks. The overarching goal of the study was to understand within-speaker variation as one index of the range of normal speech motor behavior for American English vowels. Ten male speakers of American English performed four speech tasks including citation form sentence reading with a clear-speech style (clear-speech), citation form sentence reading (citation), passage reading (reading), and conversational speech (conversation). Eight monophthong vowels in a variety of consonant contexts were studied. Clear-speech was operationally defined as the reference point for describing variation. Acoustic measures associated with the conventions of vowel targets were obtained and examined. These included temporal midpoint formant frequencies for the first three formants (F1, F2, and F3) and the derived Euclidean distances in the F1-F2 and F2-F3 planes. Results indicated that reduction toward the center of the F1-F2 and F2-F3 planes increased in magnitude across the tasks in the order of clear-speech, citation, reading, and conversation. The cross-task variation was comparable for all speakers despite fine-grained individual differences. The characteristics of systematic within-speaker acoustic variation across tasks have potential implications for the understanding of the mechanisms of speech motor control and motor speech disorders.

Sensing of Particular Speakers for the Construction of Voice Interface Utilized in Noisy Environment

NASA Astrophysics Data System (ADS)

Sawada, Hideyuki; Ohkado, Minoru

Human is able to exchange information smoothly using voice under different situations such as noisy environment in a crowd and with the existence of plural speakers. We are able to detect the position of a source sound in 3D space, extract a particular sound from mixed sounds, and recognize who is talking. By realizing this mechanism with a computer, new applications will be presented for recording a sound with high quality by reducing noise, presenting a clarified sound, and realizing a microphone-free speech recognition by extracting particular sound. The paper will introduce a realtime detection and identification of particular speaker in noisy environment using a microphone array based on the location of a speaker and the individual voice characteristics. The study will be applied to develop an adaptive auditory system of a mobile robot which collaborates with a factory worker.

Intelligibility of clear speech: effect of instruction.

PubMed

Lam, Jennifer; Tjaden, Kris

2013-10-01

The authors investigated how clear speech instructions influence sentence intelligibility. Twelve speakers produced sentences in habitual, clear, hearing impaired, and overenunciate conditions. Stimuli were amplitude normalized and mixed with multitalker babble for orthographic transcription by 40 listeners. The main analysis investigated percentage-correct intelligibility scores as a function of the 4 conditions and speaker sex. Additional analyses included listener response variability, individual speaker trends, and an alternate intelligibility measure: proportion of content words correct. Relative to the habitual condition, the overenunciate condition was associated with the greatest intelligibility benefit, followed by the hearing impaired and clear conditions. Ten speakers followed this trend. The results indicated different patterns of clear speech benefit for male and female speakers. Greater listener variability was observed for speakers with inherently low habitual intelligibility compared to speakers with inherently high habitual intelligibility. Stable proportions of content words were observed across conditions. Clear speech instructions affected the magnitude of the intelligibility benefit. The instruction to overenunciate may be most effective in clear speech training programs. The findings may help explain the range of clear speech intelligibility benefit previously reported. Listener variability analyses suggested the importance of obtaining multiple listener judgments of intelligibility, especially for speakers with inherently low habitual intelligibility.

The Communication of Public Speaking Anxiety: Perceptions of Asian and American Speakers.

ERIC Educational Resources Information Center

Martini, Marianne; And Others

1992-01-01

Finds that U.S. audiences perceive Asian speakers to have more speech anxiety than U.S. speakers, even though Asian speakers do not self-report higher anxiety levels. Confirms that speech state anxiety is not communicated effectively between speakers and audiences for Asian or U.S. speakers. (SR)

The Impact of Early Bilingualism on Face Recognition Processes.

PubMed

Kandel, Sonia; Burfin, Sabine; Méary, David; Ruiz-Tada, Elisa; Costa, Albert; Pascalis, Olivier

2016-01-01

Early linguistic experience has an impact on the way we decode audiovisual speech in face-to-face communication. The present study examined whether differences in visual speech decoding could be linked to a broader difference in face processing. To identify a phoneme we have to do an analysis of the speaker's face to focus on the relevant cues for speech decoding (e.g., locating the mouth with respect to the eyes). Face recognition processes were investigated through two classic effects in face recognition studies: the Other-Race Effect (ORE) and the Inversion Effect. Bilingual and monolingual participants did a face recognition task with Caucasian faces (own race), Chinese faces (other race), and cars that were presented in an Upright or Inverted position. The results revealed that monolinguals exhibited the classic ORE. Bilinguals did not. Overall, bilinguals were slower than monolinguals. These results suggest that bilinguals' face processing abilities differ from monolinguals'. Early exposure to more than one language may lead to a perceptual organization that goes beyond language processing and could extend to face analysis. We hypothesize that these differences could be due to the fact that bilinguals focus on different parts of the face than monolinguals, making them more efficient in other race face processing but slower. However, more studies using eye-tracking techniques are necessary to confirm this explanation.

Video indexing based on image and sound

NASA Astrophysics Data System (ADS)

Faudemay, Pascal; Montacie, Claude; Caraty, Marie-Jose

1997-10-01

Video indexing is a major challenge for both scientific and economic reasons. Information extraction can sometimes be easier from sound channel than from image channel. We first present a multi-channel and multi-modal query interface, to query sound, image and script through 'pull' and 'push' queries. We then summarize the segmentation phase, which needs information from the image channel. Detection of critical segments is proposed. It should speed-up both automatic and manual indexing. We then present an overview of the information extraction phase. Information can be extracted from the sound channel, through speaker recognition, vocal dictation with unconstrained vocabularies, and script alignment with speech. We present experiment results for these various techniques. Speaker recognition methods were tested on the TIMIT and NTIMIT database. Vocal dictation as experimented on newspaper sentences spoken by several speakers. Script alignment was tested on part of a carton movie, 'Ivanhoe'. For good quality sound segments, error rates are low enough for use in indexing applications. Major issues are the processing of sound segments with noise or music, and performance improvement through the use of appropriate, low-cost architectures or networks of workstations.

Rhythmic patterning in Malaysian and Singapore English.

PubMed

Tan, Rachel Siew Kuang; Low, Ee-Ling

2014-06-01

Previous work on the rhythm of Malaysian English has been based on impressionistic observations. This paper utilizes acoustic analysis to measure the rhythmic patterns of Malaysian English. Recordings of the read speech and spontaneous speech of 10 Malaysian English speakers were analyzed and compared with recordings of an equivalent sample of Singaporean English speakers. Analysis was done using two rhythmic indexes, the PVI and VarcoV. It was found that although the rhythm of read speech of the Singaporean speakers was syllable-based as described by previous studies, the rhythm of the Malaysian speakers was even more syllable-based. Analysis of the syllables in specific utterances showed that Malaysian speakers did not reduce vowels as much as Singaporean speakers in cases of syllables in utterances. Results of the spontaneous speech confirmed the findings for the read speech; that is, the same rhythmic patterning was found which normally triggers vowel reductions.

Effect of delayed auditory feedback on normal speakers at two speech rates

NASA Astrophysics Data System (ADS)

Stuart, Andrew; Kalinowski, Joseph; Rastatter, Michael P.; Lynch, Kerry

2002-05-01

This study investigated the effect of short and long auditory feedback delays at two speech rates with normal speakers. Seventeen participants spoke under delayed auditory feedback (DAF) at 0, 25, 50, and 200 ms at normal and fast rates of speech. Significantly two to three times more dysfluencies were displayed at 200 ms (p<0.05) relative to no delay or the shorter delays. There were significantly more dysfluencies observed at the fast rate of speech (p=0.028). These findings implicate the peripheral feedback system(s) of fluent speakers for the disruptive effects of DAF on normal speech production at long auditory feedback delays. Considering the contrast in fluency/dysfluency exhibited between normal speakers and those who stutter at short and long delays, it appears that speech disruption of normal speakers under DAF is a poor analog of stuttering.

Dysprosody and Stimulus Effects in Cantonese Speakers with Parkinson's Disease

ERIC Educational Resources Information Center

Ma, Joan K.-Y.; Whitehill, Tara; Cheung, Katherine S.-K.

2010-01-01

Background: Dysprosody is a common feature in speakers with hypokinetic dysarthria. However, speech prosody varies across different types of speech materials. This raises the question of what is the most appropriate speech material for the evaluation of dysprosody. Aims: To characterize the prosodic impairment in Cantonese speakers with…

Clear Speech Variants: An Acoustic Study in Parkinson's Disease

ERIC Educational Resources Information Center

Lam, Jennifer; Tjaden, Kris

2016-01-01

Purpose: The authors investigated how different variants of clear speech affect segmental and suprasegmental acoustic measures of speech in speakers with Parkinson's disease and a healthy control group. Method: A total of 14 participants with Parkinson's disease and 14 control participants served as speakers. Each speaker produced 18 different…

The Interaction of Lexical Characteristics and Speech Production in Parkinson's Disease

ERIC Educational Resources Information Center

Chiu, Yi-Fang; Forrest, Karen

2017-01-01

Purpose: This study sought to investigate the interaction of speech movement execution with higher order lexical parameters. The authors examined how lexical characteristics affect speech output in individuals with Parkinson's disease (PD) and healthy control (HC) speakers. Method: Twenty speakers with PD and 12 healthy speakers read sentences…

Predicting Intelligibility Gains in Individuals with Dysarthria from Baseline Speech Features

ERIC Educational Resources Information Center

Fletcher, Annalise R.; McAuliffe, Megan J.; Lansford, Kaitlin L.; Sinex, Donal G.; Liss, Julie M.

2017-01-01

Purpose: Across the treatment literature, behavioral speech modifications have produced variable intelligibility changes in speakers with dysarthria. This study is the first of two articles exploring whether measurements of baseline speech features can predict speakers' responses to these modifications. Method: Fifty speakers (7 older individuals…

Influence of Visual Information on the Intelligibility of Dysarthric Speech

ERIC Educational Resources Information Center

Keintz, Connie K.; Bunton, Kate; Hoit, Jeannette D.

2007-01-01

Purpose: To examine the influence of visual information on speech intelligibility for a group of speakers with dysarthria associated with Parkinson's disease. Method: Eight speakers with Parkinson's disease and dysarthria were recorded while they read sentences. Speakers performed a concurrent manual task to facilitate typical speech production.…

Speech Intelligibility in Severe Adductor Spasmodic Dysphonia

ERIC Educational Resources Information Center

Bender, Brenda K.; Cannito, Michael P.; Murry, Thomas; Woodson, Gayle E.

2004-01-01

This study compared speech intelligibility in nondisabled speakers and speakers with adductor spasmodic dysphonia (ADSD) before and after botulinum toxin (Botox) injection. Standard speech samples were obtained from 10 speakers diagnosed with severe ADSD prior to and 1 month following Botox injection, as well as from 10 age- and gender-matched…

The Effect of Noise on Relationships Between Speech Intelligibility and Self-Reported Communication Measures in Tracheoesophageal Speakers.

PubMed

Eadie, Tanya L; Otero, Devon Sawin; Bolt, Susan; Kapsner-Smith, Mara; Sullivan, Jessica R

2016-08-01

The purpose of this study was to examine how sentence intelligibility relates to self-reported communication in tracheoesophageal speakers when speech intelligibility is measured in quiet and noise. Twenty-four tracheoesophageal speakers who were at least 1 year postlaryngectomy provided audio recordings of 5 sentences from the Sentence Intelligibility Test. Speakers also completed self-reported measures of communication-the Voice Handicap Index-10 and the Communicative Participation Item Bank short form. Speech recordings were presented to 2 groups of inexperienced listeners who heard sentences in quiet or noise. Listeners transcribed the sentences to yield speech intelligibility scores. Very weak relationships were found between intelligibility in quiet and measures of voice handicap and communicative participation. Slightly stronger, but still weak and nonsignificant, relationships were observed between measures of intelligibility in noise and both self-reported measures. However, 12 speakers who were more than 65% intelligible in noise showed strong and statistically significant relationships with both self-reported measures (R2 = .76-.79). Speech intelligibility in quiet is a weak predictor of self-reported communication measures in tracheoesophageal speakers. Speech intelligibility in noise may be a better metric of self-reported communicative function for speakers who demonstrate higher speech intelligibility in noise.

Segment-based acoustic models for continuous speech recognition

NASA Astrophysics Data System (ADS)

Ostendorf, Mari; Rohlicek, J. R.

1993-07-01

This research aims to develop new and more accurate stochastic models for speaker-independent continuous speech recognition, by extending previous work in segment-based modeling and by introducing a new hierarchical approach to representing intra-utterance statistical dependencies. These techniques, which are more costly than traditional approaches because of the large search space associated with higher order models, are made feasible through rescoring a set of HMM-generated N-best sentence hypotheses. We expect these different modeling techniques to result in improved recognition performance over that achieved by current systems, which handle only frame-based observations and assume that these observations are independent given an underlying state sequence. In the fourth quarter of the project, we have completed the following: (1) ported our recognition system to the Wall Street Journal task, a standard task in the ARPA community; (2) developed an initial dependency-tree model of intra-utterance observation correlation; and (3) implemented baseline language model estimation software. Our initial results on the Wall Street Journal task are quite good and represent significantly improved performance over most HMM systems reporting on the Nov. 1992 5k vocabulary test set.

Retrieving Tract Variables From Acoustics: A Comparison of Different Machine Learning Strategies.

PubMed

Mitra, Vikramjit; Nam, Hosung; Espy-Wilson, Carol Y; Saltzman, Elliot; Goldstein, Louis

2010-09-13

Many different studies have claimed that articulatory information can be used to improve the performance of automatic speech recognition systems. Unfortunately, such articulatory information is not readily available in typical speaker-listener situations. Consequently, such information has to be estimated from the acoustic signal in a process which is usually termed "speech-inversion." This study aims to propose and compare various machine learning strategies for speech inversion: Trajectory mixture density networks (TMDNs), feedforward artificial neural networks (FF-ANN), support vector regression (SVR), autoregressive artificial neural network (AR-ANN), and distal supervised learning (DSL). Further, using a database generated by the Haskins Laboratories speech production model, we test the claim that information regarding constrictions produced by the distinct organs of the vocal tract (vocal tract variables) is superior to flesh-point information (articulatory pellet trajectories) for the inversion process.

A virtual speaker in noisy classroom conditions: supporting or disrupting children's listening comprehension?

PubMed

Nirme, Jens; Haake, Magnus; Lyberg Åhlander, Viveka; Brännström, Jonas; Sahlén, Birgitta

2018-04-05

Seeing a speaker's face facilitates speech recognition, particularly under noisy conditions. Evidence for how it might affect comprehension of the content of the speech is more sparse. We investigated how children's listening comprehension is affected by multi-talker babble noise, with or without presentation of a digitally animated virtual speaker, and whether successful comprehension is related to performance on a test of executive functioning. We performed a mixed-design experiment with 55 (34 female) participants (8- to 9-year-olds), recruited from Swedish elementary schools. The children were presented with four different narratives, each in one of four conditions: audio-only presentation in a quiet setting, audio-only presentation in noisy setting, audio-visual presentation in a quiet setting, and audio-visual presentation in a noisy setting. After each narrative, the children answered questions on the content and rated their perceived listening effort. Finally, they performed a test of executive functioning. We found significantly fewer correct answers to explicit content questions after listening in noise. This negative effect was only mitigated to a marginally significant degree by audio-visual presentation. Strong executive function only predicted more correct answers in quiet settings. Altogether, our results are inconclusive regarding how seeing a virtual speaker affects listening comprehension. We discuss how methodological adjustments, including modifications to our virtual speaker, can be used to discriminate between possible explanations to our results and contribute to understanding the listening conditions children face in a typical classroom.

Clear Speech Variants: An Acoustic Study in Parkinson's Disease.

PubMed

Lam, Jennifer; Tjaden, Kris

2016-08-01

The authors investigated how different variants of clear speech affect segmental and suprasegmental acoustic measures of speech in speakers with Parkinson's disease and a healthy control group. A total of 14 participants with Parkinson's disease and 14 control participants served as speakers. Each speaker produced 18 different sentences selected from the Sentence Intelligibility Test (Yorkston & Beukelman, 1996). All speakers produced stimuli in 4 speaking conditions (habitual, clear, overenunciate, and hearing impaired). Segmental acoustic measures included vowel space area and first moment (M1) coefficient difference measures for consonant pairs. Second formant slope of diphthongs and measures of vowel and fricative durations were also obtained. Suprasegmental measures included fundamental frequency, sound pressure level, and articulation rate. For the majority of adjustments, all variants of clear speech instruction differed from the habitual condition. The overenunciate condition elicited the greatest magnitude of change for segmental measures (vowel space area, vowel durations) and the slowest articulation rates. The hearing impaired condition elicited the greatest fricative durations and suprasegmental adjustments (fundamental frequency, sound pressure level). Findings have implications for a model of speech production for healthy speakers as well as for speakers with dysarthria. Findings also suggest that particular clear speech instructions may target distinct speech subsystems.

Production Variability and Single Word Intelligibility in Aphasia and Apraxia of Speech

ERIC Educational Resources Information Center

Haley, Katarina L.; Martin, Gwenyth

2011-01-01

This study was designed to estimate test-retest reliability of orthographic speech intelligibility testing in speakers with aphasia and AOS and to examine its relationship to the consistency of speaker and listener responses. Monosyllabic single word speech samples were recorded from 13 speakers with coexisting aphasia and AOS. These words were…

Not so fast: Fast speech correlates with lower lexical and structural information.

PubMed

Cohen Priva, Uriel

2017-03-01

Speakers dynamically adjust their speech rate throughout conversations. These adjustments have been linked to cognitive and communicative limitations: for example, speakers speak words that are contextually unexpected (and thus add more information) with slower speech rates. This raises the question whether limitations of this type vary wildly across speakers or are relatively constant. The latter predicts that across speakers (or conversations), speech rate and the amount of information content are inversely correlated: on average, speakers can either provide high information content or speak quickly, but not both. Using two corpus studies replicated across two corpora, I demonstrate that indeed, fast speech correlates with the use of less informative words and syntactic structures. Thus, while there are individual differences in overall information throughput, speakers are more similar in this aspect than differences in speech rate would suggest. The results suggest that information theoretic constraints on production operate at a higher level than was observed before and affect language throughout production, not only after words and structures are chosen. Copyright © 2016 Elsevier B.V. All rights reserved.

[Characteristics, advantages, and limits of matrix tests].

PubMed

Brand, T; Wagener, K C

2017-03-01

Deterioration of communication abilities due to hearing problems is particularly relevant in listening situations with noise. Therefore, speech intelligibility tests in noise are required for audiological diagnostics and evaluation of hearing rehabilitation. This study analyzed the characteristics of matrix tests assessing the 50 % speech recognition threshold in noise. What are their advantages and limitations? Matrix tests are based on a matrix of 50 words (10 five-word sentences with same grammatical structure). In the standard setting, 20 sentences are presented using an adaptive procedure estimating the individual 50 % speech recognition threshold in noise. At present, matrix tests in 17 different languages are available. A high international comparability of matrix tests exists. The German language matrix test (OLSA, male speaker) has a reference 50 % speech recognition threshold of -7.1 (± 1.1) dB SNR. Before using a matrix test for the first time, the test person has to become familiar with the basic speech material using two training lists. Hereafter, matrix tests produce constant results even if repeated many times. Matrix tests are suitable for users of hearing aids and cochlear implants, particularly for assessment of benefit during the fitting process. Matrix tests can be performed in closed form and consequently with non-native listeners, even if the experimenter does not speak the test person's native language. Short versions of matrix tests are available for listeners with a shorter memory span, e.g., children.

A Hybrid Acoustic and Pronunciation Model Adaptation Approach for Non-native Speech Recognition

NASA Astrophysics Data System (ADS)

Oh, Yoo Rhee; Kim, Hong Kook

In this paper, we propose a hybrid model adaptation approach in which pronunciation and acoustic models are adapted by incorporating the pronunciation and acoustic variabilities of non-native speech in order to improve the performance of non-native automatic speech recognition (ASR). Specifically, the proposed hybrid model adaptation can be performed at either the state-tying or triphone-modeling level, depending at which acoustic model adaptation is performed. In both methods, we first analyze the pronunciation variant rules of non-native speakers and then classify each rule as either a pronunciation variant or an acoustic variant. The state-tying level hybrid method then adapts pronunciation models and acoustic models by accommodating the pronunciation variants in the pronunciation dictionary and by clustering the states of triphone acoustic models using the acoustic variants, respectively. On the other hand, the triphone-modeling level hybrid method initially adapts pronunciation models in the same way as in the state-tying level hybrid method; however, for the acoustic model adaptation, the triphone acoustic models are then re-estimated based on the adapted pronunciation models and the states of the re-estimated triphone acoustic models are clustered using the acoustic variants. From the Korean-spoken English speech recognition experiments, it is shown that ASR systems employing the state-tying and triphone-modeling level adaptation methods can relatively reduce the average word error rates (WERs) by 17.1% and 22.1% for non-native speech, respectively, when compared to a baseline ASR system.

Combining Multiple Knowledge Sources for Speech Recognition

DTIC Science & Technology

1988-09-15

Thus, the first is thle to clarify the pronunciationt ( TASSEAJ for the acronym TASA !). best adaptation sentence, the second sentence, whens addled...10 rapid adapltati,,n sen- tenrces, and 15 spell-i,, de phrases. 6101 resource rirailageo lei SPEAKER-DEPENDENT DATABASE sentences were randortily...combining the smoothed phoneme models with the de - system tested on a standard database using two well de . tailed context models. BYBLOS makes maximal use

Reduced efficiency of audiovisual integration for nonnative speech.

PubMed

Yi, Han-Gyol; Phelps, Jasmine E B; Smiljanic, Rajka; Chandrasekaran, Bharath

2013-11-01

The role of visual cues in native listeners' perception of speech produced by nonnative speakers has not been extensively studied. Native perception of English sentences produced by native English and Korean speakers in audio-only and audiovisual conditions was examined. Korean speakers were rated as more accented in audiovisual than in the audio-only condition. Visual cues enhanced word intelligibility for native English speech but less so for Korean-accented speech. Reduced intelligibility of Korean-accented audiovisual speech was associated with implicit visual biases, suggesting that listener-related factors partially influence the efficiency of audiovisual integration for nonnative speech perception.

Revisiting Speech Rate and Utterance Length Manipulations in Stuttering Speakers

ERIC Educational Resources Information Center

Blomgren, Michael; Goberman, Alexander M.

2008-01-01

The goal of this study was to evaluate stuttering frequency across a multidimensional (2 x 2) hierarchy of speech performance tasks. Specifically, this study examined the interaction between changes in length of utterance and levels of speech rate stability. Forty-four adult male speakers participated in the study (22 stuttering speakers and 22…

Status report on speech research. A report on the status and progress of studies of the nature of speech, instrumentation for its investigation and practical applications

NASA Astrophysics Data System (ADS)

Studdert-Kennedy, M.; Obrien, N.

1983-05-01

This report is one of a regular series on the status and progress of studies on the nature of speech, instrumentation for its investigation, and practical applications. Manuscripts cover the following topics: The influence of subcategorical mismatches on lexical access; The Serbo-Croatian orthography constraints the reader to a phonologically analytic strategy; Grammatical priming effects between pronouns and inflected verb forms; Misreadings by beginning readers of Serrbo-Croatian; Bi-alphabetism and work recognition; Orthographic and phonemic coding for word identification: Evidence for Hebrew; Stress and vowel duration effects on syllable recognition; Phonetic and auditory trading relations between acoustic cues in speech perception: Further results; Linguistic coding by deaf children in relation beginning reading success; Determinants of spelling ability in deaf and hearing adults: Access to linguistic structures; A dynamical basis for action systems; On the space-time structure of human interlimb coordination; Some acoustic and physiological observations on diphthongs; Relationship between pitch control and vowel articulation; Laryngeal vibrations: A comparison between high-speed filming and glottographic techniques; Compensatory articulation in hearing impaired speakers: A cinefluorographic study; and Review (Pierre Delattre: Studies in comparative phonetics.)

Towards the identification of Idiopathic Parkinson’s Disease from the speech. New articulatory kinetic biomarkers

PubMed Central

Shattuck-Hufnagel, S.; Choi, J. Y.; Moro-Velázquez, L.; Gómez-García, J. A.

2017-01-01

Although a large amount of acoustic indicators have already been proposed in the literature to evaluate the hypokinetic dysarthria of people with Parkinson’s Disease, the goal of this work is to identify and interpret new reliable and complementary articulatory biomarkers that could be applied to predict/evaluate Parkinson’s Disease from a diadochokinetic test, contributing to the possibility of a further multidimensional analysis of the speech of parkinsonian patients. The new biomarkers proposed are based on the kinetic behaviour of the envelope trace, which is directly linked with the articulatory dysfunctions introduced by the disease since the early stages. The interest of these new articulatory indicators stands on their easiness of identification and interpretation, and their potential to be translated into computer based automatic methods to screen the disease from the speech. Throughout this paper, the accuracy provided by these acoustic kinetic biomarkers is compared with the one obtained with a baseline system based on speaker identification techniques. Results show accuracies around 85% that are in line with those obtained with the complex state of the art speaker recognition techniques, but with an easier physical interpretation, which open the possibility to be transferred to a clinical setting. PMID:29240814

The influence of visual speech information on the intelligibility of English consonants produced by non-native speakers.

PubMed

Kawase, Saya; Hannah, Beverly; Wang, Yue

2014-09-01

This study examines how visual speech information affects native judgments of the intelligibility of speech sounds produced by non-native (L2) speakers. Native Canadian English perceivers as judges perceived three English phonemic contrasts (/b-v, θ-s, l-ɹ/) produced by native Japanese speakers as well as native Canadian English speakers as controls. These stimuli were presented under audio-visual (AV, with speaker voice and face), audio-only (AO), and visual-only (VO) conditions. The results showed that, across conditions, the overall intelligibility of Japanese productions of the native (Japanese)-like phonemes (/b, s, l/) was significantly higher than the non-Japanese phonemes (/v, θ, ɹ/). In terms of visual effects, the more visually salient non-Japanese phonemes /v, θ/ were perceived as significantly more intelligible when presented in the AV compared to the AO condition, indicating enhanced intelligibility when visual speech information is available. However, the non-Japanese phoneme /ɹ/ was perceived as less intelligible in the AV compared to the AO condition. Further analysis revealed that, unlike the native English productions, the Japanese speakers produced /ɹ/ without visible lip-rounding, indicating that non-native speakers' incorrect articulatory configurations may decrease the degree of intelligibility. These results suggest that visual speech information may either positively or negatively affect L2 speech intelligibility.

ChoiceKey: a real-time speech recognition program for psychology experiments with a small response set.

PubMed

Donkin, Christopher; Brown, Scott D; Heathcote, Andrew

2009-02-01

Psychological experiments often collect choice responses using buttonpresses. However, spoken responses are useful in many cases-for example, when working with special clinical populations, or when a paradigm demands vocalization, or when accurate response time measurements are desired. In these cases, spoken responses are typically collected using a voice key, which usually involves manual coding by experimenters in a tedious and error-prone manner. We describe ChoiceKey, an open-source speech recognition package for MATLAB. It can be optimized by training for small response sets and different speakers. We show ChoiceKey to be reliable with minimal training for most participants in experiments with two different responses. Problems presented by individual differences, and occasional atypical responses, are examined, and extensions to larger response sets are explored. The ChoiceKey source files and instructions may be downloaded as supplemental materials for this article from brm.psychonomic-journals.org/content/supplemental.

Automated Speech Rate Measurement in Dysarthria.

PubMed

Martens, Heidi; Dekens, Tomas; Van Nuffelen, Gwen; Latacz, Lukas; Verhelst, Werner; De Bodt, Marc

2015-06-01

In this study, a new algorithm for automated determination of speech rate (SR) in dysarthric speech is evaluated. We investigated how reliably the algorithm calculates the SR of dysarthric speech samples when compared with calculation performed by speech-language pathologists. The new algorithm was trained and tested using Dutch speech samples of 36 speakers with no history of speech impairment and 40 speakers with mild to moderate dysarthria. We tested the algorithm under various conditions: according to speech task type (sentence reading, passage reading, and storytelling) and algorithm optimization method (speaker group optimization and individual speaker optimization). Correlations between automated and human SR determination were calculated for each condition. High correlations between automated and human SR determination were found in the various testing conditions. The new algorithm measures SR in a sufficiently reliable manner. It is currently being integrated in a clinical software tool for assessing and managing prosody in dysarthric speech. Further research is needed to fine-tune the algorithm to severely dysarthric speech, to make the algorithm less sensitive to background noise, and to evaluate how the algorithm deals with syllabic consonants.

Speech transformations based on a sinusoidal representation

NASA Astrophysics Data System (ADS)

Quatieri, T. E.; McAulay, R. J.

1986-05-01

A new speech analysis/synthesis technique is presented which provides the basis for a general class of speech transformation including time-scale modification, frequency scaling, and pitch modification. These modifications can be performed with a time-varying change, permitting continuous adjustment of a speaker's fundamental frequency and rate of articulation. The method is based on a sinusoidal representation of the speech production mechanism that has been shown to produce synthetic speech that preserves the waveform shape and is essentially perceptually indistinguishable from the original. Although the analysis/synthesis system originally was designed for single-speaker signals, it is equally capable of recovering and modifying nonspeech signals such as music; multiple speakers, marine biologic sounds, and speakers in the presence of interferences such as noise and musical backgrounds.

Discrepant visual speech facilitates covert selective listening in "cocktail party" conditions.

PubMed

Williams, Jason A

2012-06-01

The presence of congruent visual speech information facilitates the identification of auditory speech, while the addition of incongruent visual speech information often impairs accuracy. This latter arrangement occurs naturally when one is being directly addressed in conversation but listens to a different speaker. Under these conditions, performance may diminish since: (a) one is bereft of the facilitative effects of the corresponding lip motion and (b) one becomes subject to visual distortion by incongruent visual speech; by contrast, speech intelligibility may be improved due to (c) bimodal localization of the central unattended stimulus. Participants were exposed to centrally presented visual and auditory speech while attending to a peripheral speech stream. In some trials, the lip movements of the central visual stimulus matched the unattended speech stream; in others, the lip movements matched the attended peripheral speech. Accuracy for the peripheral stimulus was nearly one standard deviation greater with incongruent visual information, compared to the congruent condition which provided bimodal pattern recognition cues. Likely, the bimodal localization of the central stimulus further differentiated the stimuli and thus facilitated intelligibility. Results are discussed with regard to similar findings in an investigation of the ventriloquist effect, and the relative strength of localization and speech cues in covert listening.

Effect of an 8-week practice of externally triggered speech on basal ganglia activity of stuttering and fluent speakers.

PubMed

Toyomura, Akira; Fujii, Tetsunoshin; Kuriki, Shinya

2015-04-01

The neural mechanisms underlying stuttering are not well understood. It is known that stuttering appears when persons who stutter speak in a self-paced manner, but speech fluency is temporarily increased when they speak in unison with external trigger such as a metronome. This phenomenon is very similar to the behavioral improvement by external pacing in patients with Parkinson's disease. Recent imaging studies have also suggested that the basal ganglia are involved in the etiology of stuttering. In addition, previous studies have shown that the basal ganglia are involved in self-paced movement. Then, the present study focused on the basal ganglia and explored whether long-term speech-practice using external triggers can induce modification of the basal ganglia activity of stuttering speakers. Our study of functional magnetic resonance imaging revealed that stuttering speakers possessed significantly lower activity in the basal ganglia than fluent speakers before practice, especially when their speech was self-paced. After an 8-week speech practice of externally triggered speech using a metronome, the significant difference in activity between the two groups disappeared. The cerebellar vermis of stuttering speakers showed significantly decreased activity during the self-paced speech in the second compared to the first experiment. The speech fluency and naturalness of the stuttering speakers were also improved. These results suggest that stuttering is associated with defective motor control during self-paced speech, and that the basal ganglia and the cerebellum are involved in an improvement of speech fluency of stuttering by the use of external trigger. Copyright © 2015 Elsevier Inc. All rights reserved.

When one person's mistake is another's standard usage: the effect of foreign accent on syntactic processing.

PubMed

Hanulíková, Adriana; van Alphen, Petra M; van Goch, Merel M; Weber, Andrea

2012-04-01

How do native listeners process grammatical errors that are frequent in non-native speech? We investigated whether the neural correlates of syntactic processing are modulated by speaker identity. ERPs to gender agreement errors in sentences spoken by a native speaker were compared with the same errors spoken by a non-native speaker. In line with previous research, gender violations in native speech resulted in a P600 effect (larger P600 for violations in comparison with correct sentences), but when the same violations were produced by the non-native speaker with a foreign accent, no P600 effect was observed. Control sentences with semantic violations elicited comparable N400 effects for both the native and the non-native speaker, confirming no general integration problem in foreign-accented speech. The results demonstrate that the P600 is modulated by speaker identity, extending our knowledge about the role of speaker's characteristics on neural correlates of speech processing.

The SRI NIST 2010 Speaker Recognition Evaluation System (PREPRINT)

DTIC Science & Technology

2011-01-01

of several subsystems with the use of adequate side information gives a 35% improvement on the standard telephone condition. We also show that a...ratio and amount of detected speech as side information . The SRI submissions were among the best-performing systems in SRE10. 2. COMMONALITIES This...Documentation Page Form ApprovedOMB No. 0704-0188 Public reporting burden for the collection of information is estimated to average 1 hour per response

Speaker Identity Supports Phonetic Category Learning

ERIC Educational Resources Information Center

Mani, Nivedita; Schneider, Signe

2013-01-01

Visual cues from the speaker's face, such as the discriminable mouth movements used to produce speech sounds, improve discrimination of these sounds by adults. The speaker's face, however, provides more information than just the mouth movements used to produce speech--it also provides a visual indexical cue of the identity of the speaker. The…

SPEECH HABILITATION IN THE SCHOOLS FOR THE CLEFT PALATE CHILD, THE NEW YORK STATE EDUCATION DEPARTMENT PROCEEDINGS (MARCH 17-20, 1965).

ERIC Educational Resources Information Center

VAN HATTUM, ROLLAND J.; AND OTHERS

DESIGNED TO STRENGTHEN THE SKILLS, COMPETENCIES, AND KNOWLEDGE OF SPEECH CORRECTION TEACHERS, THIS SUMMARY OF A SPECIAL STUDY INSTITUTE CONTAINS A SERIES OF PRESENTATIONS. SPEAKERS DISCUSS ASPECTS OF CLEFT PALATE INCLUDING SPEECH, SPEECH ANATOMY, SURGICAL AND DENTAL MANAGEMENT, DIAGNOSIS, AND SPEECH THERAPY. SPEAKERS REPRESENT MEDICAL AND…

Real-Time Control of an Articulatory-Based Speech Synthesizer for Brain Computer Interfaces

PubMed Central

Bocquelet, Florent; Hueber, Thomas; Girin, Laurent; Savariaux, Christophe; Yvert, Blaise

2016-01-01

Restoring natural speech in paralyzed and aphasic people could be achieved using a Brain-Computer Interface (BCI) controlling a speech synthesizer in real-time. To reach this goal, a prerequisite is to develop a speech synthesizer producing intelligible speech in real-time with a reasonable number of control parameters. We present here an articulatory-based speech synthesizer that can be controlled in real-time for future BCI applications. This synthesizer converts movements of the main speech articulators (tongue, jaw, velum, and lips) into intelligible speech. The articulatory-to-acoustic mapping is performed using a deep neural network (DNN) trained on electromagnetic articulography (EMA) data recorded on a reference speaker synchronously with the produced speech signal. This DNN is then used in both offline and online modes to map the position of sensors glued on different speech articulators into acoustic parameters that are further converted into an audio signal using a vocoder. In offline mode, highly intelligible speech could be obtained as assessed by perceptual evaluation performed by 12 listeners. Then, to anticipate future BCI applications, we further assessed the real-time control of the synthesizer by both the reference speaker and new speakers, in a closed-loop paradigm using EMA data recorded in real time. A short calibration period was used to compensate for differences in sensor positions and articulatory differences between new speakers and the reference speaker. We found that real-time synthesis of vowels and consonants was possible with good intelligibility. In conclusion, these results open to future speech BCI applications using such articulatory-based speech synthesizer. PMID:27880768

Is Language a Factor in the Perception of Foreign Accent Syndrome?

PubMed

Jose, Linda; Read, Jennifer; Miller, Nick

2016-06-01

Neurogenic foreign accent syndrome (FAS) is diagnosed when listeners perceive speech associated with motor speech impairments as foreign rather than disordered. Speakers with foreign accent syndrome typically have aphasia. It remains unclear how far language changes might contribute to the perception of foreign accent syndrome independent of accent. Judges with and without training in language analysis rated orthographic transcriptions of speech from people with foreign accent syndrome, speech-language disorder and no foreign accent syndrome, foreign accent without neurological impairment and healthy controls on scales of foreignness, normalness and disorderedness. Control speakers were judged as significantly more normal, less disordered and less foreign than other groups. Foreign accent syndrome speakers' transcriptions consistently profiled most closely to those of foreign speakers and significantly different to speakers with speech-language disorder. On normalness and foreignness ratings there were no significant differences between foreign and foreign accent syndrome speakers. For disorderedness, foreign accent syndrome participants fell midway between foreign speakers and those with speech-language impairment only. Slower rate, more hesitations, pauses within and between utterances influenced judgments, delineating control scripts from others. Word-level syntactic and morphological deviations and reduced syntactic and semantic repertoire linked strongly with foreignness perceptions. Greater disordered ratings related to word fragments, poorly intelligible grammatical structures and inappropriate word selection. Language changes influence foreignness perception. Clinical and theoretical issues are addressed.

Auditory perceptual simulation: Simulating speech rates or accents?

PubMed

Zhou, Peiyun; Christianson, Kiel

2016-07-01

When readers engage in Auditory Perceptual Simulation (APS) during silent reading, they mentally simulate characteristics of voices attributed to a particular speaker or a character depicted in the text. Previous research found that auditory perceptual simulation of a faster native English speaker during silent reading led to shorter reading times that auditory perceptual simulation of a slower non-native English speaker. Yet, it was uncertain whether this difference was triggered by the different speech rates of the speakers, or by the difficulty of simulating an unfamiliar accent. The current study investigates this question by comparing faster Indian-English speech and slower American-English speech in the auditory perceptual simulation paradigm. Analyses of reading times of individual words and the full sentence reveal that the auditory perceptual simulation effect again modulated reading rate, and auditory perceptual simulation of the faster Indian-English speech led to faster reading rates compared to auditory perceptual simulation of the slower American-English speech. The comparison between this experiment and the data from Zhou and Christianson (2016) demonstrate further that the "speakers'" speech rates, rather than the difficulty of simulating a non-native accent, is the primary mechanism underlying auditory perceptual simulation effects. Copyright © 2016 Elsevier B.V. All rights reserved.

Accent, intelligibility, and comprehensibility in the perception of foreign-accented Lombard speech

NASA Astrophysics Data System (ADS)

Li, Chi-Nin

2003-10-01

Speech produced in noise (Lombard speech) has been reported to be more intelligible than speech produced in quiet (normal speech). This study examined the perception of non-native Lombard speech in terms of intelligibility, comprehensibility, and degree of foreign accent. Twelve Cantonese speakers and a comparison group of English speakers read simple true and false English statements in quiet and in 70 dB of masking noise. Lombard and normal utterances were mixed with noise at a constant signal-to-noise ratio, and presented along with noise-free stimuli to eight new English listeners who provided transcription scores, comprehensibility ratings, and accent ratings. Analyses showed that, as expected, utterances presented in noise were less well perceived than were noise-free sentences, and that the Cantonese speakers' productions were more accented, but less intelligible and less comprehensible than those of the English speakers. For both groups of speakers, the Lombard sentences were correctly transcribed more often than their normal utterances in noisy conditions. However, the Cantonese-accented Lombard sentences were not rated as easier to understand than was the normal speech in all conditions. The assigned accent ratings were similar throughout all listening conditions. Implications of these findings will be discussed.

Phonologically-based biomarkers for major depressive disorder

NASA Astrophysics Data System (ADS)

Trevino, Andrea Carolina; Quatieri, Thomas Francis; Malyska, Nicolas

2011-12-01

Of increasing importance in the civilian and military population is the recognition of major depressive disorder at its earliest stages and intervention before the onset of severe symptoms. Toward the goal of more effective monitoring of depression severity, we introduce vocal biomarkers that are derived automatically from phonologically-based measures of speech rate. To assess our measures, we use a 35-speaker free-response speech database of subjects treated for depression over a 6-week duration. We find that dissecting average measures of speech rate into phone-specific characteristics and, in particular, combined phone-duration measures uncovers stronger relationships between speech rate and depression severity than global measures previously reported for a speech-rate biomarker. Results of this study are supported by correlation of our measures with depression severity and classification of depression state with these vocal measures. Our approach provides a general framework for analyzing individual symptom categories through phonological units, and supports the premise that speaking rate can be an indicator of psychomotor retardation severity.

The effects of gated speech on the fluency of speakers who stutter.

PubMed

Howell, Peter

2007-01-01

It is known that the speech of people who stutter improves when the speaker's own vocalization is changed while the participant is speaking. One explanation of these effects is the disruptive rhythm hypothesis (DRH). The DRH maintains that the manipulated sound only needs to disturb timing to affect speech control. The experiment investigated whether speech that was gated on and off (interrupted) affected the speech control of speakers who stutter. Eight children who stutter read a passage when they heard their voice normally and when the speech was gated. Fluency was enhanced (fewer errors were made and time to read a set passage was reduced) when speech was interrupted in this way. The results support the DRH. Copyright 2007 S. Karger AG, Basel.

Anticipatory Posturing of the Vocal Tract Reveals Dissociation of Speech Movement Plans from Linguistic Units

PubMed Central

Tilsen, Sam; Spincemaille, Pascal; Xu, Bo; Doerschuk, Peter; Luh, Wen-Ming; Feldman, Elana; Wang, Yi

2016-01-01

Models of speech production typically assume that control over the timing of speech movements is governed by the selection of higher-level linguistic units, such as segments or syllables. This study used real-time magnetic resonance imaging of the vocal tract to investigate the anticipatory movements speakers make prior to producing a vocal response. Two factors were varied: preparation (whether or not speakers had foreknowledge of the target response) and pre-response constraint (whether or not speakers were required to maintain a specific vocal tract posture prior to the response). In prepared responses, many speakers were observed to produce pre-response anticipatory movements with a variety of articulators, showing that that speech movements can be readily dissociated from higher-level linguistic units. Substantial variation was observed across speakers with regard to the articulators used for anticipatory posturing and the contexts in which anticipatory movements occurred. The findings of this study have important consequences for models of speech production and for our understanding of the normal range of variation in anticipatory speech behaviors. PMID:26760511

Anticipatory Posturing of the Vocal Tract Reveals Dissociation of Speech Movement Plans from Linguistic Units.

PubMed

Tilsen, Sam; Spincemaille, Pascal; Xu, Bo; Doerschuk, Peter; Luh, Wen-Ming; Feldman, Elana; Wang, Yi

2016-01-01

Models of speech production typically assume that control over the timing of speech movements is governed by the selection of higher-level linguistic units, such as segments or syllables. This study used real-time magnetic resonance imaging of the vocal tract to investigate the anticipatory movements speakers make prior to producing a vocal response. Two factors were varied: preparation (whether or not speakers had foreknowledge of the target response) and pre-response constraint (whether or not speakers were required to maintain a specific vocal tract posture prior to the response). In prepared responses, many speakers were observed to produce pre-response anticipatory movements with a variety of articulators, showing that that speech movements can be readily dissociated from higher-level linguistic units. Substantial variation was observed across speakers with regard to the articulators used for anticipatory posturing and the contexts in which anticipatory movements occurred. The findings of this study have important consequences for models of speech production and for our understanding of the normal range of variation in anticipatory speech behaviors.

Tolerance for audiovisual asynchrony is enhanced by the spectrotemporal fidelity of the speaker's mouth movements and speech.

PubMed

Shahin, Antoine J; Shen, Stanley; Kerlin, Jess R

2017-01-01

We examined the relationship between tolerance for audiovisual onset asynchrony (AVOA) and the spectrotemporal fidelity of the spoken words and the speaker's mouth movements. In two experiments that only varied in the temporal order of sensory modality, visual speech leading (exp1) or lagging (exp2) acoustic speech, participants watched intact and blurred videos of a speaker uttering trisyllabic words and nonwords that were noise vocoded with 4-, 8-, 16-, and 32-channels. They judged whether the speaker's mouth movements and the speech sounds were in-sync or out-of-sync . Individuals perceived synchrony (tolerated AVOA) on more trials when the acoustic speech was more speech-like (8 channels and higher vs. 4 channels), and when visual speech was intact than blurred (exp1 only). These findings suggest that enhanced spectrotemporal fidelity of the audiovisual (AV) signal prompts the brain to widen the window of integration promoting the fusion of temporally distant AV percepts.

The Role of Interaction in Native Speaker Comprehension of Nonnative Speaker Speech.

ERIC Educational Resources Information Center

Polio, Charlene; Gass, Susan M.

1998-01-01

Because interaction gives language learners an opportunity to modify their speech upon a signal of noncomprehension, it should also have a positive effect on native speakers' (NS) comprehension of nonnative speakers (NNS). This study shows that interaction does help NSs comprehend NNSs, contrasting the claims of an earlier study that found no…

Speech enhancement based on neural networks improves speech intelligibility in noise for cochlear implant users.

PubMed

Goehring, Tobias; Bolner, Federico; Monaghan, Jessica J M; van Dijk, Bas; Zarowski, Andrzej; Bleeck, Stefan

2017-02-01

Speech understanding in noisy environments is still one of the major challenges for cochlear implant (CI) users in everyday life. We evaluated a speech enhancement algorithm based on neural networks (NNSE) for improving speech intelligibility in noise for CI users. The algorithm decomposes the noisy speech signal into time-frequency units, extracts a set of auditory-inspired features and feeds them to the neural network to produce an estimation of which frequency channels contain more perceptually important information (higher signal-to-noise ratio, SNR). This estimate is used to attenuate noise-dominated and retain speech-dominated CI channels for electrical stimulation, as in traditional n-of-m CI coding strategies. The proposed algorithm was evaluated by measuring the speech-in-noise performance of 14 CI users using three types of background noise. Two NNSE algorithms were compared: a speaker-dependent algorithm, that was trained on the target speaker used for testing, and a speaker-independent algorithm, that was trained on different speakers. Significant improvements in the intelligibility of speech in stationary and fluctuating noises were found relative to the unprocessed condition for the speaker-dependent algorithm in all noise types and for the speaker-independent algorithm in 2 out of 3 noise types. The NNSE algorithms used noise-specific neural networks that generalized to novel segments of the same noise type and worked over a range of SNRs. The proposed algorithm has the potential to improve the intelligibility of speech in noise for CI users while meeting the requirements of low computational complexity and processing delay for application in CI devices. Copyright © 2016 The Authors. Published by Elsevier B.V. All rights reserved.

Perception of co-speech gestures in aphasic patients: a visual exploration study during the observation of dyadic conversations.

PubMed

Preisig, Basil C; Eggenberger, Noëmi; Zito, Giuseppe; Vanbellingen, Tim; Schumacher, Rahel; Hopfner, Simone; Nyffeler, Thomas; Gutbrod, Klemens; Annoni, Jean-Marie; Bohlhalter, Stephan; Müri, René M

2015-03-01

Co-speech gestures are part of nonverbal communication during conversations. They either support the verbal message or provide the interlocutor with additional information. Furthermore, they prompt as nonverbal cues the cooperative process of turn taking. In the present study, we investigated the influence of co-speech gestures on the perception of dyadic dialogue in aphasic patients. In particular, we analysed the impact of co-speech gestures on gaze direction (towards speaker or listener) and fixation of body parts. We hypothesized that aphasic patients, who are restricted in verbal comprehension, adapt their visual exploration strategies. Sixteen aphasic patients and 23 healthy control subjects participated in the study. Visual exploration behaviour was measured by means of a contact-free infrared eye-tracker while subjects were watching videos depicting spontaneous dialogues between two individuals. Cumulative fixation duration and mean fixation duration were calculated for the factors co-speech gesture (present and absent), gaze direction (to the speaker or to the listener), and region of interest (ROI), including hands, face, and body. Both aphasic patients and healthy controls mainly fixated the speaker's face. We found a significant co-speech gesture × ROI interaction, indicating that the presence of a co-speech gesture encouraged subjects to look at the speaker. Further, there was a significant gaze direction × ROI × group interaction revealing that aphasic patients showed reduced cumulative fixation duration on the speaker's face compared to healthy controls. Co-speech gestures guide the observer's attention towards the speaker, the source of semantic input. It is discussed whether an underlying semantic processing deficit or a deficit to integrate audio-visual information may cause aphasic patients to explore less the speaker's face. Copyright © 2014 Elsevier Ltd. All rights reserved.

Intelligibility for Binaural Speech with Discarded Low-SNR Speech Components.

PubMed

Schoenmaker, Esther; van de Par, Steven

2016-01-01

Speech intelligibility in multitalker settings improves when the target speaker is spatially separated from the interfering speakers. A factor that may contribute to this improvement is the improved detectability of target-speech components due to binaural interaction in analogy to the Binaural Masking Level Difference (BMLD). This would allow listeners to hear target speech components within specific time-frequency intervals that have a negative SNR, similar to the improvement in the detectability of a tone in noise when these contain disparate interaural difference cues. To investigate whether these negative-SNR target-speech components indeed contribute to speech intelligibility, a stimulus manipulation was performed where all target components were removed when local SNRs were smaller than a certain criterion value. It can be expected that for sufficiently high criterion values target speech components will be removed that do contribute to speech intelligibility. For spatially separated speakers, assuming that a BMLD-like detection advantage contributes to intelligibility, degradation in intelligibility is expected already at criterion values below 0 dB SNR. However, for collocated speakers it is expected that higher criterion values can be applied without impairing speech intelligibility. Results show that degradation of intelligibility for separated speakers is only seen for criterion values of 0 dB and above, indicating a negligible contribution of a BMLD-like detection advantage in multitalker settings. These results show that the spatial benefit is related to a spatial separation of speech components at positive local SNRs rather than to a BMLD-like detection improvement for speech components at negative local SNRs.

Effect of Fundamental Frequency on Judgments of Electrolaryngeal Speech

ERIC Educational Resources Information Center

Nagle, Kathy F.; Eadie, Tanya L.; Wright, Derek R.; Sumida, Yumi A.

2012-01-01

Purpose: To determine (a) the effect of fundamental frequency (f0) on speech intelligibility, acceptability, and perceived gender in electrolaryngeal (EL) speakers, and (b) the effect of known gender on speech acceptability in EL speakers. Method: A 2-part study was conducted. In Part 1, 34 healthy adults provided speech recordings using…

Speech Intelligibility and Personality Peer-Ratings of Young Adults with Cochlear Implants

ERIC Educational Resources Information Center

Freeman, Valerie

2018-01-01

Speech intelligibility, or how well a speaker's words are understood by others, affects listeners' judgments of the speaker's competence and personality. Deaf cochlear implant (CI) users vary widely in speech intelligibility, and their speech may have a noticeable "deaf" quality, both of which could evoke negative stereotypes or…

A Cross-Language Study of Acoustic Predictors of Speech Intelligibility in Individuals With Parkinson's Disease

PubMed Central

Choi, Yaelin

2017-01-01

Purpose The present study aimed to compare acoustic models of speech intelligibility in individuals with the same disease (Parkinson's disease [PD]) and presumably similar underlying neuropathologies but with different native languages (American English [AE] and Korean). Method A total of 48 speakers from the 4 speaker groups (AE speakers with PD, Korean speakers with PD, healthy English speakers, and healthy Korean speakers) were asked to read a paragraph in their native languages. Four acoustic variables were analyzed: acoustic vowel space, voice onset time contrast scores, normalized pairwise variability index, and articulation rate. Speech intelligibility scores were obtained from scaled estimates of sentences extracted from the paragraph. Results The findings indicated that the multiple regression models of speech intelligibility were different in Korean and AE, even with the same set of predictor variables and with speakers matched on speech intelligibility across languages. Analysis of the descriptive data for the acoustic variables showed the expected compression of the vowel space in speakers with PD in both languages, lower normalized pairwise variability index scores in Korean compared with AE, and no differences within or across language in articulation rate. Conclusions The results indicate that the basis of an intelligibility deficit in dysarthria is likely to depend on the native language of the speaker and listener. Additional research is required to explore other potential predictor variables, as well as additional language comparisons to pursue cross-linguistic considerations in classification and diagnosis of dysarthria types. PMID:28821018

Recognition and localization of speech by adult cochlear implant recipients wearing a digital hearing aid in the nonimplanted ear (bimodal hearing).

PubMed

Potts, Lisa G; Skinner, Margaret W; Litovsky, Ruth A; Strube, Michael J; Kuk, Francis

2009-06-01

The use of bilateral amplification is now common clinical practice for hearing aid users but not for cochlear implant recipients. In the past, most cochlear implant recipients were implanted in one ear and wore only a monaural cochlear implant processor. There has been recent interest in benefits arising from bilateral stimulation that may be present for cochlear implant recipients. One option for bilateral stimulation is the use of a cochlear implant in one ear and a hearing aid in the opposite nonimplanted ear (bimodal hearing). This study evaluated the effect of wearing a cochlear implant in one ear and a digital hearing aid in the opposite ear on speech recognition and localization. A repeated-measures correlational study was completed. Nineteen adult Cochlear Nucleus 24 implant recipients participated in the study. The participants were fit with a Widex Senso Vita 38 hearing aid to achieve maximum audibility and comfort within their dynamic range. Soundfield thresholds, loudness growth, speech recognition, localization, and subjective questionnaires were obtained six-eight weeks after the hearing aid fitting. Testing was completed in three conditions: hearing aid only, cochlear implant only, and cochlear implant and hearing aid (bimodal). All tests were repeated four weeks after the first test session. Repeated-measures analysis of variance was used to analyze the data. Significant effects were further examined using pairwise comparison of means or in the case of continuous moderators, regression analyses. The speech-recognition and localization tasks were unique, in that a speech stimulus presented from a variety of roaming azimuths (140 degree loudspeaker array) was used. Performance in the bimodal condition was significantly better for speech recognition and localization compared to the cochlear implant-only and hearing aid-only conditions. Performance was also different between these conditions when the location (i.e., side of the loudspeaker array that presented the word) was analyzed. In the bimodal condition, the speech-recognition and localization tasks were equal regardless of which side of the loudspeaker array presented the word, while performance was significantly poorer for the monaural conditions (hearing aid only and cochlear implant only) when the words were presented on the side with no stimulation. Binaural loudness summation of 1-3 dB was seen in soundfield thresholds and loudness growth in the bimodal condition. Measures of the audibility of sound with the hearing aid, including unaided thresholds, soundfield thresholds, and the Speech Intelligibility Index, were significant moderators of speech recognition and localization. Based on the questionnaire responses, participants showed a strong preference for bimodal stimulation. These findings suggest that a well-fit digital hearing aid worn in conjunction with a cochlear implant is beneficial to speech recognition and localization. The dynamic test procedures used in this study illustrate the importance of bilateral hearing for locating, identifying, and switching attention between multiple speakers. It is recommended that unilateral cochlear implant recipients, with measurable unaided hearing thresholds, be fit with a hearing aid.

And then I saw her race: Race-based expectations affect infants' word processing.

PubMed

Weatherhead, Drew; White, Katherine S

2018-08-01

How do our expectations about speakers shape speech perception? Adults' speech perception is influenced by social properties of the speaker (e.g., race). When in development do these influences begin? In the current study, 16-month-olds heard familiar words produced in their native accent (e.g., "dog") and in an unfamiliar accent involving a vowel shift (e.g., "dag"), in the context of an image of either a same-race speaker or an other-race speaker. Infants' interpretation of the words depended on the speaker's race. For the same-race speaker, infants only recognized words produced in the familiar accent; for the other-race speaker, infants recognized both versions of the words. Two additional experiments showed that infants only recognized an other-race speaker's atypical pronunciations when they differed systematically from the native accent. These results provide the first evidence that expectations driven by unspoken properties of speakers, such as race, influence infants' speech processing. Copyright © 2018 Elsevier B.V. All rights reserved.

Patterns of lung volume use during an extemporaneous speech task in persons with Parkinson disease.

PubMed

Bunton, Kate

2005-01-01

This study examined patterns of lung volume use in speakers with Parkinson disease (PD) during an extemporaneous speaking task. The performance of a control group was also examined. Behaviors described are based on acoustic, kinematic and linguistic measures. Group differences were found in breath group duration, lung volume initiation, and lung volume termination measures. Speakers in the control group alternated between a longer and shorter breath groups. With starting lung volumes being higher for the longer breath groups and lower for shorter breath groups. Speech production was terminated before reaching tidal end expiratory level. This pattern was also seen in 4 of 7 speakers with PD. The remaining 3 PD speakers initiated speech at low starting lung volumes and continued speaking below EEL. This subgroup of PD speakers ended breath groups at agrammatical boundaries, whereas control speakers ended at appropriate grammatical boundaries. As a result of participating in this exercise, the reader will (1) be able to describe the patterns of lung volume use in speakers with Parkinson disease and compare them with those employed by control speakers; and (2) obtain information about the influence of speaking task on speech breathing.

Neural Systems Involved When Attending to a Speaker

PubMed Central

Kamourieh, Salwa; Braga, Rodrigo M.; Leech, Robert; Newbould, Rexford D.; Malhotra, Paresh; Wise, Richard J. S.

2015-01-01

Remembering what a speaker said depends on attention. During conversational speech, the emphasis is on working memory, but listening to a lecture encourages episodic memory encoding. With simultaneous interference from background speech, the need for auditory vigilance increases. We recreated these context-dependent demands on auditory attention in 2 ways. The first was to require participants to attend to one speaker in either the absence or presence of a distracting background speaker. The second was to alter the task demand, requiring either an immediate or delayed recall of the content of the attended speech. Across 2 fMRI studies, common activated regions associated with segregating attended from unattended speech were the right anterior insula and adjacent frontal operculum (aI/FOp), the left planum temporale, and the precuneus. In contrast, activity in a ventral right frontoparietal system was dependent on both the task demand and the presence of a competing speaker. Additional multivariate analyses identified other domain-general frontoparietal systems, where activity increased during attentive listening but was modulated little by the need for speech stream segregation in the presence of 2 speakers. These results make predictions about impairments in attentive listening in different communicative contexts following focal or diffuse brain pathology. PMID:25596592

Language-Specific Developmental Differences in Speech Production: A Cross-Language Acoustic Study

ERIC Educational Resources Information Center

Li, Fangfang

2012-01-01

Speech productions of 40 English- and 40 Japanese-speaking children (aged 2-5) were examined and compared with the speech produced by 20 adult speakers (10 speakers per language). Participants were recorded while repeating words that began with "s" and "sh" sounds. Clear language-specific patterns in adults' speech were found,…

Auditory-Perceptual Assessment of Fluency in Typical and Neurologically Disordered Speech

ERIC Educational Resources Information Center

Penttilä, Nelly; Korpijaakko-Huuhka, Anna-Maija; Kent, Ray D.

2018-01-01

Purpose: The aim of this study is to investigate how speech fluency in typical and atypical speech is perceptually assessed by speech-language pathologists (SLPs). Our research questions were as follows: (a) How do SLPs rate fluency in speakers with and without neurological communication disorders? (b) Do they differentiate the speaker groups? and…

The Interrelationships between Ratings of Speech and Facial Acceptability in Persons with Cleft Palate.

ERIC Educational Resources Information Center

Sinko, Garnet R.; Hedrick, Dona L.

1982-01-01

Thirty untrained young adult observers rated the speech and facial acceptablity of 20 speakers with cleft palate. The observers were reliable in rating both speech and facial acceptability. Judgments of facial acceptability were generally more positive, suggesting that speech is generally judged more negatively in speakers with cleft palate.…

Auditory Long Latency Responses to Tonal and Speech Stimuli

ERIC Educational Resources Information Center

Swink, Shannon; Stuart, Andrew

2012-01-01

Purpose: The effects of type of stimuli (i.e., nonspeech vs. speech), speech (i.e., natural vs. synthetic), gender of speaker and listener, speaker (i.e., self vs. other), and frequency alteration in self-produced speech on the late auditory cortical evoked potential were examined. Method: Young adult men (n = 15) and women (n = 15), all with…

Intonation and dialog context as constraints for speech recognition.

PubMed

Taylor, P; King, S; Isard, S; Wright, H

1998-01-01

This paper describes a way of using intonation and dialog context to improve the performance of an automatic speech recognition (ASR) system. Our experiments were run on the DCIEM Maptask corpus, a corpus of spontaneous task-oriented dialog speech. This corpus has been tagged according to a dialog analysis scheme that assigns each utterance to one of 12 "move types," such as "acknowledge," "query-yes/no" or "instruct." Most ASR systems use a bigram language model to constrain the possible sequences of words that might be recognized. Here we use a separate bigram language model for each move type. We show that when the "correct" move-specific language model is used for each utterance in the test set, the word error rate of the recognizer drops. Of course when the recognizer is run on previously unseen data, it cannot know in advance what move type the speaker has just produced. To determine the move type we use an intonation model combined with a dialog model that puts constraints on possible sequences of move types, as well as the speech recognizer likelihoods for the different move-specific models. In the full recognition system, the combination of automatic move type recognition with the move specific language models reduces the overall word error rate by a small but significant amount when compared with a baseline system that does not take intonation or dialog acts into account. Interestingly, the word error improvement is restricted to "initiating" move types, where word recognition is important. In "response" move types, where the important information is conveyed by the move type itself--for example, positive versus negative response--there is no word error improvement, but recognition of the response types themselves is good. The paper discusses the intonation model, the language models, and the dialog model in detail and describes the architecture in which they are combined.

The Dynamic Range for Korean Standard Sentence Material: A Gender Comparison in a Male and a Female Speakers.

PubMed

Park, Kyeong-Yeon; Jin, In-Ki

2015-09-01

The purpose of this study was to identify differences between the dynamic ranges (DRs) of male and female speakers using Korean standard sentence material. Consideration was especially given to effects within the predefined segmentalized frequency-bands. We used Korean standard sentence lists for adults as stimuli. Each sentence was normalized to a root-mean-square of 65 dB sound pressure level. The sentences were then modified to ensure there were no pauses, and the modified sentences were passed through a filter bank in order to perform the frequency analysis. Finally, the DR was quantified using a histogram that showed the cumulative envelope distribution levels of the speech in each frequency band. In DRs that were averaged across all frequency bands, there were no significant differences between the male and the female speakers. However, when considering effects within the predefined frequency bands, there were significant differences in several frequency bands between the DRs of male speech and those of female speech. This study shows that the DR of speech for the male speaker differed from the female speaker in nine frequency bands among 21 frequency bands. These observed differences suggest that a standardized DR of male speech in the band-audibility function of the speech intelligibility index may differ from that of female speech derived in the same way. Further studies are required to derive standardized DRs for Korean speakers.

Deep bottleneck features for spoken language identification.

PubMed

Jiang, Bing; Song, Yan; Wei, Si; Liu, Jun-Hua; McLoughlin, Ian Vince; Dai, Li-Rong

2014-01-01

A key problem in spoken language identification (LID) is to design effective representations which are specific to language information. For example, in recent years, representations based on both phonotactic and acoustic features have proven their effectiveness for LID. Although advances in machine learning have led to significant improvements, LID performance is still lacking, especially for short duration speech utterances. With the hypothesis that language information is weak and represented only latently in speech, and is largely dependent on the statistical properties of the speech content, existing representations may be insufficient. Furthermore they may be susceptible to the variations caused by different speakers, specific content of the speech segments, and background noise. To address this, we propose using Deep Bottleneck Features (DBF) for spoken LID, motivated by the success of Deep Neural Networks (DNN) in speech recognition. We show that DBFs can form a low-dimensional compact representation of the original inputs with a powerful descriptive and discriminative capability. To evaluate the effectiveness of this, we design two acoustic models, termed DBF-TV and parallel DBF-TV (PDBF-TV), using a DBF based i-vector representation for each speech utterance. Results on NIST language recognition evaluation 2009 (LRE09) show significant improvements over state-of-the-art systems. By fusing the output of phonotactic and acoustic approaches, we achieve an EER of 1.08%, 1.89% and 7.01% for 30 s, 10 s and 3 s test utterances respectively. Furthermore, various DBF configurations have been extensively evaluated, and an optimal system proposed.

Articulatory settings of French-English bilingual speakers

NASA Astrophysics Data System (ADS)

Wilson, Ian

2005-04-01

The idea of a language-specific articulatory setting (AS), an underlying posture of the articulators during speech, has existed for centuries [Laver, Historiogr. Ling. 5 (1978)], but until recently it had eluded direct measurement. In an analysis of x-ray movies of French and English monolingual speakers, Gick et al. [Phonetica (in press)] link AS to inter-speech posture, allowing measurement of AS without interference from segmental targets during speech, and they give quantitative evidence showing AS to be language-specific. In the present study, ultrasound and Optotrak are used to investigate whether bilingual English-French speakers have two ASs, and whether this varies depending on the mode (monolingual or bilingual) these speakers are in. Specifically, for inter-speech posture of the lips, lip aperture and protrusion are measured using Optotrak. For inter-speech posture of the tongue, tongue root retraction, tongue body and tongue tip height are measured using optically-corrected ultrasound. Segmental context is balanced across the two languages ensuring that the sets of sounds before and after an inter-speech posture are consistent across languages. By testing bilingual speakers, vocal tract morphology across languages is controlled for. Results have implications for L2 acquisition, specifically the teaching and acquisition of pronunciation.

Robust audio-visual speech recognition under noisy audio-video conditions.

PubMed

Stewart, Darryl; Seymour, Rowan; Pass, Adrian; Ming, Ji

2014-02-01

This paper presents the maximum weighted stream posterior (MWSP) model as a robust and efficient stream integration method for audio-visual speech recognition in environments, where the audio or video streams may be subjected to unknown and time-varying corruption. A significant advantage of MWSP is that it does not require any specific measurements of the signal in either stream to calculate appropriate stream weights during recognition, and as such it is modality-independent. This also means that MWSP complements and can be used alongside many of the other approaches that have been proposed in the literature for this problem. For evaluation we used the large XM2VTS database for speaker-independent audio-visual speech recognition. The extensive tests include both clean and corrupted utterances with corruption added in either/both the video and audio streams using a variety of types (e.g., MPEG-4 video compression) and levels of noise. The experiments show that this approach gives excellent performance in comparison to another well-known dynamic stream weighting approach and also compared to any fixed-weighted integration approach in both clean conditions or when noise is added to either stream. Furthermore, our experiments show that the MWSP approach dynamically selects suitable integration weights on a frame-by-frame basis according to the level of noise in the streams and also according to the naturally fluctuating relative reliability of the modalities even in clean conditions. The MWSP approach is shown to maintain robust recognition performance in all tested conditions, while requiring no prior knowledge about the type or level of noise.

On how the brain decodes vocal cues about speaker confidence.

PubMed

Jiang, Xiaoming; Pell, Marc D

2015-05-01

In speech communication, listeners must accurately decode vocal cues that refer to the speaker's mental state, such as their confidence or 'feeling of knowing'. However, the time course and neural mechanisms associated with online inferences about speaker confidence are unclear. Here, we used event-related potentials (ERPs) to examine the temporal neural dynamics underlying a listener's ability to infer speaker confidence from vocal cues during speech processing. We recorded listeners' real-time brain responses while they evaluated statements wherein the speaker's tone of voice conveyed one of three levels of confidence (confident, close-to-confident, unconfident) or were spoken in a neutral manner. Neural responses time-locked to event onset show that the perceived level of speaker confidence could be differentiated at distinct time points during speech processing: unconfident expressions elicited a weaker P2 than all other expressions of confidence (or neutral-intending utterances), whereas close-to-confident expressions elicited a reduced negative response in the 330-500 msec and 550-740 msec time window. Neutral-intending expressions, which were also perceived as relatively confident, elicited a more delayed, larger sustained positivity than all other expressions in the 980-1270 msec window for this task. These findings provide the first piece of evidence of how quickly the brain responds to vocal cues signifying the extent of a speaker's confidence during online speech comprehension; first, a rough dissociation between unconfident and confident voices occurs as early as 200 msec after speech onset. At a later stage, further differentiation of the exact level of speaker confidence (i.e., close-to-confident, very confident) is evaluated via an inferential system to determine the speaker's meaning under current task settings. These findings extend three-stage models of how vocal emotion cues are processed in speech comprehension (e.g., Schirmer & Kotz, 2006) by revealing how a speaker's mental state (i.e., feeling of knowing) is simultaneously inferred from vocal expressions. Copyright © 2015 Elsevier Ltd. All rights reserved.

Impact of clear, loud, and slow speech on scaled intelligibility and speech severity in Parkinson's disease and multiple sclerosis.

PubMed

Tjaden, Kris; Sussman, Joan E; Wilding, Gregory E

2014-06-01

The perceptual consequences of rate reduction, increased vocal intensity, and clear speech were studied in speakers with multiple sclerosis (MS), Parkinson's disease (PD), and healthy controls. Seventy-eight speakers read sentences in habitual, clear, loud, and slow conditions. Sentences were equated for peak amplitude and mixed with multitalker babble for presentation to listeners. Using a computerized visual analog scale, listeners judged intelligibility or speech severity as operationally defined in Sussman and Tjaden (2012). Loud and clear but not slow conditions improved intelligibility relative to the habitual condition. With the exception of the loud condition for the PD group, speech severity did not improve above habitual and was reduced relative to habitual in some instances. Intelligibility and speech severity were strongly related, but relationships for disordered speakers were weaker in clear and slow conditions versus habitual. Both clear and loud speech show promise for improving intelligibility and maintaining or improving speech severity in multitalker babble for speakers with mild dysarthria secondary to MS or PD, at least as these perceptual constructs were defined and measured in this study. Although scaled intelligibility and speech severity overlap, the metrics further appear to have some separate value in documenting treatment-related speech changes.

Native Reactions to Non-Native Speech: A Review of Empirical Research.

ERIC Educational Resources Information Center

Eisenstein, Miriam

1983-01-01

Recent research on native speakers' reactions to nonnative speech that views listeners, speakers, and language from a variety of perspectives using both objective and subjective research paradigms is reviewed. Studies of error gravity, relative intelligibility of language samples, the role of accent, speakers' characteristics, and context in which…

Voice emotion recognition by cochlear-implanted children and their normally-hearing peers

PubMed Central

Chatterjee, Monita; Zion, Danielle; Deroche, Mickael L.; Burianek, Brooke; Limb, Charles; Goren, Alison; Kulkarni, Aditya M.; Christensen, Julie A.

2014-01-01

Despite their remarkable success in bringing spoken language to hearing impaired listeners, the signal transmitted through cochlear implants (CIs) remains impoverished in spectro-temporal fine structure. As a consequence, pitch-dominant information such as voice emotion, is diminished. For young children, the ability to correctly identify the mood/intent of the speaker (which may not always be visible in their facial expression) is an important aspect of social and linguistic development. Previous work in the field has shown that children with cochlear implants (cCI) have significant deficits in voice emotion recognition relative to their normally hearing peers (cNH). Here, we report on voice emotion recognition by a cohort of 36 school-aged cCI. Additionally, we provide for the first time, a comparison of their performance to that of cNH and NH adults (aNH) listening to CI simulations of the same stimuli. We also provide comparisons to the performance of adult listeners with CIs (aCI), most of whom learned language primarily through normal acoustic hearing. Results indicate that, despite strong variability, on average, cCI perform similarly to their adult counterparts; that both groups’ mean performance is similar to aNHs’ performance with 8-channel noise-vocoded speech; that cNH achieve excellent scores in voice emotion recognition with full-spectrum speech, but on average, show significantly poorer scores than aNH with 8-channel noise-vocoded speech. A strong developmental effect was observed in the cNH with noise-vocoded speech in this task. These results point to the considerable benefit obtained by cochlear-implanted children from their devices, but also underscore the need for further research and development in this important and neglected area. PMID:25448167

Second Language Learners and Speech Act Comprehension

ERIC Educational Resources Information Center

Holtgraves, Thomas

2007-01-01

Recognizing the specific speech act ( Searle, 1969) that a speaker performs with an utterance is a fundamental feature of pragmatic competence. Past research has demonstrated that native speakers of English automatically recognize speech acts when they comprehend utterances (Holtgraves & Ashley, 2001). The present research examined whether this…

Untrained listeners' ratings of speech disorders in a group with cleft palate: a comparison with speech and language pathologists' ratings.

PubMed

Brunnegård, Karin; Lohmander, Anette; van Doorn, Jan

2009-01-01

Hypernasal resonance, audible nasal air emission and/or nasal turbulence, and articulation errors are typical speech disorders associated with the speech of children with cleft lip and palate. Several studies indicate that hypernasal resonance tends to be perceived negatively by listeners. Most perceptual studies of speech disorders related to cleft palate are carried out with speech and language pathologists as listeners, whereas only a few studies have been conducted to explore how judgements by untrained listeners compare with expert assessments. These types of studies can be used to determine whether children for whom speech and language pathologists recommend intervention have a significant speech deviance that is also detected by untrained listeners. To compare ratings by untrained listeners with ratings by speech and language pathologists for cleft palate speech. An assessment form for untrained listeners was developed using statements and a five-point scale. The assessment form was tailored to facilitate comparison with expert judgements. Twenty-eight untrained listeners assessed the speech of 26 speakers with cleft palate and ten speakers without cleft in a comparison group. This assessment was compared with the joint assessment of two expert speech and language pathologists. Listener groups generally agreed on which speakers were nasal. The untrained listeners detected hyper- and hyponasality when it was present in speech and considered moderate to severe hypernasality to be serious enough to call for intervention. The expert listeners assessed audible nasal air emission and/or nasal turbulence to be present in twice as many speakers as the untrained listeners who were much less sensitive to audible nasal air emission and/or nasal turbulence. The results of untrained listeners' ratings in this study in the main confirm the ratings of speech and language pathologists and show that cleft palate speech disorders may have an impact in the everyday life of the speaker.

Revisiting speech rate and utterance length manipulations in stuttering speakers.

PubMed

Blomgren, Michael; Goberman, Alexander M

2008-01-01

The goal of this study was to evaluate stuttering frequency across a multidimensional (2x2) hierarchy of speech performance tasks. Specifically, this study examined the interaction between changes in length of utterance and levels of speech rate stability. Forty-four adult male speakers participated in the study (22 stuttering speakers and 22 non-stuttering speakers). Participants were audio and video recorded while producing a spontaneous speech task and four different experimental speaking tasks. The four experimental speaking tasks involved reading a list of 45 words and a list 45 phrases two times each. One reading of each list involved speaking at a steady habitual rate (habitual rate tasks) and another reading involved producing each list at a variable speaking rate (variable rate tasks). For the variable rate tasks, participants were directed to produce words or phrases at randomly ordered slow, habitual, and fast rates. The stuttering speakers exhibited significantly more stuttering on the variable rate tasks than on the habitual rate tasks. In addition, the stuttering speakers exhibited significantly more stuttering on the first word of the phrase length tasks compared to the single word tasks. Overall, the results indicated that varying levels of both utterance length and temporal complexity function to modulate stuttering frequency in adult stuttering speakers. Discussion focuses on issues of speech performance according to stuttering severity and possible clinical implications. The reader will learn about and be able to: (1) describe the mediating effects of length of utterance and speech rate on the frequency of stuttering in stuttering speakers; (2) understand the rationale behind multidimensional skill performance matrices; and (3) describe possible applications of motor skill performance matrices to stuttering therapy.

Speech production in experienced cochlear implant users undergoing short-term auditory deprivation

NASA Astrophysics Data System (ADS)

Greenman, Geoffrey; Tjaden, Kris; Kozak, Alexa T.

2005-09-01

This study examined the effect of short-term auditory deprivation on the speech production of five postlingually deafened women, all of whom were experienced cochlear implant users. Each cochlear implant user, as well as age and gender matched control speakers, produced CVC target words embedded in a reading passage. Speech samples for the deafened adults were collected on two separate occasions. First, the speakers were recorded after wearing their speech processor consistently for at least two to three hours prior to recording (implant ``ON''). The second recording occurred when the speakers had their speech processors turned off for approximately ten to twelve hours prior to recording (implant ``OFF''). Acoustic measures, including fundamental frequency (F0), the first (F1) and second (F2) formants of the vowels, vowel space area, vowel duration, spectral moments of the consonants, as well as utterance duration and sound pressure level (SPL) across the entire utterance were analyzed in both speaking conditions. For each implant speaker, acoustic measures will be compared across implant ``ON'' and implant ``OFF'' speaking conditions, and will also be compared to data obtained from normal hearing speakers.

Speech and pause characteristics associated with voluntary rate reduction in Parkinson's disease and Multiple Sclerosis.

PubMed

Tjaden, Kris; Wilding, Greg

2011-01-01

The primary purpose of this study was to investigate how speakers with Parkinson's disease (PD) and Multiple Sclerosis (MS) accomplish voluntary reductions in speech rate. A group of talkers with no history of neurological disease was included for comparison. This study was motivated by the idea that knowledge of how speakers with dysarthria voluntarily accomplish a reduced speech rate would contribute toward a descriptive model of speaking rate change in dysarthria. Such a model has the potential to assist in identifying rate control strategies to receive focus in clinical treatment programs and also would advance understanding of global speech timing in dysarthria. All speakers read a passage in Habitual and Slow conditions. Speech rate, articulation rate, pause duration, and pause frequency were measured. All speaker groups adjusted articulation time as well as pause time to reduce overall speech rate. Group differences in how voluntary rate reduction was accomplished were primarily one of quantity or degree. Overall, a slower-than-normal rate was associated with a reduced articulation rate, shorter speech runs that included fewer syllables, and longer more frequent pauses. Taken together, these results suggest that existing skills or strategies used by patients should be emphasized in dysarthria training programs focusing on rate reduction. Results further suggest that a model of voluntary speech rate reduction based on neurologically normal speech shows promise as being applicable for mild to moderate dysarthria. The reader will be able to: (1) describe the importance of studying voluntary adjustments in speech rate in dysarthria, (2) discuss how speakers with Parkinson's disease and Multiple Sclerosis adjust articulation time and pause time to slow speech rate. Copyright © 2011 Elsevier Inc. All rights reserved.

Developing Multi-Voice Speech Recognition Confidence Measures and Applying Them to AHLTA-Mobile

DTIC Science & Technology

2011-05-01

target application, then only the phoneme models used in that application’s command set need be adapted. For the purpose of the recorder app , I opted...and solve if. We also plan on creating a simplified civilian version of the recorder for iPhone and Android . Conclusion: First, speaker search...pushed forward to the field hospital before the injured soldier arrives. It is not onerous to play all of them. Trouble Shooting: You say “Blood

Predicting Intelligibility Gains in Dysarthria through Automated Speech Feature Analysis

ERIC Educational Resources Information Center

Fletcher, Annalise R.; Wisler, Alan A.; McAuliffe, Megan J.; Lansford, Kaitlin L.; Liss, Julie M.

2017-01-01

Purpose: Behavioral speech modifications have variable effects on the intelligibility of speakers with dysarthria. In the companion article, a significant relationship was found between measures of speakers' baseline speech and their intelligibility gains following cues to speak louder and reduce rate (Fletcher, McAuliffe, Lansford, Sinex, &…

Inducing Speech Errors in Dysarthria Using Tongue Twisters

ERIC Educational Resources Information Center

Kember, Heather; Connaghan, Kathryn; Patel, Rupal

2017-01-01

Although tongue twisters have been widely use to study speech production in healthy speakers, few studies have employed this methodology for individuals with speech impairment. The present study compared tongue twister errors produced by adults with dysarthria and age-matched healthy controls. Eight speakers (four female, four male; mean age =…

Perception of intelligibility and qualities of non-native accented speakers.

PubMed

Fuse, Akiko; Navichkova, Yuliya; Alloggio, Krysteena

To provide effective treatment to clients, speech-language pathologists must be understood, and be perceived to demonstrate the personal qualities necessary for therapeutic practice (e.g., resourcefulness and empathy). One factor that could interfere with the listener's perception of non-native speech is the speaker's accent. The current study explored the relationship between how accurately listeners could understand non-native speech and their perceptions of personal attributes of the speaker. Additionally, this study investigated how listeners' familiarity and experience with other languages may influence their perceptions of non-native accented speech. Through an online survey, native monolingual and bilingual English listeners rated four non-native accents (i.e., Spanish, Chinese, Russian, and Indian) on perceived intelligibility and perceived personal qualities (i.e., professionalism, intelligence, resourcefulness, empathy, and patience) necessary for speech-language pathologists. The results indicated significant relationships between the perception of intelligibility and the perception of personal qualities (i.e., professionalism, intelligence, and resourcefulness) attributed to non-native speakers. However, these findings were not supported for the Chinese accent. Bilingual listeners judged the non-native speech as more intelligible in comparison to monolingual listeners. No significant differences were found in the ratings between bilingual listeners who share the same language background as the speaker and other bilingual listeners. Based on the current findings, greater perception of intelligibility was the key to promoting a positive perception of personal qualities such as professionalism, intelligence, and resourcefulness, important for speech-language pathologists. The current study found evidence to support the claim that bilinguals have a greater ability in understanding non-native accented speech compared to monolingual listeners. The results, however, did not confirm an advantage for bilingual listeners sharing the same language backgrounds with the non-native speaker over other bilingual listeners. Copyright © 2017 Elsevier Inc. All rights reserved.

Prosodic Temporal Alignment of Co-Speech Gestures to Speech Facilitates Referent Resolution

ERIC Educational Resources Information Center

Jesse, Alexandra; Johnson, Elizabeth K.

2012-01-01

Using a referent detection paradigm, we examined whether listeners can determine the object speakers are referring to by using the temporal alignment between the motion speakers impose on objects and their labeling utterances. Stimuli were created by videotaping speakers labeling a novel creature. Without being explicitly instructed to do so,…

Second- and Foreign-Language Variation in Tense Backshifting in Indirect Reported Speech

ERIC Educational Resources Information Center

Charkova, Krassimira D.; Halliday, Laura J.

2011-01-01

This study examined how English learners in second-language (SL) and foreign-language (FL) contexts employ tense backshifting in indirect reported speech. Participants included 35 international students in the United States, 37 Bulgarian speakers of English, 38 Bosnian speakers of English, and 41 native English speakers. The instrument involved…

The role of voice input for human-machine communication.

PubMed Central

Cohen, P R; Oviatt, S L

1995-01-01

Optimism is growing that the near future will witness rapid growth in human-computer interaction using voice. System prototypes have recently been built that demonstrate speaker-independent real-time speech recognition, and understanding of naturally spoken utterances with vocabularies of 1000 to 2000 words, and larger. Already, computer manufacturers are building speech recognition subsystems into their new product lines. However, before this technology can be broadly useful, a substantial knowledge base is needed about human spoken language and performance during computer-based spoken interaction. This paper reviews application areas in which spoken interaction can play a significant role, assesses potential benefits of spoken interaction with machines, and compares voice with other modalities of human-computer interaction. It also discusses information that will be needed to build a firm empirical foundation for the design of future spoken and multimodal interfaces. Finally, it argues for a more systematic and scientific approach to investigating spoken input and performance with future language technology. PMID:7479803

The Atlanta Motor Speech Disorders Corpus: Motivation, Development, and Utility.

PubMed

Laures-Gore, Jacqueline; Russell, Scott; Patel, Rupal; Frankel, Michael

2016-01-01

This paper describes the design and collection of a comprehensive spoken language dataset from speakers with motor speech disorders in Atlanta, Ga., USA. This collaborative project aimed to gather a spoken database consisting of nonmainstream American English speakers residing in the Southeastern US in order to provide a more diverse perspective of motor speech disorders. Ninety-nine adults with an acquired neurogenic disorder resulting in a motor speech disorder were recruited. Stimuli include isolated vowels, single words, sentences with contrastive focus, sentences with emotional content and prosody, sentences with acoustic and perceptual sensitivity to motor speech disorders, as well as 'The Caterpillar' and 'The Grandfather' passages. Utility of this data in understanding the potential interplay of dialect and dysarthria was demonstrated with a subset of the speech samples existing in the database. The Atlanta Motor Speech Disorders Corpus will enrich our understanding of motor speech disorders through the examination of speech from a diverse group of speakers. © 2016 S. Karger AG, Basel.

Predicting fundamental frequency from mel-frequency cepstral coefficients to enable speech reconstruction.

PubMed

Shao, Xu; Milner, Ben

2005-08-01

This work proposes a method to reconstruct an acoustic speech signal solely from a stream of mel-frequency cepstral coefficients (MFCCs) as may be encountered in a distributed speech recognition (DSR) system. Previous methods for speech reconstruction have required, in addition to the MFCC vectors, fundamental frequency and voicing components. In this work the voicing classification and fundamental frequency are predicted from the MFCC vectors themselves using two maximum a posteriori (MAP) methods. The first method enables fundamental frequency prediction by modeling the joint density of MFCCs and fundamental frequency using a single Gaussian mixture model (GMM). The second scheme uses a set of hidden Markov models (HMMs) to link together a set of state-dependent GMMs, which enables a more localized modeling of the joint density of MFCCs and fundamental frequency. Experimental results on speaker-independent male and female speech show that accurate voicing classification and fundamental frequency prediction is attained when compared to hand-corrected reference fundamental frequency measurements. The use of the predicted fundamental frequency and voicing for speech reconstruction is shown to give very similar speech quality to that obtained using the reference fundamental frequency and voicing.

Analytic study of the Tadoma method: background and preliminary results.

PubMed

Norton, S J; Schultz, M C; Reed, C M; Braida, L D; Durlach, N I; Rabinowitz, W M; Chomsky, C

1977-09-01

Certain deaf-blind persons have been taught, through the Tadoma method of speechreading, to use vibrotactile cues from the face and neck to understand speech. This paper reports the results of preliminary tests of the speechreading ability of one adult Tadoma user. The tests were of four major types: (1) discrimination of speech stimuli; (2) recognition of words in isolation and in sentences; (3) interpretation of prosodic and syntactic features in sentences; and (4) comprehension of written (Braille) and oral speech. Words in highly contextual environments were much better perceived than were words in low-context environments. Many of the word errors involved phonemic substitutions which shared articulatory features with the target phonemes, with a higher error rate for vowels than consonants. Relative to performance on word-recognition tests, performance on some of the discrimination tests was worse than expected. Perception of sentences appeared to be mildly sensitive to rate of talking and to speaker differences. Results of the tests on perception of prosodic and syntactic features, while inconclusive, indicate that many of the features tested were not used in interpreting sentences. On an English comprehension test, a higher score was obtained for items administered in Braille than through oral presentation.

Emergence of neural encoding of auditory objects while listening to competing speakers

PubMed Central

Ding, Nai; Simon, Jonathan Z.

2012-01-01

A visual scene is perceived in terms of visual objects. Similar ideas have been proposed for the analogous case of auditory scene analysis, although their hypothesized neural underpinnings have not yet been established. Here, we address this question by recording from subjects selectively listening to one of two competing speakers, either of different or the same sex, using magnetoencephalography. Individual neural representations are seen for the speech of the two speakers, with each being selectively phase locked to the rhythm of the corresponding speech stream and from which can be exclusively reconstructed the temporal envelope of that speech stream. The neural representation of the attended speech dominates responses (with latency near 100 ms) in posterior auditory cortex. Furthermore, when the intensity of the attended and background speakers is separately varied over an 8-dB range, the neural representation of the attended speech adapts only to the intensity of that speaker but not to the intensity of the background speaker, suggesting an object-level intensity gain control. In summary, these results indicate that concurrent auditory objects, even if spectrotemporally overlapping and not resolvable at the auditory periphery, are neurally encoded individually in auditory cortex and emerge as fundamental representational units for top-down attentional modulation and bottom-up neural adaptation. PMID:22753470

Short-Term Exposure to One Dialect Affects Processing of Another

ERIC Educational Resources Information Center

Hay, Jen; Drager, Katie; Warren, Paul

2010-01-01

It is well established that speakers accommodate in speech production. Recent work has shown a similar effect in perception--speech perception is affected by a listener's beliefs about the speaker. In this paper, we explore the consequences of such perceptual accommodation for experiments in speech perception and lexical access. Our interest is…

The Production of Speech Acts by EFL Learners.

ERIC Educational Resources Information Center

Cohen, Andrew D.; Olshtain, Elite

A study is reported that describes ways in which nonnative speakers assess, plan, and execute speech acts in certain situations. The subjects, 15 advanced English foreign-language learners, were given 6 speech act situations (two apologies, two complaints, and two requests) in which they were to role play along with a native speaker. The…

An Acoustic Study of the Relationships among Neurologic Disease, Dysarthria Type, and Severity of Dysarthria

ERIC Educational Resources Information Center

Kim, Yunjung; Kent, Raymond D.; Weismer, Gary

2011-01-01

Purpose: This study examined acoustic predictors of speech intelligibility in speakers with several types of dysarthria secondary to different diseases and conducted classification analysis solely by acoustic measures according to 3 variables (disease, speech severity, and dysarthria type). Method: Speech recordings from 107 speakers with…

Intonation Contrast in Cantonese Speakers with Hypokinetic Dysarthria Associated with Parkinson's Disease

ERIC Educational Resources Information Center

Ma, Joan K.-Y.; Whitehill, Tara L.; So, Susanne Y.-S.

2010-01-01

Purpose: Speech produced by individuals with hypokinetic dysarthria associated with Parkinson's disease (PD) is characterized by a number of features including impaired speech prosody. The purpose of this study was to investigate intonation contrasts produced by this group of speakers. Method: Speech materials with a question-statement contrast…

Stuttered and Fluent Speakers' Heart Rate and Skin Conductance in Response to Fluent and Stuttered Speech

ERIC Educational Resources Information Center

Zhang, Jianliang; Kalinowski, Joseph; Saltuklaroglu, Tim; Hudock, Daniel

2010-01-01

Background: Previous studies have found simultaneous increases in skin conductance response and decreases in heart rate when normally fluent speakers watched and listened to stuttered speech compared with fluent speech, suggesting that stuttering induces arousal and emotional unpleasantness in listeners. However, physiological responses of persons…

Evaluation of speech errors in Putonghua speakers with cleft palate: a critical review of methodology issues.

PubMed

Jiang, Chenghui; Whitehill, Tara L

2014-04-01

Speech errors associated with cleft palate are well established for English and several other Indo-European languages. Few articles describing the speech of Putonghua (standard Mandarin Chinese) speakers with cleft palate have been published in English language journals. Although methodological guidelines have been published for the perceptual speech evaluation of individuals with cleft palate, there has been no critical review of methodological issues in studies of Putonghua speakers with cleft palate. A literature search was conducted to identify relevant studies published over the past 30 years in Chinese language journals. Only studies incorporating perceptual analysis of speech were included. Thirty-seven articles which met inclusion criteria were analyzed and coded on a number of methodological variables. Reliability was established by having all variables recoded for all studies. This critical review identified many methodological issues. These design flaws make it difficult to draw reliable conclusions about characteristic speech errors in this group of speakers. Specific recommendations are made to improve the reliability and validity of future studies, as well to facilitate cross-center comparisons.

Do individuals with fragile X syndrome show developmental stuttering or not? Comment on "Speech fluency in fragile X syndrome" by van Borsel, Dor and Rondal.

PubMed

Howell, Peter

2008-02-01

Van Borsel, Dor, and Rondal (2007) examined the speech of seven boys and two young male adults with fragile X syndrome and considered whether their speech was comparable to that reported in the developmental stuttering literature. They listed five criteria which led them to conclude that the speech patterns of speakers with fragile X syndrome differed from those observed in developmental stuttering. The differences noted were: 1) distribution of type of dysfluency; 2) the class of word on which dysfluency occurred; 3) whether word length affected dysfluency; 4) number of times words and phrases were repeated; and 5) whether there were influences of material type on fluency (spontaneous speech, repeated material etc.). They concluded that the speech of speakers with fragile X syndrome differed from developmental stuttering. The comparisons that van Borsel et al. (2007) made between participant groups were not for speakers of comparable ages. Comparisons with groups of corresponding ages support the opposite conclusion, namely the young speakers with fragile X syndrome show patterns similar to developmental stuttering.

Recognition and Localization of Speech by Adult Cochlear Implant Recipients Wearing a Digital Hearing Aid in the Nonimplanted Ear (Bimodal Hearing)

PubMed Central

Potts, Lisa G.; Skinner, Margaret W.; Litovsky, Ruth A.; Strube, Michael J; Kuk, Francis

2010-01-01

Background The use of bilateral amplification is now common clinical practice for hearing aid users but not for cochlear implant recipients. In the past, most cochlear implant recipients were implanted in one ear and wore only a monaural cochlear implant processor. There has been recent interest in benefits arising from bilateral stimulation that may be present for cochlear implant recipients. One option for bilateral stimulation is the use of a cochlear implant in one ear and a hearing aid in the opposite nonimplanted ear (bimodal hearing). Purpose This study evaluated the effect of wearing a cochlear implant in one ear and a digital hearing aid in the opposite ear on speech recognition and localization. Research Design A repeated-measures correlational study was completed. Study Sample Nineteen adult Cochlear Nucleus 24 implant recipients participated in the study. Intervention The participants were fit with a Widex Senso Vita 38 hearing aid to achieve maximum audibility and comfort within their dynamic range. Data Collection and Analysis Soundfield thresholds, loudness growth, speech recognition, localization, and subjective questionnaires were obtained six–eight weeks after the hearing aid fitting. Testing was completed in three conditions: hearing aid only, cochlear implant only, and cochlear implant and hearing aid (bimodal). All tests were repeated four weeks after the first test session. Repeated-measures analysis of variance was used to analyze the data. Significant effects were further examined using pairwise comparison of means or in the case of continuous moderators, regression analyses. The speech-recognition and localization tasks were unique, in that a speech stimulus presented from a variety of roaming azimuths (140 degree loudspeaker array) was used. Results Performance in the bimodal condition was significantly better for speech recognition and localization compared to the cochlear implant–only and hearing aid–only conditions. Performance was also different between these conditions when the location (i.e., side of the loudspeaker array that presented the word) was analyzed. In the bimodal condition, the speech-recognition and localization tasks were equal regardless of which side of the loudspeaker array presented the word, while performance was significantly poorer for the monaural conditions (hearing aid only and cochlear implant only) when the words were presented on the side with no stimulation. Binaural loudness summation of 1–3 dB was seen in soundfield thresholds and loudness growth in the bimodal condition. Measures of the audibility of sound with the hearing aid, including unaided thresholds, soundfield thresholds, and the Speech Intelligibility Index, were significant moderators of speech recognition and localization. Based on the questionnaire responses, participants showed a strong preference for bimodal stimulation. Conclusions These findings suggest that a well-fit digital hearing aid worn in conjunction with a cochlear implant is beneficial to speech recognition and localization. The dynamic test procedures used in this study illustrate the importance of bilateral hearing for locating, identifying, and switching attention between multiple speakers. It is recommended that unilateral cochlear implant recipients, with measurable unaided hearing thresholds, be fit with a hearing aid. PMID:19594084

Toddlers Use Speech Disfluencies to Predict Speakers' Referential Intentions

ERIC Educational Resources Information Center

Kidd, Celeste; White, Katherine S.; Aslin, Richard N.

2011-01-01

The ability to infer the referential intentions of speakers is a crucial part of learning a language. Previous research has uncovered various contextual and social cues that children may use to do this. Here we provide the first evidence that children also use speech disfluencies to infer speaker intention. Disfluencies (e.g. filled pauses "uh"…

A Cross-Language Study of Acoustic Predictors of Speech Intelligibility in Individuals with Parkinson's Disease

ERIC Educational Resources Information Center

Kim, Yunjung; Choi, Yaelin

2017-01-01

Purpose: The present study aimed to compare acoustic models of speech intelligibility in individuals with the same disease (Parkinson's disease [PD]) and presumably similar underlying neuropathologies but with different native languages (American English [AE] and Korean). Method: A total of 48 speakers from the 4 speaker groups (AE speakers with…

How Children and Adults Produce and Perceive Uncertainty in Audiovisual Speech

ERIC Educational Resources Information Center

Krahmer, Emiel; Swerts, Marc

2005-01-01

We describe two experiments on signaling and detecting uncertainty in audiovisual speech by adults and children. In the first study, utterances from adult speakers and child speakers (aged 7-8) were elicited and annotated with a set of six audiovisual features. It was found that when adult speakers were uncertain they were more likely to produce…

The Use of Artificial Neural Networks to Estimate Speech Intelligibility from Acoustic Variables: A Preliminary Analysis.

ERIC Educational Resources Information Center

Metz, Dale Evan; And Others

1992-01-01

A preliminary scheme for estimating the speech intelligibility of hearing-impaired speakers from acoustic parameters, using a computerized artificial neural network to process mathematically the acoustic input variables, is outlined. Tests with 60 hearing-impaired speakers found the scheme to be highly accurate in identifying speakers separated by…

Objective eye-gaze behaviour during face-to-face communication with proficient alaryngeal speakers: a preliminary study.

PubMed

Evitts, Paul; Gallop, Robert

2011-01-01

There is a large body of research demonstrating the impact of visual information on speaker intelligibility in both normal and disordered speaker populations. However, there is minimal information on which specific visual features listeners find salient during conversational discourse. To investigate listeners' eye-gaze behaviour during face-to-face conversation with normal, laryngeal and proficient alaryngeal speakers. Sixty participants individually participated in a 10-min conversation with one of four speakers (typical laryngeal, tracheoesophageal, oesophageal, electrolaryngeal; 15 participants randomly assigned to one mode of speech). All speakers were > 85% intelligible and were judged to be 'proficient' by two certified speech-language pathologists. Participants were fitted with a head-mounted eye-gaze tracking device (Mobile Eye, ASL) that calculated the region of interest and mean duration of eye-gaze. Self-reported gaze behaviour was also obtained following the conversation using a 10 cm visual analogue scale. While listening, participants viewed the lower facial region of the oesophageal speaker more than the normal or tracheoesophageal speaker. Results of non-hierarchical cluster analyses showed that while listening, the pattern of eye-gaze was predominantly directed at the lower face of the oesophageal and electrolaryngeal speaker and more evenly dispersed among the background, lower face, and eyes of the normal and tracheoesophageal speakers. Finally, results show a low correlation between self-reported eye-gaze behaviour and objective regions of interest data. Overall, results suggest similar eye-gaze behaviour when healthy controls converse with normal and tracheoesophageal speakers and that participants had significantly different eye-gaze patterns when conversing with an oesophageal speaker. Results are discussed in terms of existing eye-gaze data and its potential implications on auditory-visual speech perception. © 2011 Royal College of Speech & Language Therapists.

Effects of speaking task on intelligibility in Parkinson’s disease

PubMed Central

TJADEN, KRIS; WILDING, GREG

2017-01-01

Intelligibility tests for dysarthria typically provide an estimate of overall severity for speech materials elicited through imitation or read from a printed script. The extent to which these types of tasks and procedures reflect intelligibility for extemporaneous speech is not well understood. The purpose of this study was to compare intelligibility estimates obtained for a reading passage and an extemporaneous monologue produced by12 speakers with Parkinson’s disease (PD). The relationship between structural characteristics of utterances and scaled intelligibility was explored within speakers. Speakers were audio-recorded while reading a paragraph and producing a monologue. Speech samples were separated into individual utterances for presentation to 70 listeners who judged intelligibility using orthographic transcription and direct magnitude estimation (DME). Results suggest that scaled estimates of intelligibility for reading show potential for indexing intelligibility of an extemporaneous monologue. Within-speaker variation in scaled intelligibility also was related to the number of words per speech run for extemporaneous speech. PMID:20887216

Reviewing the connection between speech and obstructive sleep apnea.

PubMed

Espinoza-Cuadros, Fernando; Fernández-Pozo, Rubén; Toledano, Doroteo T; Alcázar-Ramírez, José D; López-Gonzalo, Eduardo; Hernández-Gómez, Luis A

2016-02-20

Sleep apnea (OSA) is a common sleep disorder characterized by recurring breathing pauses during sleep caused by a blockage of the upper airway (UA). The altered UA structure or function in OSA speakers has led to hypothesize the automatic analysis of speech for OSA assessment. In this paper we critically review several approaches using speech analysis and machine learning techniques for OSA detection, and discuss the limitations that can arise when using machine learning techniques for diagnostic applications. A large speech database including 426 male Spanish speakers suspected to suffer OSA and derived to a sleep disorders unit was used to study the clinical validity of several proposals using machine learning techniques to predict the apnea-hypopnea index (AHI) or classify individuals according to their OSA severity. AHI describes the severity of patients' condition. We first evaluate AHI prediction using state-of-the-art speaker recognition technologies: speech spectral information is modelled using supervectors or i-vectors techniques, and AHI is predicted through support vector regression (SVR). Using the same database we then critically review several OSA classification approaches previously proposed. The influence and possible interference of other clinical variables or characteristics available for our OSA population: age, height, weight, body mass index, and cervical perimeter, are also studied. The poor results obtained when estimating AHI using supervectors or i-vectors followed by SVR contrast with the positive results reported by previous research. This fact prompted us to a careful review of these approaches, also testing some reported results over our database. Several methodological limitations and deficiencies were detected that may have led to overoptimistic results. The methodological deficiencies observed after critically reviewing previous research can be relevant examples of potential pitfalls when using machine learning techniques for diagnostic applications. We have found two common limitations that can explain the likelihood of false discovery in previous research: (1) the use of prediction models derived from sources, such as speech, which are also correlated with other patient characteristics (age, height, sex,…) that act as confounding factors; and (2) overfitting of feature selection and validation methods when working with a high number of variables compared to the number of cases. We hope this study could not only be a useful example of relevant issues when using machine learning for medical diagnosis, but it will also help in guiding further research on the connection between speech and OSA.

Freedom of Speech and the Communication Discipline: Defending the Value of Low-Value Speech. Wicked Problems Forum: Freedom of Speech at Colleges and Universities

ERIC Educational Resources Information Center

Herbeck, Dale A.

2018-01-01

Heated battles over free speech have erupted on college campuses across the United States in recent months. Some of the most prominent incidents involve efforts by students to prevent public appearances by speakers espousing controversial viewpoints. Efforts to silence offensive speakers on college campuses are not new; in these endeavors, one can…

Frontal and temporal contributions to understanding the iconic co-speech gestures that accompany speech.

PubMed

Dick, Anthony Steven; Mok, Eva H; Raja Beharelle, Anjali; Goldin-Meadow, Susan; Small, Steven L

2014-03-01

In everyday conversation, listeners often rely on a speaker's gestures to clarify any ambiguities in the verbal message. Using fMRI during naturalistic story comprehension, we examined which brain regions in the listener are sensitive to speakers' iconic gestures. We focused on iconic gestures that contribute information not found in the speaker's talk, compared with those that convey information redundant with the speaker's talk. We found that three regions-left inferior frontal gyrus triangular (IFGTr) and opercular (IFGOp) portions, and left posterior middle temporal gyrus (MTGp)--responded more strongly when gestures added information to nonspecific language, compared with when they conveyed the same information in more specific language; in other words, when gesture disambiguated speech as opposed to reinforced it. An increased BOLD response was not found in these regions when the nonspecific language was produced without gesture, suggesting that IFGTr, IFGOp, and MTGp are involved in integrating semantic information across gesture and speech. In addition, we found that activity in the posterior superior temporal sulcus (STSp), previously thought to be involved in gesture-speech integration, was not sensitive to the gesture-speech relation. Together, these findings clarify the neurobiology of gesture-speech integration and contribute to an emerging picture of how listeners glean meaning from gestures that accompany speech. Copyright © 2012 Wiley Periodicals, Inc.

Automated speech recognition for time recording in out-of-hospital emergency medicine-an experimental approach.

PubMed

Gröschel, J; Philipp, F; Skonetzki, St; Genzwürker, H; Wetter, Th; Ellinger, K

2004-02-01

Precise documentation of medical treatment in emergency medical missions and for resuscitation is essential from a medical, legal and quality assurance point of view [Anästhesiologie und Intensivmedizin, 41 (2000) 737]. All conventional methods of time recording are either too inaccurate or elaborate for routine application. Automated speech recognition may offer a solution. A special erase programme for the documentation of all time events was developed. Standard speech recognition software (IBM ViaVoice 7.0) was adapted and installed on two different computer systems. One was a stationary PC (500MHz Pentium III, 128MB RAM, Soundblaster PCI 128 Soundcard, Win NT 4.0), the other was a mobile pen-PC that had already proven its value during emergency missions [Der Notarzt 16, p. 177] (Fujitsu Stylistic 2300, 230Mhz MMX Processor, 160MB RAM, embedded soundcard ESS 1879 chipset, Win98 2nd ed.). On both computers two different microphones were tested. One was a standard headset that came with the recognition software, the other was a small microphone (Lavalier-Kondensatormikrofon EM 116 from Vivanco), that could be attached to the operators collar. Seven women and 15 men spoke a text with 29 phrases to be recognised. Two emergency physicians tested the system in a simulated emergency setting using the collar microphone and the pen-PC with an analogue wireless connection. Overall recognition was best for the PC with a headset (89%) followed by the pen-PC with a headset (85%), the PC with a microphone (84%) and the pen-PC with a microphone (80%). Nevertheless, the difference was not statistically significant. Recognition became significantly worse (89.5% versus 82.3%, P<0.0001 ) when numbers had to be recognised. The gender of speaker and the number of words in a sentence had no influence. Average recognition in the simulated emergency setting was 75%. At no time did false recognition appear. Time recording with automated speech recognition seems to be possible in emergency medical missions. Although results show an average recognition of only 75%, it is possible that missing elements may be reconstructed more precisely. Future technology should integrate a secure wireless connection between microphone and mobile computer. The system could then prove its value for real out-of-hospital emergencies.

Speech perception benefits of FM and infrared devices to children with hearing aids in a typical classroom.

PubMed

Anderson, Karen L; Goldstein, Howard

2004-04-01

Children typically learn in classroom environments that have background noise and reverberation that interfere with accurate speech perception. Amplification technology can enhance the speech perception of students who are hard of hearing. This study used a single-subject alternating treatments design to compare the speech recognition abilities of children who are, hard of hearing when they were using hearing aids with each of three frequency modulated (FM) or infrared devices. Eight 9-12-year-olds with mild to severe hearing loss repeated Hearing in Noise Test (HINT) sentence lists under controlled conditions in a typical kindergarten classroom with a background noise level of +10 dB signal-to-noise (S/N) ratio and 1.1 s reverberation time. Participants listened to HINT lists using hearing aids alone and hearing aids in combination with three types of S/N-enhancing devices that are currently used in mainstream classrooms: (a) FM systems linked to personal hearing aids, (b) infrared sound field systems with speakers placed throughout the classroom, and (c) desktop personal sound field FM systems. The infrared ceiling sound field system did not provide benefit beyond that provided by hearing aids alone. Desktop and personal FM systems in combination with personal hearing aids provided substantial improvements in speech recognition. This information can assist in making S/N-enhancing device decisions for students using hearing aids. In a reverberant and noisy classroom setting, classroom sound field devices are not beneficial to speech perception for students with hearing aids, whereas either personal FM or desktop sound field systems provide listening benefits.

Relative Difficulty of Understanding Foreign Accents as a Marker of Proficiency

ERIC Educational Resources Information Center

Lev-Ari, Shiri; van Heugten, Marieke; Peperkamp, Sharon

2017-01-01

Foreign-accented speech is generally harder to understand than native-accented speech. This difficulty is reduced for non-native listeners who share their first language with the non-native speaker. It is currently unclear, however, how non-native listeners deal with foreign-accented speech produced by speakers of a different language. We show…

Little Houses and Casas Pequenas: Message Formulation and Syntactic Form in Unscripted Speech with Speakers of English and Spanish

ERIC Educational Resources Information Center

Brown-Schmidt, Sarah; Konopka, Agnieszka E.

2008-01-01

During unscripted speech, speakers coordinate the formulation of pre-linguistic messages with the linguistic processes that implement those messages into speech. We examine the process of constructing a contextually appropriate message and interfacing that message with utterance planning in English ("the small butterfly") and Spanish ("la mariposa…

Machine learning based sample extraction for automatic speech recognition using dialectal Assamese speech.

PubMed

Agarwalla, Swapna; Sarma, Kandarpa Kumar

2016-06-01

Automatic Speaker Recognition (ASR) and related issues are continuously evolving as inseparable elements of Human Computer Interaction (HCI). With assimilation of emerging concepts like big data and Internet of Things (IoT) as extended elements of HCI, ASR techniques are found to be passing through a paradigm shift. Oflate, learning based techniques have started to receive greater attention from research communities related to ASR owing to the fact that former possess natural ability to mimic biological behavior and that way aids ASR modeling and processing. The current learning based ASR techniques are found to be evolving further with incorporation of big data, IoT like concepts. Here, in this paper, we report certain approaches based on machine learning (ML) used for extraction of relevant samples from big data space and apply them for ASR using certain soft computing techniques for Assamese speech with dialectal variations. A class of ML techniques comprising of the basic Artificial Neural Network (ANN) in feedforward (FF) and Deep Neural Network (DNN) forms using raw speech, extracted features and frequency domain forms are considered. The Multi Layer Perceptron (MLP) is configured with inputs in several forms to learn class information obtained using clustering and manual labeling. DNNs are also used to extract specific sentence types. Initially, from a large storage, relevant samples are selected and assimilated. Next, a few conventional methods are used for feature extraction of a few selected types. The features comprise of both spectral and prosodic types. These are applied to Recurrent Neural Network (RNN) and Fully Focused Time Delay Neural Network (FFTDNN) structures to evaluate their performance in recognizing mood, dialect, speaker and gender variations in dialectal Assamese speech. The system is tested under several background noise conditions by considering the recognition rates (obtained using confusion matrices and manually) and computation time. It is found that the proposed ML based sentence extraction techniques and the composite feature set used with RNN as classifier outperform all other approaches. By using ANN in FF form as feature extractor, the performance of the system is evaluated and a comparison is made. Experimental results show that the application of big data samples has enhanced the learning of the ASR system. Further, the ANN based sample and feature extraction techniques are found to be efficient enough to enable application of ML techniques in big data aspects as part of ASR systems. Copyright © 2015 Elsevier Ltd. All rights reserved.

When Alphabets Collide: Alphabetic First-Language Speakers' Approach to Speech Production in an Alphabetic Second Language

ERIC Educational Resources Information Center

Vokic, Gabriela

2011-01-01

This study analysed the extent to which literate native speakers of a language with a phonemic alphabetic orthography rely on their first language (L1) orthography during second language (L2) speech production of a language that has a morphophonemic alphabetic orthography. The production of the English flapping rule by 15 adult native speakers of…

Bridging Gaps in Common Ground: Speakers Design Their Gestures for Their Listeners

ERIC Educational Resources Information Center

Hilliard, Caitlin; Cook, Susan Wagner

2016-01-01

Communication is shaped both by what we are trying to say and by whom we are saying it to. We examined whether and how shared information influences the gestures speakers produce along with their speech. Unlike prior work examining effects of common ground on speech and gesture, we examined a situation in which some speakers have the same amount…

I "hear" what you're "saying": Auditory perceptual simulation, reading speed, and reading comprehension.

PubMed

Zhou, Peiyun; Christianson, Kiel

2016-01-01

Auditory perceptual simulation (APS) during silent reading refers to situations in which the reader actively simulates the voice of a character or other person depicted in a text. In three eye-tracking experiments, APS effects were investigated as people read utterances attributed to a native English speaker, a non-native English speaker, or no speaker at all. APS effects were measured via online eye movements and offline comprehension probes. Results demonstrated that inducing APS during silent reading resulted in observable differences in reading speed when readers simulated the speech of faster compared to slower speakers and compared to silent reading without APS. Social attitude survey results indicated that readers' attitudes towards the native and non-native speech did not consistently influence APS-related effects. APS of both native speech and non-native speech increased reading speed, facilitated deeper, less good-enough sentence processing, and improved comprehension compared to normal silent reading.

Advances in real-time magnetic resonance imaging of the vocal tract for speech science and technology research.

PubMed

Toutios, Asterios; Narayanan, Shrikanth S

2016-01-01

Real-time magnetic resonance imaging (rtMRI) of the moving vocal tract during running speech production is an important emerging tool for speech production research providing dynamic information of a speaker's upper airway from the entire mid-sagittal plane or any other scan plane of interest. There have been several advances in the development of speech rtMRI and corresponding analysis tools, and their application to domains such as phonetics and phonological theory, articulatory modeling, and speaker characterization. An important recent development has been the open release of a database that includes speech rtMRI data from five male and five female speakers of American English each producing 460 phonetically balanced sentences. The purpose of the present paper is to give an overview and outlook of the advances in rtMRI as a tool for speech research and technology development.

A characterization of verb use in Turkish agrammatic narrative speech.

PubMed

Arslan, Seçkin; Bamyacı, Elif; Bastiaanse, Roelien

2016-01-01

This study investigates the characteristics of narrative-speech production and the use of verbs in Turkish agrammatic speakers (n = 10) compared to non-brain-damaged controls (n = 10). To elicit narrative-speech samples, personal interviews and storytelling tasks were conducted. Turkish has a large and regular verb inflection paradigm where verbs are inflected for evidentiality (i.e. direct versus indirect evidence available to the speaker). Particularly, we explored the general characteristics of the speech samples (e.g. utterance length) and the uses of lexical, finite and non-finite verbs and direct and indirect evidentials. The results show that speech rate is slow, verbs per utterance are lower than normal and the verb diversity is reduced in the agrammatic speakers. Verb inflection is relatively intact; however, a trade-off pattern between inflection for direct evidentials and verb diversity is found. The implications of the data are discussed in connection with narrative-speech production studies on other languages.

Advances in real-time magnetic resonance imaging of the vocal tract for speech science and technology research

PubMed Central

TOUTIOS, ASTERIOS; NARAYANAN, SHRIKANTH S.

2016-01-01

Real-time magnetic resonance imaging (rtMRI) of the moving vocal tract during running speech production is an important emerging tool for speech production research providing dynamic information of a speaker's upper airway from the entire mid-sagittal plane or any other scan plane of interest. There have been several advances in the development of speech rtMRI and corresponding analysis tools, and their application to domains such as phonetics and phonological theory, articulatory modeling, and speaker characterization. An important recent development has been the open release of a database that includes speech rtMRI data from five male and five female speakers of American English each producing 460 phonetically balanced sentences. The purpose of the present paper is to give an overview and outlook of the advances in rtMRI as a tool for speech research and technology development. PMID:27833745

Processing changes when listening to foreign-accented speech

PubMed Central

Romero-Rivas, Carlos; Martin, Clara D.; Costa, Albert

2015-01-01

This study investigates the mechanisms responsible for fast changes in processing foreign-accented speech. Event Related brain Potentials (ERPs) were obtained while native speakers of Spanish listened to native and foreign-accented speakers of Spanish. We observed a less positive P200 component for foreign-accented speech relative to native speech comprehension. This suggests that the extraction of spectral information and other important acoustic features was hampered during foreign-accented speech comprehension. However, the amplitude of the N400 component for foreign-accented speech comprehension decreased across the experiment, suggesting the use of a higher level, lexical mechanism. Furthermore, during native speech comprehension, semantic violations in the critical words elicited an N400 effect followed by a late positivity. During foreign-accented speech comprehension, semantic violations only elicited an N400 effect. Overall, our results suggest that, despite a lack of improvement in phonetic discrimination, native listeners experience changes at lexical-semantic levels of processing after brief exposure to foreign-accented speech. Moreover, these results suggest that lexical access, semantic integration and linguistic re-analysis processes are permeable to external factors, such as the accent of the speaker. PMID:25859209

Differential modulation of auditory responses to attended and unattended speech in different listening conditions

PubMed Central

Kong, Ying-Yee; Mullangi, Ala; Ding, Nai

2014-01-01

This study investigates how top-down attention modulates neural tracking of the speech envelope in different listening conditions. In the quiet conditions, a single speech stream was presented and the subjects paid attention to the speech stream (active listening) or watched a silent movie instead (passive listening). In the competing speaker (CS) conditions, two speakers of opposite genders were presented diotically. Ongoing electroencephalographic (EEG) responses were measured in each condition and cross-correlated with the speech envelope of each speaker at different time lags. In quiet, active and passive listening resulted in similar neural responses to the speech envelope. In the CS conditions, however, the shape of the cross-correlation function was remarkably different between the attended and unattended speech. The cross-correlation with the attended speech showed stronger N1 and P2 responses but a weaker P1 response compared with the cross-correlation with the unattended speech. Furthermore, the N1 response to the attended speech in the CS condition was enhanced and delayed compared with the active listening condition in quiet, while the P2 response to the unattended speaker in the CS condition was attenuated compared with the passive listening in quiet. Taken together, these results demonstrate that top-down attention differentially modulates envelope-tracking neural activity at different time lags and suggest that top-down attention can both enhance the neural responses to the attended sound stream and suppress the responses to the unattended sound stream. PMID:25124153

Speed-difficulty trade-off in speech: Chinese versus English

PubMed Central

Sun, Yao; Latash, Elizaveta M.; Mikaelian, Irina L.

2011-01-01

This study continues the investigation of the previously described speed-difficulty trade-off in picture description tasks. In particular, we tested a hypothesis that the Mandarin Chinese and American English are similar in showing logarithmic dependences between speech time and index of difficulty (ID), while they differ significantly in the amount of time needed to describe simple pictures, this difference increases for more complex pictures, and it is associated with a proportional difference in the number of syllables used. Subjects (eight Chinese speakers and eight English speakers) were tested in pairs. One subject (the Speaker) described simple pictures, while the other subject (the Performer) tried to reproduce the pictures based on the verbal description as quickly as possible with a set of objects. The Chinese speakers initiated speech production significantly faster than the English speakers. Speech time scaled linearly with ln(ID) in all subjects, but the regression coefficient was significantly higher in the English speakers as compared with the Chinese speakers. The number of errors was somewhat lower in the Chinese participants (not significantly). The Chinese pairs also showed a shorter delay between the initiation of speech and initiation of action by the Performer, shorter movement time by the Performer, and shorter overall performance time. The number of syllables scaled with ID, and the Chinese speakers used significantly smaller numbers of syllables. Speech rate was comparable between the two groups, about 3 syllables/s; it dropped for more complex pictures (higher ID). When asked to reproduce the same pictures without speaking, movement time scaled linearly with ln(ID); the Chinese performers were slower than the English performers. We conclude that natural languages show a speed-difficulty trade-off similar to Fitts’ law; the trade-offs in movement and speech production are likely to originate at a cognitive level. The time advantage of the Chinese participants originates not from similarity of the simple pictures and Chinese written characters and not from more sloppy performance. It is linked to using fewer syllables to transmit the same information. We suggest that natural languages may differ by informational density defined as the amount of information transmitted by a given number of syllables. PMID:21479658

Some articulatory details of emotional speech

NASA Astrophysics Data System (ADS)

Lee, Sungbok; Yildirim, Serdar; Bulut, Murtaza; Kazemzadeh, Abe; Narayanan, Shrikanth

2005-09-01

Differences in speech articulation among four emotion types, neutral, anger, sadness, and happiness are investigated by analyzing tongue tip, jaw, and lip movement data collected from one male and one female speaker of American English. The data were collected using an electromagnetic articulography (EMA) system while subjects produce simulated emotional speech. Pitch, root-mean-square (rms) energy and the first three formants were estimated for vowel segments. For both speakers, angry speech exhibited the largest rms energy and largest articulatory activity in terms of displacement range and movement speed. Happy speech is characterized by largest pitch variability. It has higher rms energy than neutral speech but articulatory activity is rather comparable to, or less than, neutral speech. That is, happy speech is more prominent in voicing activity than in articulation. Sad speech exhibits longest sentence duration and lower rms energy. However, its articulatory activity is no less than neutral speech. Interestingly, for the male speaker, articulation for vowels in sad speech is consistently more peripheral (i.e., more forwarded displacements) when compared to other emotions. However, this does not hold for female subject. These and other results will be discussed in detail with associated acoustics and perceived emotional qualities. [Work supported by NIH.

Speaker-sensitive emotion recognition via ranking: Studies on acted and spontaneous speech☆

PubMed Central

Cao, Houwei; Verma, Ragini; Nenkova, Ani

2014-01-01

We introduce a ranking approach for emotion recognition which naturally incorporates information about the general expressivity of speakers. We demonstrate that our approach leads to substantial gains in accuracy compared to conventional approaches. We train ranking SVMs for individual emotions, treating the data from each speaker as a separate query, and combine the predictions from all rankers to perform multi-class prediction. The ranking method provides two natural benefits. It captures speaker specific information even in speaker-independent training/testing conditions. It also incorporates the intuition that each utterance can express a mix of possible emotion and that considering the degree to which each emotion is expressed can be productively exploited to identify the dominant emotion. We compare the performance of the rankers and their combination to standard SVM classification approaches on two publicly available datasets of acted emotional speech, Berlin and LDC, as well as on spontaneous emotional data from the FAU Aibo dataset. On acted data, ranking approaches exhibit significantly better performance compared to SVM classification both in distinguishing a specific emotion from all others and in multi-class prediction. On the spontaneous data, which contains mostly neutral utterances with a relatively small portion of less intense emotional utterances, ranking-based classifiers again achieve much higher precision in identifying emotional utterances than conventional SVM classifiers. In addition, we discuss the complementarity of conventional SVM and ranking-based classifiers. On all three datasets we find dramatically higher accuracy for the test items on whose prediction the two methods agree compared to the accuracy of individual methods. Furthermore on the spontaneous data the ranking and standard classification are complementary and we obtain marked improvement when we combine the two classifiers by late-stage fusion. PMID:25422534

Speaker-sensitive emotion recognition via ranking: Studies on acted and spontaneous speech☆

PubMed

Cao, Houwei; Verma, Ragini; Nenkova, Ani

2015-01-01

We introduce a ranking approach for emotion recognition which naturally incorporates information about the general expressivity of speakers. We demonstrate that our approach leads to substantial gains in accuracy compared to conventional approaches. We train ranking SVMs for individual emotions, treating the data from each speaker as a separate query, and combine the predictions from all rankers to perform multi-class prediction. The ranking method provides two natural benefits. It captures speaker specific information even in speaker-independent training/testing conditions. It also incorporates the intuition that each utterance can express a mix of possible emotion and that considering the degree to which each emotion is expressed can be productively exploited to identify the dominant emotion. We compare the performance of the rankers and their combination to standard SVM classification approaches on two publicly available datasets of acted emotional speech, Berlin and LDC, as well as on spontaneous emotional data from the FAU Aibo dataset. On acted data, ranking approaches exhibit significantly better performance compared to SVM classification both in distinguishing a specific emotion from all others and in multi-class prediction. On the spontaneous data, which contains mostly neutral utterances with a relatively small portion of less intense emotional utterances, ranking-based classifiers again achieve much higher precision in identifying emotional utterances than conventional SVM classifiers. In addition, we discuss the complementarity of conventional SVM and ranking-based classifiers. On all three datasets we find dramatically higher accuracy for the test items on whose prediction the two methods agree compared to the accuracy of individual methods. Furthermore on the spontaneous data the ranking and standard classification are complementary and we obtain marked improvement when we combine the two classifiers by late-stage fusion.

Voice-processing technologies--their application in telecommunications.

PubMed Central

Wilpon, J G

1995-01-01

As the telecommunications industry evolves over the next decade to provide the products and services that people will desire, several key technologies will become commonplace. Two of these, automatic speech recognition and text-to-speech synthesis, will provide users with more freedom on when, where, and how they access information. While these technologies are currently in their infancy, their capabilities are rapidly increasing and their deployment in today's telephone network is expanding. The economic impact of just one application, the automation of operator services, is well over $100 million per year. Yet there still are many technical challenges that must be resolved before these technologies can be deployed ubiquitously in products and services throughout the worldwide telephone network. These challenges include: (i) High level of accuracy. The technology must be perceived by the user as highly accurate, robust, and reliable. (ii) Easy to use. Speech is only one of several possible input/output modalities for conveying information between a human and a machine, much like a computer terminal or Touch-Tone pad on a telephone. It is not the final product. Therefore, speech technologies must be hidden from the user. That is, the burden of using the technology must be on the technology itself. (iii) Quick prototyping and development of new products and services. The technology must support the creation of new products and services based on speech in an efficient and timely fashion. In this paper I present a vision of the voice-processing industry with a focus on the areas with the broadest base of user penetration: speech recognition, text-to-speech synthesis, natural language processing, and speaker recognition technologies. The current and future applications of these technologies in the telecommunications industry will be examined in terms of their strengths, limitations, and the degree to which user needs have been or have yet to be met. Although noteworthy gains have been made in areas with potentially small user bases and in the more mature speech-coding technologies, these subjects are outside the scope of this paper. Images Fig. 1 PMID:7479815

A Nonword Repetition Task for Speakers with Misarticulations: The Syllable Repetition Task (SRT)

PubMed Central

Shriberg, Lawrence D.; Lohmeier, Heather L.; Campbell, Thomas F.; Dollaghan, Christine A.; Green, Jordan R.; Moore, Christopher A.

2010-01-01

Purpose Conceptual and methodological confounds occur when non(sense) repetition tasks are administered to speakers who do not have the target speech sounds in their phonetic inventories or who habitually misarticulate targeted speech sounds. We describe a nonword repetition task, the Syllable Repetiton Task (SRT) that eliminates this confound and report findings from three validity studies. Method Ninety-five preschool children with Speech Delay and 63 with Typical Speech, completed an assessment battery that included the Nonword Repetition Task (NRT: Dollaghan & Campbell, 1998) and the SRT. SRT stimuli include only four of the earliest occurring consonants and one early occurring vowel. Results Study 1 findings indicated that the SRT eliminated the speech confound in nonword testing with speakers who misarticulate. Study 2 findings indicated that the accuracy of the SRT to identify expressive language impairment was comparable to findings for the NRT. Study 3 findings illustrated the SRT’s potential to interrogate speech processing constraints underlying poor nonword repetition accuracy. Results supported both memorial and auditory-perceptual encoding constraints underlying nonword repetition errors in children with speech-language impairment. Conclusion The SRT appears to be a psychometrically stable and substantively informative nonword repetition task for emerging genetic and other research with speakers who misarticulate. PMID:19635944

Pragmatic Difficulties in the Production of the Speech Act of Apology by Iraqi EFL Learners

ERIC Educational Resources Information Center

Al-Ghazalli, Mehdi Falih; Al-Shammary, Mohanad A. Amert

2014-01-01

The purpose of this paper is to investigate the pragmatic difficulties encountered by Iraqi EFL university students in producing the speech act of apology. Although the act of apology is easy to recognize or use by native speakers of English, non-native speakers generally encounter difficulties in discriminating one speech act from another. The…

Pausing Preceding and Following "Que" in the Production of Native Speakers of French

ERIC Educational Resources Information Center

Genc, Bilal; Mavasoglu, Mustafa; Bada, Erdogan

2011-01-01

Pausing strategies in read and spontaneous speech have been of significant interest for researchers since in literature it was observed that read speech and spontaneous speech pausing patterns do display some considerable differences. This, at least, is the case in the English language as it was produced by native speakers. As to what may be the…

Impact of Clear, Loud, and Slow Speech on Scaled Intelligibility and Speech Severity in Parkinson's Disease and Multiple Sclerosis

ERIC Educational Resources Information Center

Tjaden, Kris; Sussman, Joan E.; Wilding, Gregory E.

2014-01-01

Purpose: The perceptual consequences of rate reduction, increased vocal intensity, and clear speech were studied in speakers with multiple sclerosis (MS), Parkinson's disease (PD), and healthy controls. Method: Seventy-eight speakers read sentences in habitual, clear, loud, and slow conditions. Sentences were equated for peak amplitude and…

Do Native Speakers of North American and Singapore English Differentially Perceive Comprehensibility in Second Language Speech?

ERIC Educational Resources Information Center

Saito, Kazuya; Shintani, Natsuko

2016-01-01

The current study examined the extent to which native speakers of North American and Singapore English differentially perceive the comprehensibility (ease of understanding) of second language (L2) speech. Spontaneous speech samples elicited from 50 Japanese learners of English with various proficiency levels were first rated by 10 Canadian and 10…

Developing a corpus of spoken language variability

NASA Astrophysics Data System (ADS)

Carmichael, Lesley; Wright, Richard; Wassink, Alicia Beckford

2003-10-01

We are developing a novel, searchable corpus as a research tool for investigating phonetic and phonological phenomena across various speech styles. Five speech styles have been well studied independently in previous work: reduced (casual), careful (hyperarticulated), citation (reading), Lombard effect (speech in noise), and ``motherese'' (child-directed speech). Few studies to date have collected a wide range of styles from a single set of speakers, and fewer yet have provided publicly available corpora. The pilot corpus includes recordings of (1) a set of speakers participating in a variety of tasks designed to elicit the five speech styles, and (2) casual peer conversations and wordlists to illustrate regional vowels. The data include high-quality recordings and time-aligned transcriptions linked to text files that can be queried. Initial measures drawn from the database provide comparison across speech styles along the following acoustic dimensions: MLU (changes in unit duration); relative intra-speaker intensity changes (mean and dynamic range); and intra-speaker pitch values (minimum, maximum, mean, range). The corpus design will allow for a variety of analyses requiring control of demographic and style factors, including hyperarticulation variety, disfluencies, intonation, discourse analysis, and detailed spectral measures.

Physiological Indices of Bilingualism: Oral-Motor Coordination and Speech Rate in Bengali-English Speakers

ERIC Educational Resources Information Center

Chakraborty, Rahul; Goffman, Lisa; Smith, Anne

2008-01-01

Purpose: To examine how age of immersion and proficiency in a 2nd language influence speech movement variability and speaking rate in both a 1st language and a 2nd language. Method: A group of 21 Bengali-English bilingual speakers participated. Lip and jaw movements were recorded. For all 21 speakers, lip movement variability was assessed based on…

An Analysis of Speech Disfluencies of Turkish Speakers Based on Age Variable

ERIC Educational Resources Information Center

Altiparmak, Ayse; Kuruoglu, Gülmira

2018-01-01

The focus of this research is to verify the influence of the age variable on fluent Turkish native speakers' production of the various types of speech disfluencies. To accomplish this, four groups of native speakers of Turkish between ages 4-8, 18-23, 33-50 years respectively and those over 50-years-old were constructed. A total of 84 participants…

A self-teaching image processing and voice-recognition-based, intelligent and interactive system to educate visually impaired children

NASA Astrophysics Data System (ADS)

Iqbal, Asim; Farooq, Umar; Mahmood, Hassan; Asad, Muhammad Usman; Khan, Akrama; Atiq, Hafiz Muhammad

2010-02-01

A self teaching image processing and voice recognition based system is developed to educate visually impaired children, chiefly in their primary education. System comprises of a computer, a vision camera, an ear speaker and a microphone. Camera, attached with the computer system is mounted on the ceiling opposite (on the required angle) to the desk on which the book is placed. Sample images and voices in the form of instructions and commands of English, Urdu alphabets, Numeric Digits, Operators and Shapes are already stored in the database. A blind child first reads the embossed character (object) with the help of fingers than he speaks the answer, name of the character, shape etc into the microphone. With the voice command of a blind child received by the microphone, image is taken by the camera which is processed by MATLAB® program developed with the help of Image Acquisition and Image processing toolbox and generates a response or required set of instructions to child via ear speaker, resulting in self education of a visually impaired child. Speech recognition program is also developed in MATLAB® with the help of Data Acquisition and Signal Processing toolbox which records and process the command of the blind child.

Intonation contrast in Cantonese speakers with hypokinetic dysarthria associated with Parkinson's disease.

PubMed

Ma, Joan K-Y; Whitehill, Tara L; So, Susanne Y-S

2010-08-01

Speech produced by individuals with hypokinetic dysarthria associated with Parkinson's disease (PD) is characterized by a number of features including impaired speech prosody. The purpose of this study was to investigate intonation contrasts produced by this group of speakers. Speech materials with a question-statement contrast were collected from 14 Cantonese speakers with PD. Twenty listeners then classified the productions as either questions or statements. Acoustic analyses of F0, duration, and intensity were conducted to determine which acoustic cues distinguished the production of questions from statements, and which cues appeared to be exploited by listeners in identifying intonational contrasts. The results show that listeners identified statements with a high degree of accuracy, but the accuracy of question identification ranged from 0.56% to 96% across the 14 speakers. The speakers with PD used similar acoustic cues as nondysarthric Cantonese speakers to mark the question-statement contrast, although the contrasts were not observed in all speakers. Listeners mainly used F0 cues at the final syllable for intonation identification. These data contribute to the researchers' understanding of intonation marking in speakers with PD, with specific application to the production and perception of intonation in a lexical tone language.

Speech motor programming in apraxia of speech: evidence from a delayed picture-word interference task.

PubMed

Mailend, Marja-Liisa; Maas, Edwin

2013-05-01

Apraxia of speech (AOS) is considered a speech motor programming impairment, but the specific nature of the impairment remains a matter of debate. This study investigated 2 hypotheses about the underlying impairment in AOS framed within the Directions Into Velocities of Articulators (DIVA; Guenther, Ghosh, & Tourville, 2006) model: The retrieval hypothesis states that access to the motor programs is impaired, and the damaged programs hypothesis states that the motor programs themselves are damaged. The experiment used a delayed picture-word interference paradigm in which participants prepare their response and auditory distracters are presented with the go signal. The overlap between target and distracter words was manipulated (i.e., shared sounds or no shared sounds), and participants' reaction times (RTs) were measured. Participants included 5 speakers with AOS (4 with concomitant aphasia), 2 speakers with aphasia without AOS, and 9 age-matched control speakers. The control speakers showed no effects of distracter type or presence. The speakers with AOS had longer RTs in the distracter condition compared to the no-distracter condition. The speakers with aphasia without AOS were comparable to the control group in their overall RTs and RT pattern. Results provide preliminary support for the retrieval hypothesis, suggesting that access to motor programs may be impaired in speakers with AOS. However, the possibility that the motor programs may also be damaged cannot be ruled out.

The 2016 NIST Speaker Recognition Evaluation

DTIC Science & Technology

2017-08-20

The 2016 NIST Speaker Recognition Evaluation Seyed Omid Sadjadi1,∗, Timothée Kheyrkhah1,†, Audrey Tong1, Craig Greenberg1, Douglas Reynolds2, Elliot...recent in an ongoing series of speaker recognition evaluations (SRE) to foster research in ro- bust text-independent speaker recognition, as well as...online evaluation platform, a fixed training data condition, more variability in test segment duration (uni- formly distributed between 10s and 60s

a Study of Multiplexing Schemes for Voice and Data.

NASA Astrophysics Data System (ADS)

Sriram, Kotikalapudi

Voice traffic variations are characterized by on/off transitions of voice calls, and talkspurt/silence transitions of speakers in conversations. A speaker is known to be in silence for more than half the time during a telephone conversation. In this dissertation, we study some schemes which exploit speaker silences for an efficient utilization of the transmission capacity in integrated voice/data multiplexing and in digital speech interpolation. We study two voice/data multiplexing schemes. In each scheme, any time slots momentarily unutilized by the voice traffic are made available to data. In the first scheme, the multiplexer does not use speech activity detectors (SAD), and hence the voice traffic variations are due to call on/off only. In the second scheme, the multiplexer detects speaker silences using SAD and transmits voice only during talkspurts. The multiplexer with SAD performs digital speech interpolation (DSI) as well as dynamic channel allocation to voice and data. The performance of the two schemes is evaluated using discrete-time modeling and analysis. The data delay performance for the case of English speech is compared with that for the case of Japanese speech. A closed form expression for the mean data message delay is derived for the single-channel single-talker case. In a DSI system, occasional speech losses occur whenever the number of speakers in simultaneous talkspurt exceeds the number of TDM voice channels. In a buffered DSI system, speech loss is further reduced at the cost of delay. We propose a novel fixed-delay buffered DSI scheme. In this scheme, speech fill-in/hangover is not required because there are no variable delays. Hence, all silences that naturally occur in speech are fully utilized. Consequently, a substantial improvement in the DSI performance is made possible. The scheme is modeled and analyzed in discrete -time. Its performance is evaluated in terms of the probability of speech clipping, packet rejection ratio, DSI advantage, and the delay.

Perceptual Learning of Time-Compressed Speech: More than Rapid Adaptation

PubMed Central

Banai, Karen; Lavner, Yizhar

2012-01-01

Background Time-compressed speech, a form of rapidly presented speech, is harder to comprehend than natural speech, especially for non-native speakers. Although it is possible to adapt to time-compressed speech after a brief exposure, it is not known whether additional perceptual learning occurs with further practice. Here, we ask whether multiday training on time-compressed speech yields more learning than that observed during the initial adaptation phase and whether the pattern of generalization following successful learning is different than that observed with initial adaptation only. Methodology/Principal Findings Two groups of non-native Hebrew speakers were tested on five different conditions of time-compressed speech identification in two assessments conducted 10–14 days apart. Between those assessments, one group of listeners received five practice sessions on one of the time-compressed conditions. Between the two assessments, trained listeners improved significantly more than untrained listeners on the trained condition. Furthermore, the trained group generalized its learning to two untrained conditions in which different talkers presented the trained speech materials. In addition, when the performance of the non-native speakers was compared to that of a group of naïve native Hebrew speakers, performance of the trained group was equivalent to that of the native speakers on all conditions on which learning occurred, whereas performance of the untrained non-native listeners was substantially poorer. Conclusions/Significance Multiday training on time-compressed speech results in significantly more perceptual learning than brief adaptation. Compared to previous studies of adaptation, the training induced learning is more stimulus specific. Taken together, the perceptual learning of time-compressed speech appears to progress from an initial, rapid adaptation phase to a subsequent prolonged and more stimulus specific phase. These findings are consistent with the predictions of the Reverse Hierarchy Theory of perceptual learning and suggest constraints on the use of perceptual-learning regimens during second language acquisition. PMID:23056592

Research on the optoacoustic communication system for speech transmission by variable laser-pulse repetition rates

NASA Astrophysics Data System (ADS)

Jiang, Hongyan; Qiu, Hongbing; He, Ning; Liao, Xin

2018-06-01

For the optoacoustic communication from in-air platforms to submerged apparatus, a method based on speech recognition and variable laser-pulse repetition rates is proposed, which realizes character encoding and transmission for speech. Firstly, the theories and spectrum characteristics of the laser-generated underwater sound are analyzed; and moreover character conversion and encoding for speech as well as the pattern of codes for laser modulation is studied; lastly experiments to verify the system design are carried out. Results show that the optoacoustic system, where laser modulation is controlled by speech-to-character baseband codes, is beneficial to improve flexibility in receiving location for underwater targets as well as real-time performance in information transmission. In the overwater transmitter, a pulse laser is controlled to radiate by speech signals with several repetition rates randomly selected in the range of one to fifty Hz, and then in the underwater receiver laser pulse repetition rate and data can be acquired by the preamble and information codes of the corresponding laser-generated sound. When the energy of the laser pulse is appropriate, real-time transmission for speaker-independent speech can be realized in that way, which solves the problem of underwater bandwidth resource and provides a technical approach for the air-sea communication.

Post-treatment speech naturalness of comprehensive stuttering program clients and differences in ratings among listener groups.

PubMed

Teshima, Shelli; Langevin, Marilyn; Hagler, Paul; Kully, Deborah

2010-03-01

The purposes of this study were to investigate naturalness of the post-treatment speech of Comprehensive Stuttering Program (CSP) clients and differences in naturalness ratings by three listener groups. Listeners were 21 student speech-language pathologists, 9 community members, and 15 listeners who stutter. Listeners rated perceptually fluent speech samples of CSP clients obtained immediately post-treatment (Post) and at 5 years follow-up (F5), and speech samples of matched typically fluent (TF) speakers. A 9-point interval rating scale was used. A 3 (listener group)x2 (time)x2 (speaker) mixed ANOVA was used to test for differences among mean ratings. The difference between CSP Post and F5 mean ratings was statistically significant. The F5 mean rating was within the range reported for typically fluent speakers. Student speech-language pathologists were found to be less critical than community members and listeners who stutter in rating naturalness; however, there were no significant differences in ratings made by community members and listeners who stutter. Results indicate that the naturalness of post-treatment speech of CSP clients improves in the post-treatment period and that it is possible for clients to achieve levels of naturalness that appear to be acceptable to adults who stutter and that are within the range of naturalness ratings given to typically fluent speakers. Readers will be able to (a) summarize key findings of studies that have investigated naturalness ratings, and (b) interpret the naturalness ratings of Comprehensive Stuttering Program speaker samples and the ratings made by the three listener groups in this study.

English vowel learning by speakers of Mandarin

NASA Astrophysics Data System (ADS)

Thomson, Ron I.

2005-04-01

One of the most influential models of second language (L2) speech perception and production [Flege, Speech Perception and Linguistic Experience (York, Baltimore, 1995) pp. 233-277] argues that during initial stages of L2 acquisition, perceptual categories sharing the same or nearly the same acoustic space as first language (L1) categories will be processed as members of that L1 category. Previous research has generally been limited to testing these claims on binary L2 contrasts, rather than larger portions of the perceptual space. This study examines the development of 10 English vowel categories by 20 Mandarin L1 learners of English. Imitation of English vowel stimuli by these learners, at 6 data collection points over the course of one year, were recorded. Using a statistical pattern recognition model, these productions were then assessed against native speaker norms. The degree to which the learners' perception/production shifted toward the target English vowels and the degree to which they matched L1 categories in ways predicted by theoretical models are discussed. The results of this experiment suggest that previous claims about perceptual assimilation of L2 categories to L1 categories may be too strong.

Comparison of singer's formant, speaker's ring, and LTA spectrum among classical singers and untrained normal speakers.

PubMed

Oliveira Barrichelo, V M; Heuer, R J; Dean, C M; Sataloff, R T

2001-09-01

Many studies have described and analyzed the singer's formant. A similar phenomenon produced by trained speakers led some authors to examine the speaker's ring. If we consider these phenomena as resonance effects associated with vocal tract adjustments and training, can we hypothesize that trained singers can carry over their singing formant ability into speech, also obtaining a speaker's ring? Can we find similar differences for energy distribution in continuous speech? Forty classically trained singers and forty untrained normal speakers performed an all-voiced reading task and produced a sample of a sustained spoken vowel /a/. The singers were also requested to perform a sustained sung vowel /a/ at a comfortable pitch. The reading was analyzed by the long-term average spectrum (LTAS) method. The sustained vowels were analyzed through power spectrum analysis. The data suggest that singers show more energy concentration in the singer's formant/speaker's ring region in both sung and spoken vowels. The singers' spoken vowel energy in the speaker's ring area was found to be significantly larger than that of the untrained speakers. The LTAS showed similar findings suggesting that those differences also occur in continuous speech. This finding supports the value of further research on the effect of singing training on the resonance of the speaking voice.

Vocal Age Disguise: The Role of Fundamental Frequency and Speech Rate and Its Perceived Effects.

PubMed

Skoog Waller, Sara; Eriksson, Mårten

2016-01-01

The relationship between vocal characteristics and perceived age is of interest in various contexts, as is the possibility to affect age perception through vocal manipulation. A few examples of such situations are when age is staged by actors, when ear witnesses make age assessments based on vocal cues only or when offenders (e.g., online groomers) disguise their voice to appear younger or older. This paper investigates how speakers spontaneously manipulate two age related vocal characteristics ( f 0 and speech rate) in attempt to sound younger versus older than their true age, and if the manipulations correspond to actual age related changes in f 0 and speech rate (Study 1). Further aims of the paper is to determine how successful vocal age disguise is by asking listeners to estimate the age of generated speech samples (Study 2) and to examine whether or not listeners use f 0 and speech rate as cues to perceived age. In Study 1, participants from three age groups (20-25, 40-45, and 60-65 years) agreed to read a short text under three voice conditions. There were 12 speakers in each age group (six women and six men). They used their natural voice in one condition, attempted to sound 20 years younger in another and 20 years older in a third condition. In Study 2, 60 participants (listeners) listened to speech samples from the three voice conditions in Study 1 and estimated the speakers' age. Each listener was exposed to all three voice conditions. The results from Study 1 indicated that the speakers increased fundamental frequency ( f 0 ) and speech rate when attempting to sound younger and decreased f 0 and speech rate when attempting to sound older. Study 2 showed that the voice manipulations had an effect in the sought-after direction, although the achieved mean effect was only 3 years, which is far less than the intended effect of 20 years. Moreover, listeners used speech rate, but not f 0 , as a cue to speaker age. It was concluded that age disguise by voice can be achieved by naïve speakers even though the perceived effect was smaller than intended.

Inferior frontal sensitivity to common speech sounds is amplified by increasing word intelligibility.

PubMed

Vaden, Kenneth I; Kuchinsky, Stefanie E; Keren, Noam I; Harris, Kelly C; Ahlstrom, Jayne B; Dubno, Judy R; Eckert, Mark A

2011-11-01

The left inferior frontal gyrus (LIFG) exhibits increased responsiveness when people listen to words composed of speech sounds that frequently co-occur in the English language (Vaden, Piquado, & Hickok, 2011), termed high phonotactic frequency (Vitevitch & Luce, 1998). The current experiment aimed to further characterize the relation of phonotactic frequency to LIFG activity by manipulating word intelligibility in participants of varying age. Thirty six native English speakers, 19-79 years old (mean=50.5, sd=21.0) indicated with a button press whether they recognized 120 binaurally presented consonant-vowel-consonant words during a sparse sampling fMRI experiment (TR=8 s). Word intelligibility was manipulated by low-pass filtering (cutoff frequencies of 400 Hz, 1000 Hz, 1600 Hz, and 3150 Hz). Group analyses revealed a significant positive correlation between phonotactic frequency and LIFG activity, which was unaffected by age and hearing thresholds. A region of interest analysis revealed that the relation between phonotactic frequency and LIFG activity was significantly strengthened for the most intelligible words (low-pass cutoff at 3150 Hz). These results suggest that the responsiveness of the left inferior frontal cortex to phonotactic frequency reflects the downstream impact of word recognition rather than support of word recognition, at least when there are no speech production demands. Published by Elsevier Ltd.

Combining Behavioral and ERP Methodologies to Investigate the Differences Between McGurk Effects Demonstrated by Cantonese and Mandarin Speakers.

PubMed

Zhang, Juan; Meng, Yaxuan; McBride, Catherine; Fan, Xitao; Yuan, Zhen

2018-01-01

The present study investigated the impact of Chinese dialects on McGurk effect using behavioral and event-related potential (ERP) methodologies. Specifically, intra-language comparison of McGurk effect was conducted between Mandarin and Cantonese speakers. The behavioral results showed that Cantonese speakers exhibited a stronger McGurk effect in audiovisual speech perception compared to Mandarin speakers, although both groups performed equally in the auditory and visual conditions. ERP results revealed that Cantonese speakers were more sensitive to visual cues than Mandarin speakers, though this was not the case for the auditory cues. Taken together, the current findings suggest that the McGurk effect generated by Chinese speakers is mainly influenced by segmental phonology during audiovisual speech integration.

Combining Behavioral and ERP Methodologies to Investigate the Differences Between McGurk Effects Demonstrated by Cantonese and Mandarin Speakers

PubMed Central

Zhang, Juan; Meng, Yaxuan; McBride, Catherine; Fan, Xitao; Yuan, Zhen

2018-01-01

The present study investigated the impact of Chinese dialects on McGurk effect using behavioral and event-related potential (ERP) methodologies. Specifically, intra-language comparison of McGurk effect was conducted between Mandarin and Cantonese speakers. The behavioral results showed that Cantonese speakers exhibited a stronger McGurk effect in audiovisual speech perception compared to Mandarin speakers, although both groups performed equally in the auditory and visual conditions. ERP results revealed that Cantonese speakers were more sensitive to visual cues than Mandarin speakers, though this was not the case for the auditory cues. Taken together, the current findings suggest that the McGurk effect generated by Chinese speakers is mainly influenced by segmental phonology during audiovisual speech integration. PMID:29780312

A dynamic multi-channel speech enhancement system for distributed microphones in a car environment

NASA Astrophysics Data System (ADS)

Matheja, Timo; Buck, Markus; Fingscheidt, Tim

2013-12-01

Supporting multiple active speakers in automotive hands-free or speech dialog applications is an interesting issue not least due to comfort reasons. Therefore, a multi-channel system for enhancement of speech signals captured by distributed distant microphones in a car environment is presented. Each of the potential speakers in the car has a dedicated directional microphone close to his position that captures the corresponding speech signal. The aim of the resulting overall system is twofold: On the one hand, a combination of an arbitrary pre-defined subset of speakers' signals can be performed, e.g., to create an output signal in a hands-free telephone conference call for a far-end communication partner. On the other hand, annoying cross-talk components from interfering sound sources occurring in multiple different mixed output signals are to be eliminated, motivated by the possibility of other hands-free applications being active in parallel. The system includes several signal processing stages. A dedicated signal processing block for interfering speaker cancellation attenuates the cross-talk components of undesired speech. Further signal enhancement comprises the reduction of residual cross-talk and background noise. Subsequently, a dynamic signal combination stage merges the processed single-microphone signals to obtain appropriate mixed signals at the system output that may be passed to applications such as telephony or a speech dialog system. Based on signal power ratios between the particular microphone signals, an appropriate speaker activity detection and therewith a robust control mechanism of the whole system is presented. The proposed system may be dynamically configured and has been evaluated for a car setup with four speakers sitting in the car cabin disturbed in various noise conditions.

Focused and divided attention in a simulated cocktail-party situation: ERP evidence from younger and older adults.

PubMed

Getzmann, Stephan; Golob, Edward J; Wascher, Edmund

2016-05-01

Speech perception under complex listening conditions usually decreases in aging. This is especially true for listening conditions requiring divided attention among 2 and more relevant speakers. Using a speech perception task and event-related potential measures, we studied the ability of younger and older adults to attend to speech information from a single-target speaker (focused attention) or from 2 different (alternative) target speakers (divided attention). The focused and divided attention conditions were presented either in silence or in the presence of 3 concurrent speakers. In the presence of concurrent speakers, older participants showed worse performance with divided versus focused attention. In contrast, there was no effect of attention condition for the younger adults. Relative to the young, event-related potential analysis in older subjects indicated a decline in preparatory activity for the critical speech information (a delayed and smaller contingent negative variation), and delayed attentional control (indicated by a longer P2 latency). Standardized low-resolution brain electromagnetic tomography revealed that the age-related decline in preparatory activity was associated with reduced activation of medial and superior frontal gyrus and anterior cingulate gyrus. The results suggest that age-related differences in these prefrontal brain areas reflect declines in preparatory attention and gating of subsequent task-related speech information, especially under conditions of divided attention. These findings may reflect mechanisms relating to impaired speech perception by older people in "cocktail-party" listening situations. Copyright © 2016 Elsevier Inc. All rights reserved.

Linking language to the visual world: Neural correlates of comprehending verbal reference to objects through pointing and visual cues.

PubMed

Peeters, David; Snijders, Tineke M; Hagoort, Peter; Özyürek, Aslı

2017-01-27

In everyday communication speakers often refer in speech and/or gesture to objects in their immediate environment, thereby shifting their addressee's attention to an intended referent. The neurobiological infrastructure involved in the comprehension of such basic multimodal communicative acts remains unclear. In an event-related fMRI study, we presented participants with pictures of a speaker and two objects while they concurrently listened to her speech. In each picture, one of the objects was singled out, either through the speaker's index-finger pointing gesture or through a visual cue that made the object perceptually more salient in the absence of gesture. A mismatch (compared to a match) between speech and the object singled out by the speaker's pointing gesture led to enhanced activation in left IFG and bilateral pMTG, showing the importance of these areas in conceptual matching between speech and referent. Moreover, a match (compared to a mismatch) between speech and the object made salient through a visual cue led to enhanced activation in the mentalizing system, arguably reflecting an attempt to converge on a jointly attended referent in the absence of pointing. These findings shed new light on the neurobiological underpinnings of the core communicative process of comprehending a speaker's multimodal referential act and stress the power of pointing as an important natural device to link speech to objects. Copyright © 2016 Elsevier Ltd. All rights reserved.

Use of listening strategies for the speech of individuals with dysarthria and cerebral palsy.

PubMed

Hustad, Katherine C; Dardis, Caitlin M; Kramper, Amy J

2011-03-01

This study examined listeners' endorsement of cognitive, linguistic, segmental, and suprasegmental strategies employed when listening to speakers with dysarthria. The study also examined whether strategy endorsement differed between listeners who earned the highest and lowest intelligibility scores. Speakers were eight individuals with dysarthria and cerebral palsy. Listeners were 80 individuals who transcribed speech stimuli and rated their use of each of 24 listening strategies on a 4-point scale. Results showed that cognitive and linguistic strategies were most highly endorsed. Use of listening strategies did not differ between listeners with the highest and lowest intelligibility scores. Results suggest that there may be a core of strategies common to listeners of speakers with dysarthria that may be supplemented by additional strategies, based on characteristics of the speaker and speech signal.

Comparison of different speech tasks among adults who stutter and adults who do not stutter

PubMed Central

Ritto, Ana Paula; Costa, Julia Biancalana; Juste, Fabiola Staróbole; de Andrade, Claudia Regina Furquim

2016-01-01

OBJECTIVES: In this study, we compared the performance of both fluent speakers and people who stutter in three different speaking situations: monologue speech, oral reading and choral reading. This study follows the assumption that the neuromotor control of speech can be influenced by external auditory stimuli in both speakers who stutter and speakers who do not stutter. METHOD: Seventeen adults who stutter and seventeen adults who do not stutter were assessed in three speaking tasks: monologue, oral reading (solo reading aloud) and choral reading (reading in unison with the evaluator). Speech fluency and rate were measured for each task. RESULTS: The participants who stuttered had a lower frequency of stuttering during choral reading than during monologue and oral reading. CONCLUSIONS: According to the dual premotor system model, choral speech enhanced fluency by providing external cues for the timing of each syllable compensating for deficient internal cues. PMID:27074176

A posteriori error estimates in voice source recovery

NASA Astrophysics Data System (ADS)

Leonov, A. S.; Sorokin, V. N.

2017-12-01

The inverse problem of voice source pulse recovery from a segment of a speech signal is under consideration. A special mathematical model is used for the solution that relates these quantities. A variational method of solving inverse problem of voice source recovery for a new parametric class of sources, that is for piecewise-linear sources (PWL-sources), is proposed. Also, a technique for a posteriori numerical error estimation for obtained solutions is presented. A computer study of the adequacy of adopted speech production model with PWL-sources is performed in solving the inverse problems for various types of voice signals, as well as corresponding study of a posteriori error estimates. Numerical experiments for speech signals show satisfactory properties of proposed a posteriori error estimates, which represent the upper bounds of possible errors in solving the inverse problem. The estimate of the most probable error in determining the source-pulse shapes is about 7-8% for the investigated speech material. It is noted that a posteriori error estimates can be used as a criterion of the quality for obtained voice source pulses in application to speaker recognition.

Auditory noise increases the allocation of attention to the mouth, and the eyes pay the price: An eye-tracking study.

PubMed

Król, Magdalena Ewa

2018-01-01

We investigated the effect of auditory noise added to speech on patterns of looking at faces in 40 toddlers. We hypothesised that noise would increase the difficulty of processing speech, making children allocate more attention to the mouth of the speaker to gain visual speech cues from mouth movements. We also hypothesised that this shift would cause a decrease in fixation time to the eyes, potentially decreasing the ability to monitor gaze. We found that adding noise increased the number of fixations to the mouth area, at the price of a decreased number of fixations to the eyes. Thus, to our knowledge, this is the first study demonstrating a mouth-eyes trade-off between attention allocated to social cues coming from the eyes and linguistic cues coming from the mouth. We also found that children with higher word recognition proficiency and higher average pupil response had an increased likelihood of fixating the mouth, compared to the eyes and the rest of the screen, indicating stronger motivation to decode the speech.

Auditory noise increases the allocation of attention to the mouth, and the eyes pay the price: An eye-tracking study

PubMed Central

2018-01-01

We investigated the effect of auditory noise added to speech on patterns of looking at faces in 40 toddlers. We hypothesised that noise would increase the difficulty of processing speech, making children allocate more attention to the mouth of the speaker to gain visual speech cues from mouth movements. We also hypothesised that this shift would cause a decrease in fixation time to the eyes, potentially decreasing the ability to monitor gaze. We found that adding noise increased the number of fixations to the mouth area, at the price of a decreased number of fixations to the eyes. Thus, to our knowledge, this is the first study demonstrating a mouth-eyes trade-off between attention allocated to social cues coming from the eyes and linguistic cues coming from the mouth. We also found that children with higher word recognition proficiency and higher average pupil response had an increased likelihood of fixating the mouth, compared to the eyes and the rest of the screen, indicating stronger motivation to decode the speech. PMID:29558514

Advances in audio source seperation and multisource audio content retrieval

NASA Astrophysics Data System (ADS)

Vincent, Emmanuel

2012-06-01

Audio source separation aims to extract the signals of individual sound sources from a given recording. In this paper, we review three recent advances which improve the robustness of source separation in real-world challenging scenarios and enable its use for multisource content retrieval tasks, such as automatic speech recognition (ASR) or acoustic event detection (AED) in noisy environments. We present a Flexible Audio Source Separation Toolkit (FASST) and discuss its advantages compared to earlier approaches such as independent component analysis (ICA) and sparse component analysis (SCA). We explain how cues as diverse as harmonicity, spectral envelope, temporal fine structure or spatial location can be jointly exploited by this toolkit. We subsequently present the uncertainty decoding (UD) framework for the integration of audio source separation and audio content retrieval. We show how the uncertainty about the separated source signals can be accurately estimated and propagated to the features. Finally, we explain how this uncertainty can be efficiently exploited by a classifier, both at the training and the decoding stage. We illustrate the resulting performance improvements in terms of speech separation quality and speaker recognition accuracy.

Evaluation of a cochlear-implant processing strategy incorporating phantom stimulation and asymmetric pulses

PubMed Central

Monstrey, Jolijn; Deeks, John M.; Macherey, Olivier

2014-01-01

Objective To evaluate a speech-processing strategy in which the lowest frequency channel is conveyed using an asymmetric pulse shape and “phantom stimulation”, where current is injected into one intra-cochlear electrode and where the return current is shared between an intra-cochlear and an extra-cochlear electrode. This strategy is expected to provide more selective excitation of the cochlear apex, compared to a standard strategy where the lowest-frequency channel is conveyed by symmetric pulses in monopolar mode. In both strategies all other channels were conveyed by monopolar stimulation. Design Within-subjects comparison between the two strategies. Four experiments: (1) discrimination between the strategies, controlling for loudness differences, (2) consonant identification, (3) recognition of lowpass-filtered sentences in quiet, (4) sentence recognition in the presence of a competing speaker. Study sample Eight users of the Advanced Bionics CII/Hi-Res 90k cochlear implant. Results Listeners could easily discriminate between the two strategies but no consistent differences in performance were observed. Conclusions The proposed method does not improve speech perception, at least in the short term. PMID:25358027

Evaluation of a cochlear-implant processing strategy incorporating phantom stimulation and asymmetric pulses.

PubMed

Carlyon, Robert P; Monstrey, Jolijn; Deeks, John M; Macherey, Olivier

2014-12-01

To evaluate a speech-processing strategy in which the lowest frequency channel is conveyed using an asymmetric pulse shape and "phantom stimulation", where current is injected into one intra-cochlear electrode and where the return current is shared between an intra-cochlear and an extra-cochlear electrode. This strategy is expected to provide more selective excitation of the cochlear apex, compared to a standard strategy where the lowest-frequency channel is conveyed by symmetric pulses in monopolar mode. In both strategies all other channels were conveyed by monopolar stimulation. Within-subjects comparison between the two strategies. Four experiments: (1) discrimination between the strategies, controlling for loudness differences, (2) consonant identification, (3) recognition of lowpass-filtered sentences in quiet, (4) sentence recognition in the presence of a competing speaker. Eight users of the Advanced Bionics CII/Hi-Res 90k cochlear implant. Listeners could easily discriminate between the two strategies but no consistent differences in performance were observed. The proposed method does not improve speech perception, at least in the short term.

Real-time speech gisting for ATC applications

NASA Astrophysics Data System (ADS)

Dunkelberger, Kirk A.

1995-06-01

Command and control within the ATC environment remains primarily voice-based. Hence, automatic real time, speaker independent, continuous speech recognition (CSR) has many obvious applications and implied benefits to the ATC community: automated target tagging, aircraft compliance monitoring, controller training, automatic alarm disabling, display management, and many others. However, while current state-of-the-art CSR systems provide upwards of 98% word accuracy in laboratory environments, recent low-intrusion experiments in the ATCT environments demonstrated less than 70% word accuracy in spite of significant investments in recognizer tuning. Acoustic channel irregularities and controller/pilot grammar verities impact current CSR algorithms at their weakest points. It will be shown herein, however, that real time context- and environment-sensitive gisting can provide key command phrase recognition rates of greater than 95% using the same low-intrusion approach. The combination of real time inexact syntactic pattern recognition techniques and a tight integration of CSR, gisting, and ATC database accessor system components is the key to these high phase recognition rates. A system concept for real time gisting in the ATC context is presented herein. After establishing an application context, discussion presents a minimal CSR technology context then focuses on the gisting mechanism, desirable interfaces into the ATCT database environment, and data and control flow within the prototype system. Results of recent tests for a subset of the functionality are presented together with suggestions for further research.

Formant transitions in the fluent speech of Farsi-speaking people who stutter.

PubMed

Dehqan, Ali; Yadegari, Fariba; Blomgren, Michael; Scherer, Ronald C

2016-06-01

Second formant (F2) transitions can be used to infer attributes of articulatory transitions. This study compared formant transitions during fluent speech segments of Farsi (Persian) speaking people who stutter and normally fluent Farsi speakers. Ten Iranian males who stutter and 10 normally fluent Iranian males participated. Sixteen different "CVt" tokens were embedded within the phrase "Begu CVt an". Measures included overall F2 transition frequency extents, durations, and derived overall slopes, initial F2 transition slopes at 30ms and 60ms, and speaking rate. (1) Mean overall formant frequency extent was significantly greater in 14 of the 16 CVt tokens for the group of stuttering speakers. (2) Stuttering speakers exhibited significantly longer overall F2 transitions for all 16 tokens compared to the nonstuttering speakers. (3) The overall F2 slopes were similar between the two groups. (4) The stuttering speakers exhibited significantly greater initial F2 transition slopes (positive or negative) for five of the 16 tokens at 30ms and six of the 16 tokens at 60ms. (5) The stuttering group produced a slower syllable rate than the non-stuttering group. During perceptually fluent utterances, the stuttering speakers had greater F2 frequency extents during transitions, took longer to reach vowel steady state, exhibited some evidence of steeper slopes at the beginning of transitions, had overall similar F2 formant slopes, and had slower speaking rates compared to nonstuttering speakers. Findings support the notion of different speech motor timing strategies in stuttering speakers. Findings are likely to be independent of the language spoken. Educational objectives This study compares aspects of F2 formant transitions between 10 stuttering and 10 nonstuttering speakers. Readers will be able to describe: (a) characteristics of formant frequency as a specific acoustic feature used to infer speech movements in stuttering and nonstuttering speakers, (b) two methods of measuring second formant (F2) transitions: the visual criteria method and fixed time criteria method, (c) characteristics of F2 transitions in the fluent speech of stuttering speakers and how those characteristics appear to differ from normally fluent speakers, and (d) possible cross-linguistic effects on acoustic analyses of stuttering. Copyright © 2016 Elsevier Inc. All rights reserved.

Voice emotion recognition by cochlear-implanted children and their normally-hearing peers.

PubMed

Chatterjee, Monita; Zion, Danielle J; Deroche, Mickael L; Burianek, Brooke A; Limb, Charles J; Goren, Alison P; Kulkarni, Aditya M; Christensen, Julie A

2015-04-01

Despite their remarkable success in bringing spoken language to hearing impaired listeners, the signal transmitted through cochlear implants (CIs) remains impoverished in spectro-temporal fine structure. As a consequence, pitch-dominant information such as voice emotion, is diminished. For young children, the ability to correctly identify the mood/intent of the speaker (which may not always be visible in their facial expression) is an important aspect of social and linguistic development. Previous work in the field has shown that children with cochlear implants (cCI) have significant deficits in voice emotion recognition relative to their normally hearing peers (cNH). Here, we report on voice emotion recognition by a cohort of 36 school-aged cCI. Additionally, we provide for the first time, a comparison of their performance to that of cNH and NH adults (aNH) listening to CI simulations of the same stimuli. We also provide comparisons to the performance of adult listeners with CIs (aCI), most of whom learned language primarily through normal acoustic hearing. Results indicate that, despite strong variability, on average, cCI perform similarly to their adult counterparts; that both groups' mean performance is similar to aNHs' performance with 8-channel noise-vocoded speech; that cNH achieve excellent scores in voice emotion recognition with full-spectrum speech, but on average, show significantly poorer scores than aNH with 8-channel noise-vocoded speech. A strong developmental effect was observed in the cNH with noise-vocoded speech in this task. These results point to the considerable benefit obtained by cochlear-implanted children from their devices, but also underscore the need for further research and development in this important and neglected area. This article is part of a Special Issue entitled . Copyright © 2014 Elsevier B.V. All rights reserved.

Audiovisual sentence recognition not predicted by susceptibility to the McGurk effect.

PubMed

Van Engen, Kristin J; Xie, Zilong; Chandrasekaran, Bharath

2017-02-01

In noisy situations, visual information plays a critical role in the success of speech communication: listeners are better able to understand speech when they can see the speaker. Visual influence on auditory speech perception is also observed in the McGurk effect, in which discrepant visual information alters listeners' auditory perception of a spoken syllable. When hearing /ba/ while seeing a person saying /ga/, for example, listeners may report hearing /da/. Because these two phenomena have been assumed to arise from a common integration mechanism, the McGurk effect has often been used as a measure of audiovisual integration in speech perception. In this study, we test whether this assumed relationship exists within individual listeners. We measured participants' susceptibility to the McGurk illusion as well as their ability to identify sentences in noise across a range of signal-to-noise ratios in audio-only and audiovisual modalities. Our results do not show a relationship between listeners' McGurk susceptibility and their ability to use visual cues to understand spoken sentences in noise, suggesting that McGurk susceptibility may not be a valid measure of audiovisual integration in everyday speech processing.

Attentional influences on functional mapping of speech sounds in human auditory cortex.

PubMed

Obleser, Jonas; Elbert, Thomas; Eulitz, Carsten

2004-07-21

The speech signal contains both information about phonological features such as place of articulation and non-phonological features such as speaker identity. These are different aspects of the 'what'-processing stream (speaker vs. speech content), and here we show that they can be further segregated as they may occur in parallel but within different neural substrates. Subjects listened to two different vowels, each spoken by two different speakers. During one block, they were asked to identify a given vowel irrespectively of the speaker (phonological categorization), while during the other block the speaker had to be identified irrespectively of the vowel (speaker categorization). Auditory evoked fields were recorded using 148-channel magnetoencephalography (MEG), and magnetic source imaging was obtained for 17 subjects. During phonological categorization, a vowel-dependent difference of N100m source location perpendicular to the main tonotopic gradient replicated previous findings. In speaker categorization, the relative mapping of vowels remained unchanged but sources were shifted towards more posterior and more superior locations. These results imply that the N100m reflects the extraction of abstract invariants from the speech signal. This part of the processing is accomplished in auditory areas anterior to AI, which are part of the auditory 'what' system. This network seems to include spatially separable modules for identifying the phonological information and for associating it with a particular speaker that are activated in synchrony but within different regions, suggesting that the 'what' processing can be more adequately modeled by a stream of parallel stages. The relative activation of the parallel processing stages can be modulated by attentional or task demands.

Mother and Father Speech: Distribution of Parental Speech Features in English and Spanish. Papers and Reports on Child Language Development, No. 12.

ERIC Educational Resources Information Center

Blount, Ben G.; Padgug, Elise J.

Features of parental speech to young children was studied in four English-speaking and four Spanish-speaking families. Children ranged in age from 9 to 12 months for the English speakers and from 8 to 22 months for the Spanish speakers. Examination of the utterances led to the identification of 34 prosodic, paralinguistic, and interactional…

The Impact of Dysphonic Voices on Healthy Listeners: Listener Reaction Times, Speech Intelligibility, and Listener Comprehension.

PubMed

Evitts, Paul M; Starmer, Heather; Teets, Kristine; Montgomery, Christen; Calhoun, Lauren; Schulze, Allison; MacKenzie, Jenna; Adams, Lauren

2016-11-01

There is currently minimal information on the impact of dysphonia secondary to phonotrauma on listeners. Considering the high incidence of voice disorders with professional voice users, it is important to understand the impact of a dysphonic voice on their audiences. Ninety-one healthy listeners (39 men, 52 women; mean age = 23.62 years) were presented with speech stimuli from 5 healthy speakers and 5 speakers diagnosed with dysphonia secondary to phonotrauma. Dependent variables included processing speed (reaction time [RT] ratio), speech intelligibility, and listener comprehension. Voice quality ratings were also obtained for all speakers by 3 expert listeners. Statistical results showed significant differences between RT ratio and number of speech intelligibility errors between healthy and dysphonic voices. There was not a significant difference in listener comprehension errors. Multiple regression analyses showed that voice quality ratings from the Consensus Assessment Perceptual Evaluation of Voice (Kempster, Gerratt, Verdolini Abbott, Barkmeier-Kraemer, & Hillman, 2009) were able to predict RT ratio and speech intelligibility but not listener comprehension. Results of the study suggest that although listeners require more time to process and have more intelligibility errors when presented with speech stimuli from speakers with dysphonia secondary to phonotrauma, listener comprehension may not be affected.

The Wildcat Corpus of Native- and Foreign-Accented English: Communicative Efficiency across Conversational Dyads with Varying Language Alignment Profiles

PubMed Central

Van Engen, Kristin J.; Baese-Berk, Melissa; Baker, Rachel E.; Choi, Arim; Kim, Midam; Bradlow, Ann R.

2012-01-01

This paper describes the development of the Wildcat Corpus of native- and foreign-accented English, a corpus containing scripted and spontaneous speech recordings from 24 native speakers of American English and 52 non-native speakers of English. The core element of this corpus is a set of spontaneous speech recordings, for which a new method of eliciting dialogue-based, laboratory-quality speech recordings was developed (the Diapix task). Dialogues between two native speakers of English, between two non-native speakers of English (with either shared or different L1s), and between one native and one non-native speaker of English are included and analyzed in terms of general measures of communicative efficiency. The overall finding was that pairs of native talkers were most efficient, followed by mixed native/non-native pairs and non-native pairs with shared L1. Non-native pairs with different L1s were least efficient. These results support the hypothesis that successful speech communication depends both on the alignment of talkers to the target language and on the alignment of talkers to one another in terms of native language background. PMID:21313992

Perceiving non-native speech: Word segmentation

NASA Astrophysics Data System (ADS)

Mondini, Michèle; Miller, Joanne L.

2004-05-01

One important source of information listeners use to segment speech into discrete words is allophonic variation at word junctures. Previous research has shown that non-native speakers impose their native-language phonetic norms on their second language; as a consequence, non-native speech may (in some cases) exhibit altered patterns of allophonic variation at word junctures. We investigated the perceptual consequences of this for word segmentation by presenting native-English listeners with English word pairs produced either by six native-English speakers or six highly fluent, native-French speakers of English. The target word pairs had contrastive word juncture involving voiceless stop consonants (e.g., why pink/wipe ink; gray ties/great eyes; we cash/weak ash). The task was to identify randomized instances of each individual target word pair (as well as control pairs) by selecting one of four possible choices (e.g., why pink, wipe ink, why ink, wipe pink). Overall, listeners were more accurate in identifying target word pairs produced by the native-English speakers than by the non-native English speakers. These findings suggest that one contribution to the processing cost associated with listening to non-native speech may be the presence of altered allophonic information important for word segmentation. [Work supported by NIH/NIDCD.

Understanding speaker attitudes from prosody by adults with Parkinson's disease.

PubMed

Monetta, Laura; Cheang, Henry S; Pell, Marc D

2008-09-01

The ability to interpret vocal (prosodic) cues during social interactions can be disrupted by Parkinson's disease, with notable effects on how emotions are understood from speech. This study investigated whether PD patients who have emotional prosody deficits exhibit further difficulties decoding the attitude of a speaker from prosody. Vocally inflected but semantically nonsensical 'pseudo-utterances' were presented to listener groups with and without PD in two separate rating tasks. Task I required participants to rate how confident a speaker sounded from their voice and Task 2 required listeners to rate how polite the speaker sounded for a comparable set of pseudo-utterances. The results showed that PD patients were significantly less able than HC participants to use prosodic cues to differentiate intended levels of speaker confidence in speech, although the patients could accurately detect the politelimpolite attitude of the speaker from prosody in most cases. Our data suggest that many PD patients fail to use vocal cues to effectively infer a speaker's emotions as well as certain attitudes in speech such as confidence, consistent with the idea that the basal ganglia play a role in the meaningful processing of prosodic sequences in spoken language (Pell & Leonard, 2003).

Breath-Group Intelligibility in Dysarthria: Characteristics and Underlying Correlates

ERIC Educational Resources Information Center

Yunusova, Yana; Weismer, Gary; Kent, Ray D.; Rusche, Nicole M.

2005-01-01

Purpose: This study was designed to determine whether within-speaker fluctuations in speech intelligibility occurred among speakers with dysarthria who produced a reading passage, and, if they did, whether selected linguistic and acoustic variables predicted the variations in speech intelligibility. Method: Participants with dysarthria included a…

Speech Situation Checklist-Revised: Investigation With Adults Who Do Not Stutter and Treatment-Seeking Adults Who Stutter.

PubMed

Vanryckeghem, Martine; Matthews, Michael; Xu, Peixin

2017-11-08

The aim of this study was to evaluate the usefulness of the Speech Situation Checklist for adults who stutter (SSC) in differentiating people who stutter (PWS) from speakers with no stutter based on self-reports of anxiety and speech disruption in communicative settings. The SSC's psychometric properties were examined, norms were established, and suggestions for treatment were formulated. The SSC was administered to 88 PWS seeking treatment and 209 speakers with no stutter between the ages of 18 and 62. The SSC consists of 2 sections investigating negative emotional reaction and speech disruption in 38 speech situations that are identical in both sections. The SSC-Emotional Reaction and SSC-Speech Disruption data show that these self-report tests differentiate PWS from speakers with no stutter to a statistically significant extent and have great discriminative value. The tests have good internal reliability, content, and construct validity. Age and gender do not affect the scores of the PWS. The SSC-Emotional Reaction and SSC-Speech Disruption seem to be powerful measures to investigate negative emotion and speech breakdown in an array of speech situations. The item scores give direction to treatment by suggesting speech situations that need a clinician's attention in terms of generalization and carry-over of within-clinic therapeutic gains into in vivo settings.

Speech effort measurement and stuttering: investigating the chorus reading effect.

PubMed

Ingham, Roger J; Warner, Allison; Byrd, Anne; Cotton, John

2006-06-01

The purpose of this study was to investigate chorus reading's (CR's) effect on speech effort during oral reading by adult stuttering speakers and control participants. The effect of a speech effort measurement highlighting strategy was also investigated. Twelve persistent stuttering (PS) adults and 12 normally fluent control participants completed 1-min base rate readings (BR-nonchorus) and CRs within a BR/CR/BR/CR/BR experimental design. Participants self-rated speech effort using a 9-point scale after each reading trial. Stuttering frequency, speech rate, and speech naturalness measures were also obtained. Instructions highlighting speech effort ratings during BR and CR phases were introduced after the first CR. CR improved speech effort ratings for the PS group, but the control group showed a reverse trend. Both groups' effort ratings were not significantly different during CR phases but were significantly poorer than the control group's effort ratings during BR phases. The highlighting strategy did not significantly change effort ratings. The findings show that CR will produce not only stutter-free and natural sounding speech but also reliable reductions in speech effort. However, these reductions do not reach effort levels equivalent to those achieved by normally fluent speakers, thereby conditioning its use as a gold standard of achievable normal fluency by PS speakers.

Variability and Intelligibility of Clarified Speech to Different Listener Groups

NASA Astrophysics Data System (ADS)

Silber, Ronnie F.

Two studies examined the modifications that adult speakers make in speech to disadvantaged listeners. Previous research that has focused on speech to the deaf individuals and to young children has shown that adults clarify speech when addressing these two populations. Acoustic measurements suggest that the signal undergoes similar changes for both populations. Perceptual tests corroborate these results for the deaf population, but are nonsystematic in developmental studies. The differences in the findings for these populations and the nonsystematic results in the developmental literature may be due to methodological factors. The present experiments addressed these methodological questions. Studies of speech to hearing impaired listeners have used read, nonsense, sentences, for which speakers received explicit clarification instructions and feedback, while in the child literature, excerpts of real-time conversations were used. Therefore, linguistic samples were not precisely matched. In this study, experiments used various linguistic materials. Experiment 1 used a children's story; experiment 2, nonsense sentences. Four mothers read both types of material in four ways: (1) in "normal" adult speech, (2) in "babytalk," (3) under the clarification instructions used in the "hearing impaired studies" (instructed clear speech) and (4) in (spontaneous) clear speech without instruction. No extra practice or feedback was given. Sentences were presented to 40 normal hearing college students with and without simultaneous masking noise. Results were separately tabulated for content and function words, and analyzed using standard statistical tests. The major finding in the study was individual variation in speaker intelligibility. "Real world" speakers vary in their baseline intelligibility. The four speakers also showed unique patterns of intelligibility as a function of each independent variable. Results were as follows. Nonsense sentences were less intelligible than story sentences. Function words were equal to, or more intelligible than, content words. Babytalk functioned as a clear speech style in story sentences but not nonsense sentences. One of the two clear speech styles was clearer than normal speech in adult-directed clarification. However, which style was clearer depended on interactions among the variables. The individual patterns seemed to result from interactions among demand characteristics, baseline intelligibility, materials, and differences in articulatory flexibility.

Sociological effects on vocal aging: Age related F0 effects in two languages

NASA Astrophysics Data System (ADS)

Nagao, Kyoko

2005-04-01

Listeners can estimate the age of a speaker fairly accurately from their speech (Ptacek and Sander, 1966). It is generally considered that this perception is based on physiologically determined aspects of the speech. However, the degree to which it is due to conventional sociolinguistic aspects of speech is unknown. The current study examines the degree to which fundamental frequency (F0) changes due to advanced aging across two language groups of speakers. It also examines the degree to which the speakers associate these changes with aging in a voice disguising task. Thirty native speakers each of English and Japanese, taken from three age groups, read a target phrase embedded in a carrier sentence in their native language. Each speaker also read the sentence pretending to be 20-years younger or 20-years older than their own age. Preliminary analysis of eighteen Japanese speakers indicates that the mean and maximum F0 values increase when the speakers pretended to be younger than when they pretended to be older. Some previous studies on age perception, however, suggested that F0 has minor effects on listeners' age estimation. The acoustic results will also be discussed in conjunction with the results of the listeners' age estimation of the speakers.

Musical experience facilitates lexical tone processing among Mandarin speakers: Behavioral and neural evidence.

PubMed

Tang, Wei; Xiong, Wen; Zhang, Yu-Xuan; Dong, Qi; Nan, Yun

2016-10-01

Music and speech share many sound attributes. Pitch, as the percept of fundamental frequency, often occupies the center of researchers' attention in studies on the relationship between music and speech. One widely held assumption is that music experience may confer an advantage in speech tone processing. The cross-domain effects of musical training on non-tonal language speakers' linguistic pitch processing have been relatively well established. However, it remains unclear whether musical experience improves the processing of lexical tone for native tone language speakers who actually use lexical tones in their daily communication. Using a passive oddball paradigm, the present study revealed that among Mandarin speakers, musicians demonstrated enlarged electrical responses to lexical tone changes as reflected by the increased mismatch negativity (MMN) amplitudes, as well as faster behavioral discrimination performance compared with age- and IQ-matched nonmusicians. The current results suggest that in spite of the preexisting long-term experience with lexical tones in both musicians and nonmusicians, musical experience can still modulate the cortical plasticity of linguistic tone processing and is associated with enhanced neural processing of speech tones. Our current results thus provide the first electrophysiological evidence supporting the notion that pitch expertise in the music domain may indeed be transferable to the speech domain even for native tone language speakers. Copyright © 2016 Elsevier Ltd. All rights reserved.

Unilateral Hearing Loss: Understanding Speech Recognition and Localization Variability-Implications for Cochlear Implant Candidacy.

PubMed

Firszt, Jill B; Reeder, Ruth M; Holden, Laura K

At a minimum, unilateral hearing loss (UHL) impairs sound localization ability and understanding speech in noisy environments, particularly if the loss is severe to profound. Accompanying the numerous negative consequences of UHL is considerable unexplained individual variability in the magnitude of its effects. Identification of covariables that affect outcome and contribute to variability in UHLs could augment counseling, treatment options, and rehabilitation. Cochlear implantation as a treatment for UHL is on the rise yet little is known about factors that could impact performance or whether there is a group at risk for poor cochlear implant outcomes when hearing is near-normal in one ear. The overall goal of our research is to investigate the range and source of variability in speech recognition in noise and localization among individuals with severe to profound UHL and thereby help determine factors relevant to decisions regarding cochlear implantation in this population. The present study evaluated adults with severe to profound UHL and adults with bilateral normal hearing. Measures included adaptive sentence understanding in diffuse restaurant noise, localization, roving-source speech recognition (words from 1 of 15 speakers in a 140° arc), and an adaptive speech-reception threshold psychoacoustic task with varied noise types and noise-source locations. There were three age-sex-matched groups: UHL (severe to profound hearing loss in one ear and normal hearing in the contralateral ear), normal hearing listening bilaterally, and normal hearing listening unilaterally. Although the normal-hearing-bilateral group scored significantly better and had less performance variability than UHLs on all measures, some UHL participants scored within the range of the normal-hearing-bilateral group on all measures. The normal-hearing participants listening unilaterally had better monosyllabic word understanding than UHLs for words presented on the blocked/deaf side but not the open/hearing side. In contrast, UHLs localized better than the normal-hearing unilateral listeners for stimuli on the open/hearing side but not the blocked/deaf side. This suggests that UHLs had learned strategies for improved localization on the side of the intact ear. The UHL and unilateral normal-hearing participant groups were not significantly different for speech in noise measures. UHL participants with childhood rather than recent hearing loss onset localized significantly better; however, these two groups did not differ for speech recognition in noise. Age at onset in UHL adults appears to affect localization ability differently than understanding speech in noise. Hearing thresholds were significantly correlated with speech recognition for UHL participants but not the other two groups. Auditory abilities of UHLs varied widely and could be explained only in part by hearing threshold levels. Age at onset and length of hearing loss influenced performance on some, but not all measures. Results support the need for a revised and diverse set of clinical measures, including sound localization, understanding speech in varied environments, and careful consideration of functional abilities as individuals with severe to profound UHL are being considered potential cochlear implant candidates.

Increased vocal intensity due to the Lombard effect in speakers with Parkinson's disease: simultaneous laryngeal and respiratory strategies.

PubMed

Stathopoulos, Elaine T; Huber, Jessica E; Richardson, Kelly; Kamphaus, Jennifer; DeCicco, Devan; Darling, Meghan; Fulcher, Katrina; Sussman, Joan E

2014-01-01

The objective of the present study was to investigate whether speakers with hypophonia, secondary to Parkinson's disease (PD), would increases their vocal intensity when speaking in a noisy environment (Lombard effect). The other objective was to examine the underlying laryngeal and respiratory strategies used to increase vocal intensity. Thirty-three participants with PD were included for study. Each participant was fitted with the SpeechVive™ device that played multi-talker babble noise into one ear during speech. Using acoustic, aerodynamic and respiratory kinematic techniques, the simultaneous laryngeal and respiratory mechanisms used to regulate vocal intensity were examined. Significant group results showed that most speakers with PD (26/33) were successful at increasing their vocal intensity when speaking in the condition of multi-talker babble noise. They were able to support their increased vocal intensity and subglottal pressure with combined strategies from both the laryngeal and respiratory mechanisms. Individual speaker analysis indicated that the particular laryngeal and respiratory interactions differed among speakers. The SpeechVive™ device elicited higher vocal intensities from patients with PD. Speakers used different combinations of laryngeal and respiratory physiologic mechanisms to increase vocal intensity, thus suggesting that disease process does not uniformly affect the speech subsystems. Readers will be able to: (1) identify speech characteristics of people with Parkinson's disease (PD), (2) identify typical respiratory strategies for increasing sound pressure level (SPL), (3) identify typical laryngeal strategies for increasing SPL, (4) define the Lombard effect. Copyright © 2014 Elsevier Inc. All rights reserved.

How auditory discontinuities and linguistic experience affect the perception of speech and non-speech in English- and Spanish-speaking listeners

NASA Astrophysics Data System (ADS)

Hay, Jessica F.; Holt, Lori L.; Lotto, Andrew J.; Diehl, Randy L.

2005-04-01

The present study was designed to investigate the effects of long-term linguistic experience on the perception of non-speech sounds in English and Spanish speakers. Research using tone-onset-time (TOT) stimuli, a type of non-speech analogue of voice-onset-time (VOT) stimuli, has suggested that there is an underlying auditory basis for the perception of stop consonants based on a threshold for detecting onset asynchronies in the vicinity of +20 ms. For English listeners, stop consonant labeling boundaries are congruent with the positive auditory discontinuity, while Spanish speakers place their VOT labeling boundaries and discrimination peaks in the vicinity of 0 ms VOT. The present study addresses the question of whether long-term linguistic experience with different VOT categories affects the perception of non-speech stimuli that are analogous in their acoustic timing characteristics. A series of synthetic VOT stimuli and TOT stimuli were created for this study. Using language appropriate labeling and ABX discrimination tasks, labeling boundaries (VOT) and discrimination peaks (VOT and TOT) are assessed for 24 monolingual English speakers and 24 monolingual Spanish speakers. The interplay between language experience and auditory biases are discussed. [Work supported by NIDCD.

Intelligibility of foreign-accented speech: Effects of listening condition, listener age, and listener hearing status

NASA Astrophysics Data System (ADS)

Ferguson, Sarah Hargus

2005-09-01

It is well known that, for listeners with normal hearing, speech produced by non-native speakers of the listener's first language is less intelligible than speech produced by native speakers. Intelligibility is well correlated with listener's ratings of talker comprehensibility and accentedness, which have been shown to be related to several talker factors, including age of second language acquisition and level of similarity between the talker's native and second language phoneme inventories. Relatively few studies have focused on factors extrinsic to the talker. The current project explored the effects of listener and environmental factors on the intelligibility of foreign-accented speech. Specifically, monosyllabic English words previously recorded from two talkers, one a native speaker of American English and the other a native speaker of Spanish, were presented to three groups of listeners (young listeners with normal hearing, elderly listeners with normal hearing, and elderly listeners with hearing impairment; n=20 each) in three different listening conditions (undistorted words in quiet, undistorted words in 12-talker babble, and filtered words in quiet). Data analysis will focus on interactions between talker accent, listener age, listener hearing status, and listening condition. [Project supported by American Speech-Language-Hearing Association AARC Award.

The effects of gated speech on the fluency of speakers who stutter

PubMed Central

Howell, Peter

2007-01-01

It is known that the speech of people who stutter improves when the speaker’s own vocalization is changed while the participant is speaking. One explanation of these effects is the disruptive rhythm hypothesis (DRH). DRH maintains that the manipulated sound only needs to disturb timing to affect speech control. The experiment investigated whether speech that was gated on and off (interrupted) affected the speech control of speakers who stutter. Eight children who stutter read a passage when they heard their voice normally and when the speech was gated. Fluency was enhanced (fewer errors were made and time to read a set passage was reduced) when speech was interrupted in this way. The results support the DRH. PMID:17726328

Switching of auditory attention in "cocktail-party" listening: ERP evidence of cueing effects in younger and older adults.

PubMed

Getzmann, Stephan; Jasny, Julian; Falkenstein, Michael

2017-02-01

Verbal communication in a "cocktail-party situation" is a major challenge for the auditory system. In particular, changes in target speaker usually result in declined speech perception. Here, we investigated whether speech cues indicating a subsequent change in target speaker reduce the costs of switching in younger and older adults. We employed event-related potential (ERP) measures and a speech perception task, in which sequences of short words were simultaneously presented by four speakers. Changes in target speaker were either unpredictable or semantically cued by a word within the target stream. Cued changes resulted in a less decreased performance than uncued changes in both age groups. The ERP analysis revealed shorter latencies in the change-related N400 and late positive complex (LPC) after cued changes, suggesting an acceleration in context updating and attention switching. Thus, both younger and older listeners used semantic cues to prepare changes in speaker setting. Copyright © 2016 Elsevier Inc. All rights reserved.

Interlanguage Variation: A Point Missed?

ERIC Educational Resources Information Center

Tice, Bradley Scott

A study investigated patterns in phonological errors occurring in the speaker's second language in both formal and informal speaking situations. Subjects were three adult learners of English as a second language, including a native Spanish-speaker and two Asians. Their speech was recorded during diagnostic testing (formal speech) and in everyday…

Foreign-Accented Speech Perception Ratings: A Multifactorial Case Study

ERIC Educational Resources Information Center

Kraut, Rachel; Wulff, Stefanie

2013-01-01

Seventy-eight native English speakers rated the foreign-accented speech (FAS) of 24 international students enrolled in an Intensive English programme at a public university in Texas on degree of accent, comprehensibility and communicative ability. Variables considered to potentially impact listeners' ratings were the sex of the speaker, the first…

Spanish Native-Speaker Perception of Accentedness in Learner Speech

ERIC Educational Resources Information Center

Moranski, Kara

2012-01-01

Building upon current research in native-speaker (NS) perception of L2 learner phonology (Zielinski, 2008; Derwing & Munro, 2009), the present investigation analyzed multiple dimensions of NS speech perception in order to achieve a more complete understanding of the specific linguistic elements and attitudinal variables that contribute to…

Variation in /?/ Outcomes in the Speech of U.S

ERIC Educational Resources Information Center

Figueroa, Nicholas James

2017-01-01

This dissertation investigated the speech productions of the implosive -r consonant by U.S.-born Puerto Rican and Dominican Heritage Language Spanish speakers in New York. The following main research questions were addressed: 1) Do heritage language Caribbean Spanish speakers evidence the same variation with the /?/ consonant in the implosive…

Speech sound classification and detection of articulation disorders with support vector machines and wavelets.

PubMed

Georgoulas, George; Georgopoulos, Voula C; Stylios, Chrysostomos D

2006-01-01

This paper proposes a novel integrated methodology to extract features and classify speech sounds with intent to detect the possible existence of a speech articulation disorder in a speaker. Articulation, in effect, is the specific and characteristic way that an individual produces the speech sounds. A methodology to process the speech signal, extract features and finally classify the signal and detect articulation problems in a speaker is presented. The use of support vector machines (SVMs), for the classification of speech sounds and detection of articulation disorders is introduced. The proposed method is implemented on a data set where different sets of features and different schemes of SVMs are tested leading to satisfactory performance.

Tuning time-frequency methods for the detection of metered HF speech

NASA Astrophysics Data System (ADS)

Nelson, Douglas J.; Smith, Lawrence H.

2002-12-01

Speech is metered if the stresses occur at a nearly regular rate. Metered speech is common in poetry, and it can occur naturally in speech, if the speaker is spelling a word or reciting words or numbers from a list. In radio communications, the CQ request, call sign and other codes are frequently metered. In tactical communications and air traffic control, location, heading and identification codes may be metered. Moreover metering may be expected to survive even in HF communications, which are corrupted by noise, interference and mistuning. For this environment, speech recognition and conventional machine-based methods are not effective. We describe Time-Frequency methods which have been adapted successfully to the problem of mitigation of HF signal conditions and detection of metered speech. These methods are based on modeled time and frequency correlation properties of nearly harmonic functions. We derive these properties and demonstrate a performance gain over conventional correlation and spectral methods. Finally, in addressing the problem of HF single sideband (SSB) communications, the problems of carrier mistuning, interfering signals, such as manual Morse, and fast automatic gain control (AGC) must be addressed. We demonstrate simple methods which may be used to blindly mitigate mistuning and narrowband interference, and effectively invert the fast automatic gain function.

Analysis of Acoustic Features in Speakers with Cognitive Disorders and Speech Impairments

NASA Astrophysics Data System (ADS)

Saz, Oscar; Simón, Javier; Rodríguez, W. Ricardo; Lleida, Eduardo; Vaquero, Carlos

2009-12-01

This work presents the results in the analysis of the acoustic features (formants and the three suprasegmental features: tone, intensity and duration) of the vowel production in a group of 14 young speakers suffering different kinds of speech impairments due to physical and cognitive disorders. A corpus with unimpaired children's speech is used to determine the reference values for these features in speakers without any kind of speech impairment within the same domain of the impaired speakers; this is 57 isolated words. The signal processing to extract the formant and pitch values is based on a Linear Prediction Coefficients (LPCs) analysis of the segments considered as vowels in a Hidden Markov Model (HMM) based Viterbi forced alignment. Intensity and duration are also based in the outcome of the automated segmentation. As main conclusion of the work, it is shown that intelligibility of the vowel production is lowered in impaired speakers even when the vowel is perceived as correct by human labelers. The decrease in intelligibility is due to a 30% of increase in confusability in the formants map, a reduction of 50% in the discriminative power in energy between stressed and unstressed vowels and to a 50% increase of the standard deviation in the length of the vowels. On the other hand, impaired speakers keep good control of tone in the production of stressed and unstressed vowels.

Noise Reduction with Microphone Arrays for Speaker Identification

DOE Office of Scientific and Technical Information (OSTI.GOV)

Cohen, Z

Reducing acoustic noise in audio recordings is an ongoing problem that plagues many applications. This noise is hard to reduce because of interfering sources and non-stationary behavior of the overall background noise. Many single channel noise reduction algorithms exist but are limited in that the more the noise is reduced; the more the signal of interest is distorted due to the fact that the signal and noise overlap in frequency. Specifically acoustic background noise causes problems in the area of speaker identification. Recording a speaker in the presence of acoustic noise ultimately limits the performance and confidence of speaker identificationmore » algorithms. In situations where it is impossible to control the environment where the speech sample is taken, noise reduction filtering algorithms need to be developed to clean the recorded speech of background noise. Because single channel noise reduction algorithms would distort the speech signal, the overall challenge of this project was to see if spatial information provided by microphone arrays could be exploited to aid in speaker identification. The goals are: (1) Test the feasibility of using microphone arrays to reduce background noise in speech recordings; (2) Characterize and compare different multichannel noise reduction algorithms; (3) Provide recommendations for using these multichannel algorithms; and (4) Ultimately answer the question - Can the use of microphone arrays aid in speaker identification?« less

A positron emission tomography study of the neural basis of informational and energetic masking effects in speech perception

NASA Astrophysics Data System (ADS)

Scott, Sophie K.; Rosen, Stuart; Wickham, Lindsay; Wise, Richard J. S.

2004-02-01

Positron emission tomography (PET) was used to investigate the neural basis of the comprehension of speech in unmodulated noise (``energetic'' masking, dominated by effects at the auditory periphery), and when presented with another speaker (``informational'' masking, dominated by more central effects). Each type of signal was presented at four different signal-to-noise ratios (SNRs) (+3, 0, -3, -6 dB for the speech-in-speech, +6, +3, 0, -3 dB for the speech-in-noise), with listeners instructed to listen for meaning to the target speaker. Consistent with behavioral studies, there was SNR-dependent activation associated with the comprehension of speech in noise, with no SNR-dependent activity for the comprehension of speech-in-speech (at low or negative SNRs). There was, in addition, activation in bilateral superior temporal gyri which was associated with the informational masking condition. The extent to which this activation of classical ``speech'' areas of the temporal lobes might delineate the neural basis of the informational masking is considered, as is the relationship of these findings to the interfering effects of unattended speech and sound on more explicit working memory tasks. This study is a novel demonstration of candidate neural systems involved in the perception of speech in noisy environments, and of the processing of multiple speakers in the dorso-lateral temporal lobes.

Word Durations in Non-Native English

PubMed Central

Baker, Rachel E.; Baese-Berk, Melissa; Bonnasse-Gahot, Laurent; Kim, Midam; Van Engen, Kristin J.; Bradlow, Ann R.

2010-01-01

In this study, we compare the effects of English lexical features on word duration for native and non-native English speakers and for non-native speakers with different L1s and a range of L2 experience. We also examine whether non-native word durations lead to judgments of a stronger foreign accent. We measured word durations in English paragraphs read by 12 American English (AE), 20 Korean, and 20 Chinese speakers. We also had AE listeners rate the `accentedness' of these non-native speakers. AE speech had shorter durations, greater within-speaker word duration variance, greater reduction of function words, and less between-speaker variance than non-native speech. However, both AE and non-native speakers showed sensitivity to lexical predictability by reducing second mentions and high frequency words. Non-native speakers with more native-like word durations, greater within-speaker word duration variance, and greater function word reduction were perceived as less accented. Overall, these findings identify word duration as an important and complex feature of foreign-accented English. PMID:21516172

Neural networks to classify speaker independent isolated words recorded in radio car environments

NASA Astrophysics Data System (ADS)

Alippi, C.; Simeoni, M.; Torri, V.

1993-02-01

Many applications, in particular the ones requiring nonlinear signal processing, have proved Artificial Neural Networks (ANN's) to be invaluable tools for model free estimation. The classifying abilities of ANN's are addressed by testing their performance in a speaker independent word recognition application. A real world case requiring implementation of compact integrated devices is taken into account: the classification of isolated words in radio car environment. A multispeaker database of isolated words was recorded in different environments. Data were first processed to determinate the boundaries of each word and then to extract speech features, the latter accomplished by using cepstral coefficient representation, log area ratios and filters bank techniques. Multilayered perceptron and adaptive vector quantization neural paradigms were tested to find a reasonable compromise between performances and network simplicity, fundamental requirement for the implementation of compact real time running neural devices.

Attentional influences on functional mapping of speech sounds in human auditory cortex

PubMed Central

Obleser, Jonas; Elbert, Thomas; Eulitz, Carsten

2004-01-01

Background The speech signal contains both information about phonological features such as place of articulation and non-phonological features such as speaker identity. These are different aspects of the 'what'-processing stream (speaker vs. speech content), and here we show that they can be further segregated as they may occur in parallel but within different neural substrates. Subjects listened to two different vowels, each spoken by two different speakers. During one block, they were asked to identify a given vowel irrespectively of the speaker (phonological categorization), while during the other block the speaker had to be identified irrespectively of the vowel (speaker categorization). Auditory evoked fields were recorded using 148-channel magnetoencephalography (MEG), and magnetic source imaging was obtained for 17 subjects. Results During phonological categorization, a vowel-dependent difference of N100m source location perpendicular to the main tonotopic gradient replicated previous findings. In speaker categorization, the relative mapping of vowels remained unchanged but sources were shifted towards more posterior and more superior locations. Conclusions These results imply that the N100m reflects the extraction of abstract invariants from the speech signal. This part of the processing is accomplished in auditory areas anterior to AI, which are part of the auditory 'what' system. This network seems to include spatially separable modules for identifying the phonological information and for associating it with a particular speaker that are activated in synchrony but within different regions, suggesting that the 'what' processing can be more adequately modeled by a stream of parallel stages. The relative activation of the parallel processing stages can be modulated by attentional or task demands. PMID:15268765

Sound Localization and Speech Perception in Noise of Pediatric Cochlear Implant Recipients: Bimodal Fitting Versus Bilateral Cochlear Implants.

PubMed

Choi, Ji Eun; Moon, Il Joon; Kim, Eun Yeon; Park, Hee-Sung; Kim, Byung Kil; Chung, Won-Ho; Cho, Yang-Sun; Brown, Carolyn J; Hong, Sung Hwa

The aim of this study was to compare binaural performance of auditory localization task and speech perception in babble measure between children who use a cochlear implant (CI) in one ear and a hearing aid (HA) in the other (bimodal fitting) and those who use bilateral CIs. Thirteen children (mean age ± SD = 10 ± 2.9 years) with bilateral CIs and 19 children with bimodal fitting were recruited to participate. Sound localization was assessed using a 13-loudspeaker array in a quiet sound-treated booth. Speakers were placed in an arc from -90° azimuth to +90° azimuth (15° interval) in horizontal plane. To assess the accuracy of sound location identification, we calculated the absolute error in degrees between the target speaker and the response speaker during each trial. The mean absolute error was computed by dividing the sum of absolute errors by the total number of trials. We also calculated the hemifield identification score to reflect the accuracy of right/left discrimination. Speech-in-babble perception was also measured in the sound field using target speech presented from the front speaker. Eight-talker babble was presented in the following four different listening conditions: from the front speaker (0°), from one of the two side speakers (+90° or -90°), from both side speakers (±90°). Speech, spatial, and quality questionnaire was administered. When the two groups of children were directly compared with each other, there was no significant difference in localization accuracy ability or hemifield identification score under binaural condition. Performance in speech perception test was also similar to each other under most babble conditions. However, when the babble was from the first device side (CI side for children with bimodal stimulation or first CI side for children with bilateral CIs), speech understanding in babble by bilateral CI users was significantly better than that by bimodal listeners. Speech, spatial, and quality scores were comparable with each other between the two groups. Overall, the binaural performance was similar to each other between children who are fit with two CIs (CI + CI) and those who use bimodal stimulation (HA + CI) in most conditions. However, the bilateral CI group showed better speech perception than the bimodal CI group when babble was from the first device side (first CI side for bilateral CI users or CI side for bimodal listeners). Therefore, if bimodal performance is significantly below the mean bilateral CI performance on speech perception in babble, these results suggest that a child should be considered to transit from bimodal stimulation to bilateral CIs.

Prediction and constraint in audiovisual speech perception

PubMed Central

Peelle, Jonathan E.; Sommers, Mitchell S.

2015-01-01

During face-to-face conversational speech listeners must efficiently process a rapid and complex stream of multisensory information. Visual speech can serve as a critical complement to auditory information because it provides cues to both the timing of the incoming acoustic signal (the amplitude envelope, influencing attention and perceptual sensitivity) and its content (place and manner of articulation, constraining lexical selection). Here we review behavioral and neurophysiological evidence regarding listeners' use of visual speech information. Multisensory integration of audiovisual speech cues improves recognition accuracy, particularly for speech in noise. Even when speech is intelligible based solely on auditory information, adding visual information may reduce the cognitive demands placed on listeners through increasing precision of prediction. Electrophysiological studies demonstrate oscillatory cortical entrainment to speech in auditory cortex is enhanced when visual speech is present, increasing sensitivity to important acoustic cues. Neuroimaging studies also suggest increased activity in auditory cortex when congruent visual information is available, but additionally emphasize the involvement of heteromodal regions of posterior superior temporal sulcus as playing a role in integrative processing. We interpret these findings in a framework of temporally-focused lexical competition in which visual speech information affects auditory processing to increase sensitivity to auditory information through an early integration mechanism, and a late integration stage that incorporates specific information about a speaker's articulators to constrain the number of possible candidates in a spoken utterance. Ultimately it is words compatible with both auditory and visual information that most strongly determine successful speech perception during everyday listening. Thus, audiovisual speech perception is accomplished through multiple stages of integration, supported by distinct neuroanatomical mechanisms. PMID:25890390

Interactive Voice Technology: Variations in the Vocal Utterances of Speakers Performing a Stress-Inducing Task,

DTIC Science & Technology

1983-08-16

34. " .. ,,,,.-j.Aid-is.. ;,,i . -i.t . "’" ’, V ,1 5- 4. 3- kHz 2-’ r 1 r s ’.:’ BOGEY 5D 0 S BOGEY 12D Figure 10. Spectrograms of two versions of the word...MF5852801B 0001 Reviewed by Approved and Released by Ashton Graybiel, M.D. Captain W. M. Houk , MC, USN Chief Scientific Advisor Commanding Officer 16 August...incorporating knowledge about these changes into speech recognition systems. i A J- I. . S , .4, ... ..’-° -- -iii l - - .- - i- . .. " •- - i ,f , i

Visual input enhances selective speech envelope tracking in auditory cortex at a "cocktail party".

PubMed

Zion Golumbic, Elana; Cogan, Gregory B; Schroeder, Charles E; Poeppel, David

2013-01-23

Our ability to selectively attend to one auditory signal amid competing input streams, epitomized by the "Cocktail Party" problem, continues to stimulate research from various approaches. How this demanding perceptual feat is achieved from a neural systems perspective remains unclear and controversial. It is well established that neural responses to attended stimuli are enhanced compared with responses to ignored ones, but responses to ignored stimuli are nonetheless highly significant, leading to interference in performance. We investigated whether congruent visual input of an attended speaker enhances cortical selectivity in auditory cortex, leading to diminished representation of ignored stimuli. We recorded magnetoencephalographic signals from human participants as they attended to segments of natural continuous speech. Using two complementary methods of quantifying the neural response to speech, we found that viewing a speaker's face enhances the capacity of auditory cortex to track the temporal speech envelope of that speaker. This mechanism was most effective in a Cocktail Party setting, promoting preferential tracking of the attended speaker, whereas without visual input no significant attentional modulation was observed. These neurophysiological results underscore the importance of visual input in resolving perceptual ambiguity in a noisy environment. Since visual cues in speech precede the associated auditory signals, they likely serve a predictive role in facilitating auditory processing of speech, perhaps by directing attentional resources to appropriate points in time when to-be-attended acoustic input is expected to arrive.

Perception and Production of Prosody by Speakers with Autism Spectrum Disorders

ERIC Educational Resources Information Center

Paul, Rhea; Augustyn, Amy; Klin, Ami; Volkmar, Fred R.

2005-01-01

Speakers with autism spectrum disorders (ASD) show difficulties in suprasegmental aspects of speech production, or "prosody," those aspects of speech that accompany words and sentences and create what is commonly called "tone of voice." However, little is known about the perception of prosody, or about the specific aspects of…

Linguistic Flexibility Modulates Speech Planning for Causative Motion Events: A Cross-Linguistic Study of Mandarin and English

ERIC Educational Resources Information Center

Zheng, Chun

2017-01-01

Producing a sensible utterance requires speakers to select conceptual content, lexical items, and syntactic structures almost instantaneously during speech planning. Each language offers its speakers flexibility in the selection of lexical and syntactic options to talk about the same scenarios involving movement. Languages also vary typologically…

Long-Term Speech Results of Cleft Palate Speakers with Marginal Velopharyngeal Competence.

ERIC Educational Resources Information Center

Hardin, Mary A.; And Others

1990-01-01

This study of the longitudinal speech performance of 48 cleft palate speakers with marginal velopharyngeal competence, from age 6 to adolescence, found that the adolescent subjects' velopharyngeal status could be predicted based on 2 variables at age 6: the severity ratings of articulation defectiveness and nasality. (Author/JDD)

The Listener: No Longer the Silent Partner in Reduced Intelligibility

ERIC Educational Resources Information Center

Zielinski, Beth W.

2008-01-01

In this study I investigate the impact of different characteristics of the L2 speech signal on the intelligibility of L2 speakers of English to native listeners. Three native listeners were observed and questioned as they orthographically transcribed utterances taken from connected conversational speech produced by three L2 speakers from different…

Motor excitability during visual perception of known and unknown spoken languages.

PubMed

Swaminathan, Swathi; MacSweeney, Mairéad; Boyles, Rowan; Waters, Dafydd; Watkins, Kate E; Möttönen, Riikka

2013-07-01

It is possible to comprehend speech and discriminate languages by viewing a speaker's articulatory movements. Transcranial magnetic stimulation studies have shown that viewing speech enhances excitability in the articulatory motor cortex. Here, we investigated the specificity of this enhanced motor excitability in native and non-native speakers of English. Both groups were able to discriminate between speech movements related to a known (i.e., English) and unknown (i.e., Hebrew) language. The motor excitability was higher during observation of a known language than an unknown language or non-speech mouth movements, suggesting that motor resonance is enhanced specifically during observation of mouth movements that convey linguistic information. Surprisingly, however, the excitability was equally high during observation of a static face. Moreover, the motor excitability did not differ between native and non-native speakers. These findings suggest that the articulatory motor cortex processes several kinds of visual cues during speech communication. Crown Copyright © 2013. Published by Elsevier Inc. All rights reserved.

Does dynamic information about the speaker's face contribute to semantic speech processing? ERP evidence.

PubMed

Hernández-Gutiérrez, David; Abdel Rahman, Rasha; Martín-Loeches, Manuel; Muñoz, Francisco; Schacht, Annekathrin; Sommer, Werner

2018-07-01

Face-to-face interactions characterize communication in social contexts. These situations are typically multimodal, requiring the integration of linguistic auditory input with facial information from the speaker. In particular, eye gaze and visual speech provide the listener with social and linguistic information, respectively. Despite the importance of this context for an ecological study of language, research on audiovisual integration has mainly focused on the phonological level, leaving aside effects on semantic comprehension. Here we used event-related potentials (ERPs) to investigate the influence of facial dynamic information on semantic processing of connected speech. Participants were presented with either a video or a still picture of the speaker, concomitant to auditory sentences. Along three experiments, we manipulated the presence or absence of the speaker's dynamic facial features (mouth and eyes) and compared the amplitudes of the semantic N400 elicited by unexpected words. Contrary to our predictions, the N400 was not modulated by dynamic facial information; therefore, semantic processing seems to be unaffected by the speaker's gaze and visual speech. Even though, during the processing of expected words, dynamic faces elicited a long-lasting late posterior positivity compared to the static condition. This effect was significantly reduced when the mouth of the speaker was covered. Our findings may indicate an increase of attentional processing to richer communicative contexts. The present findings also demonstrate that in natural communicative face-to-face encounters, perceiving the face of a speaker in motion provides supplementary information that is taken into account by the listener, especially when auditory comprehension is non-demanding. Copyright © 2018 Elsevier Ltd. All rights reserved.

Speaker normalization and adaptation using second-order connectionist networks.

PubMed

Watrous, R L

1993-01-01

A method for speaker normalization and adaption using connectionist networks is developed. A speaker-specific linear transformation of observations of the speech signal is computed using second-order network units. Classification is accomplished by a multilayer feedforward network that operates on the normalized speech data. The network is adapted for a new talker by modifying the transformation parameters while leaving the classifier fixed. This is accomplished by backpropagating classification error through the classifier to the second-order transformation units. This method was evaluated for the classification of ten vowels for 76 speakers using the first two formant values of the Peterson-Barney data. The results suggest that rapid speaker adaptation resulting in high classification accuracy can be accomplished by this method.

Audiovisual perceptual learning with multiple speakers.

PubMed

Mitchel, Aaron D; Gerfen, Chip; Weiss, Daniel J

2016-05-01

One challenge for speech perception is between-speaker variability in the acoustic parameters of speech. For example, the same phoneme (e.g. the vowel in "cat") may have substantially different acoustic properties when produced by two different speakers and yet the listener must be able to interpret these disparate stimuli as equivalent. Perceptual tuning, the use of contextual information to adjust phonemic representations, may be one mechanism that helps listeners overcome obstacles they face due to this variability during speech perception. Here we test whether visual contextual cues to speaker identity may facilitate the formation and maintenance of distributional representations for individual speakers, allowing listeners to adjust phoneme boundaries in a speaker-specific manner. We familiarized participants to an audiovisual continuum between /aba/ and /ada/. During familiarization, the "b-face" mouthed /aba/ when an ambiguous token was played, while the "D-face" mouthed /ada/. At test, the same ambiguous token was more likely to be identified as /aba/ when paired with a stilled image of the "b-face" than with an image of the "D-face." This was not the case in the control condition when the two faces were paired equally with the ambiguous token. Together, these results suggest that listeners may form speaker-specific phonemic representations using facial identity cues.

Strength of German accent under altered auditory feedback

PubMed Central

HOWELL, PETER; DWORZYNSKI, KATHARINA

2007-01-01

Borden’s (1979, 1980) hypothesis that speakers with vulnerable speech systems rely more heavily on feedback monitoring than do speakers with less vulnerable systems was investigated. The second language (L2) of a speaker is vulnerable, in comparison with the native language, so alteration to feedback should have a detrimental effect on it, according to this hypothesis. Here, we specifically examined whether altered auditory feedback has an effect on accent strength when speakers speak L2. There were three stages in the experiment. First, 6 German speakers who were fluent in English (their L2) were recorded under six conditions—normal listening, amplified voice level, voice shifted in frequency, delayed auditory feedback, and slowed and accelerated speech rate conditions. Second, judges were trained to rate accent strength. Training was assessed by whether it was successful in separating German speakers speaking English from native English speakers, also speaking English. In the final stage, the judges ranked recordings of each speaker from the first stage as to increasing strength of German accent. The results show that accents were more pronounced under frequency-shifted and delayed auditory feedback conditions than under normal or amplified feedback conditions. Control tests were done to ensure that listeners were judging accent, rather than fluency changes caused by altered auditory feedback. The findings are discussed in terms of Borden’s hypothesis and other accounts about why altered auditory feedback disrupts speech control. PMID:11414137

Inferring speaker attributes in adductor spasmodic dysphonia: ratings from unfamiliar listeners.

PubMed

Isetti, Derek; Xuereb, Linnea; Eadie, Tanya L

2014-05-01

To determine whether unfamiliar listeners' perceptions of speakers with adductor spasmodic dysphonia (ADSD) differ from control speakers on the parameters of relative age, confidence, tearfulness, and vocal effort and are related to speaker-rated vocal effort or voice-specific quality of life. Twenty speakers with ADSD (including 6 speakers with ADSD plus tremor) and 20 age- and sex-matched controls provided speech recordings, completed a voice-specific quality-of-life instrument (Voice Handicap Index; Jacobson et al., 1997), and rated their own vocal effort. Twenty listeners evaluated speech samples for relative age, confidence, tearfulness, and vocal effort using rating scales. Listeners judged speakers with ADSD as sounding significantly older, less confident, more tearful, and more effortful than control speakers (p < .01). Increased vocal effort was strongly associated with decreased speaker confidence (rs = .88-.89) and sounding more tearful (rs = .83-.85). Self-rated speaker effort was moderately related (rs = .45-.52) to listener impressions. Listeners' perceptions of confidence and tearfulness were also moderately associated with higher Voice Handicap Index scores (rs = .65-.70). Unfamiliar listeners judge speakers with ADSD more negatively than control speakers, with judgments extending beyond typical clinical measures. The results have implications for counseling and understanding the psychosocial effects of ADSD.

Eye’m talking to you: speakers’ gaze direction modulates co-speech gesture processing in the right MTG

PubMed Central

Toni, Ivan; Hagoort, Peter; Kelly, Spencer D.; Özyürek, Aslı

2015-01-01

Recipients process information from speech and co-speech gestures, but it is currently unknown how this processing is influenced by the presence of other important social cues, especially gaze direction, a marker of communicative intent. Such cues may modulate neural activity in regions associated either with the processing of ostensive cues, such as eye gaze, or with the processing of semantic information, provided by speech and gesture. Participants were scanned (fMRI) while taking part in triadic communication involving two recipients and a speaker. The speaker uttered sentences that were and were not accompanied by complementary iconic gestures. Crucially, the speaker alternated her gaze direction, thus creating two recipient roles: addressed (direct gaze) vs unaddressed (averted gaze) recipient. The comprehension of Speech&Gesture relative to SpeechOnly utterances recruited middle occipital, middle temporal and inferior frontal gyri, bilaterally. The calcarine sulcus and posterior cingulate cortex were sensitive to differences between direct and averted gaze. Most importantly, Speech&Gesture utterances, but not SpeechOnly utterances, produced additional activity in the right middle temporal gyrus when participants were addressed. Marking communicative intent with gaze direction modulates the processing of speech–gesture utterances in cerebral areas typically associated with the semantic processing of multi-modal communicative acts. PMID:24652857

The influence of ambient speech on adult speech productions through unintentional imitation.

PubMed

Delvaux, Véronique; Soquet, Alain

2007-01-01

This paper deals with the influence of ambient speech on individual speech productions. A methodological framework is defined to gather the experimental data necessary to feed computer models simulating self-organisation in phonological systems. Two experiments were carried out. Experiment 1 was run on French native speakers from two regiolects of Belgium: two from Liège and two from Brussels. When exposed to the way of speaking of the other regiolect via loudspeakers, the speakers of one regiolect produced vowels that were significantly different from their typical realisations, and significantly closer to the way of speaking specific of the other regiolect. Experiment 2 achieved a replication of the results for 8 Mons speakers hearing a Liège speaker. A significant part of the imitative effect remained up to 10 min after the end of the exposure to the other regiolect productions. As a whole, the results suggest that: (i) imitation occurs automatically and unintentionally, (ii) the modified realisations leave a memory trace, in which case the mechanism may be better defined as 'mimesis' than as 'imitation'. The potential effects of multiple imitative speech interactions on sound change are discussed in this paper, as well as the implications for a general theory of phonetic implementation and phonetic representation.

Perception and analysis of Spanish accents in English speech

NASA Astrophysics Data System (ADS)

Chism, Cori; Lass, Norman

2002-05-01

The purpose of the present study was to determine what relates most closely to the degree of perceived foreign accent in the English speech of native Spanish speakers: intonation, vowel length, stress, voice onset time (VOT), or segmental accuracy. Nineteen native English speaking listeners rated speech samples from 7 native English speakers and 15 native Spanish speakers for comprehensibility and degree of foreign accent. The speech samples were analyzed spectrographically and perceptually to obtain numerical values for each variable. Correlation coefficients were computed to determine the relationship beween these values and the average foreign accent scores. Results showed that the average foreign accent scores were statistically significantly correlated with three variables: the length of stressed vowels (r=-0.48, p=0.05), voice onset time (r =-0.62, p=0.01), and segmental accuracy (r=0.92, p=0.001). Implications of these findings and suggestions for future research are discussed.

The character of scientists in the Nobel Prize speeches.

PubMed

Condit, Celeste M

2018-05-01

This essay describes the ethos (i.e. the character projected to specific audiences) of the 25 Nobel Lectures in Physics, Chemistry, and Physiology or Medicine given in 2013-2015 and the 15 Presentation Speeches given at the Nobel Banquets between 2011 and 2015. A thematically focused qualitative analysis grounded in theories of epideictic discourse indicates the Nobel speakers demonstrated a range of strategies for and degrees of success in negotiating the tensions created by the implicit demands of ceremonial speeches, the scientific emphasis on didactic style and research content, and the different potential audiences (scientific experts and interested publics). Relatively few speeches explicitly displayed goodwill toward humanity instead of primarily toward the scientific community. Some speakers emphasized qualities of goodness in line with social values shared by broad audiences, but some reinforced stereotypes of scientists as anti-social. Speakers were variable in their ability to bridge the substantial gaps in resources for shared good sense.

Hybridizing Conversational and Clear Speech to Investigate the Source of Increased Intelligibility in Speakers with Parkinson's Disease

ERIC Educational Resources Information Center

Tjaden, Kris; Kain, Alexander; Lam, Jennifer

2014-01-01

Purpose: A speech analysis-resynthesis paradigm was used to investigate segmental and suprasegmental acoustic variables explaining intelligibility variation for 2 speakers with Parkinson's disease (PD). Method: Sentences were read in conversational and clear styles. Acoustic characteristics from clear sentences were extracted and applied to…

Interlingual Influence in Bilingual Speech: Cognate Status Effect in a Continuum of Bilingualism

ERIC Educational Resources Information Center

Amengual, Mark

2012-01-01

The present study investigates voice onset times (VOTs) to determine if cognates enhance the cross-language phonetic influences in the speech production of a range of Spanish-English bilinguals: Spanish heritage speakers, English heritage speakers, advanced L2 Spanish learners, and advanced L2 English learners. To answer this question, lexical…

Priming of Non-Speech Vocalizations in Male Adults: The Influence of the Speaker's Gender

ERIC Educational Resources Information Center

Fecteau, Shirley; Armony, Jorge L.; Joanette, Yves; Belin, Pascal

2004-01-01

Previous research reported a priming effect for voices. However, the type of information primed is still largely unknown. In this study, we examined the influence of speaker's gender and emotional category of the stimulus on priming of non-speech vocalizations in 10 male participants, who performed a gender identification task. We found a…

When "No" Means "Yes": Agreeing and Disagreeing in Indian English Discourse.

ERIC Educational Resources Information Center

Valentine, Tamara M.

This study examined the speech act of agreement and disagreement in the ordinary conversation of English-speakers in India. Data were collected in natural speech elicited from educated, bilingual speakers in cross-sex and same-sex conversations in a range of formal and informal settings. Subjects' ages ranged from 19 to about 60. Five agreement…

Speech and Prosody Characteristics of Adolescents and Adults with High-Functioning Autism and Asperger Syndrome.

ERIC Educational Resources Information Center

Shriberg, Lawrence D.; Paul, Rhea; McSweeny, Jane L.; Klin, Ami; Cohen, Donald J.; Volkmar, Fred R.

2001-01-01

This study compared the speech and prosody-voice profiles for 30 male speakers with either high-functioning autism (HFA) or Asperger syndrome (AS), and 53 typically developing male speakers. Both HFA and AS groups had more residual articulation distortion errors and utterances coded as inappropriate for phrasing, stress, and resonance. AS speakers…

Effects of Speech Practice on Fast Mapping in Monolingual and Bilingual Speakers

ERIC Educational Resources Information Center

Kan, Pui Fong; Sadagopan, Neeraja; Janich, Lauren; Andrade, Marixa

2014-01-01

Purpose: This study examines the effects of the levels of speech practice on fast mapping in monolingual and bilingual speakers. Method: Participants were 30 English-speaking monolingual and 30 Spanish-English bilingual young adults. Each participant was randomly assigned to 1 of 3 practice conditions prior to the fast-mapping task: (a) intensive…

Sinteiseoir 1.0: A Multidialectical TTS Application for Irish

ERIC Educational Resources Information Center

Mac Lochlainn, Micheal

2010-01-01

This paper details the development of a multidialectical text-to-speech (TTS) application, "Sinteiseoir," for the Irish language. This work is being carried out in the context of Irish as a lesser-used language, where learners and other L2 speakers have limited direct exposure to L1 speakers and speech communities, and where native sound…

Effects of Visual Information on Intelligibility of Open and Closed Class Words in Predictable Sentences Produced by Speakers with Dysarthria

ERIC Educational Resources Information Center

Hustad, Katherine C.; Dardis, Caitlin M.; Mccourt, Kelly A.

2007-01-01

This study examined the independent and interactive effects of visual information and linguistic class of words on intelligibility of dysarthric speech. Seven speakers with dysarthria participated in the study, along with 224 listeners who transcribed speech samples in audiovisual (AV) or audio-only (AO) listening conditions. Orthographic…

Cross-Language Activation Begins during Speech Planning and Extends into Second Language Speech

ERIC Educational Resources Information Center

Jacobs, April; Fricke, Melinda; Kroll, Judith F.

2016-01-01

Three groups of native English speakers named words aloud in Spanish, their second language (L2). Intermediate proficiency learners in a classroom setting (Experiment 1) and in a domestic immersion program (Experiment 2) were compared to a group of highly proficient English-Spanish speakers. All three groups named cognate words more quickly and…

The Interaction of Lexical Characteristics and Speech Production in Parkinson's Disease.

PubMed

Chiu, Yi-Fang; Forrest, Karen

2017-01-01

This study sought to investigate the interaction of speech movement execution with higher order lexical parameters. The authors examined how lexical characteristics affect speech output in individuals with Parkinson's disease (PD) and healthy control (HC) speakers. Twenty speakers with PD and 12 healthy speakers read sentences with target words that varied in word frequency and neighborhood density. The formant transitions (F2 slopes) of the diphthongs in the target words were compared across lexical categories between PD and HC groups. Both groups of speakers produced steeper F2 slopes for the diphthongs in less frequent words and words from sparse neighborhoods. The magnitude of the increase in F2 slopes was significantly less in the PD than HC group. The lexical effect on the F2 slope differed among the diphthongs and between the 2 groups. PD and healthy speakers varied their acoustic output on the basis of word frequency and neighborhood density. F2 slope variations can be traced to higher level lexical differences. This lexical effect on articulation, however, appears to be constrained by PD.

The persuasiveness of synthetic speech versus human speech.

PubMed

Stern, S E; Mullennix, J W; Dyson, C; Wilson, S J

1999-12-01

Is computer-synthesized speech as persuasive as the human voice when presenting an argument? After completing an attitude pretest, 193 participants were randomly assigned to listen to a persuasive appeal under three conditions: a high-quality synthesized speech system (DECtalk Express), a low-quality synthesized speech system (Monologue), and a tape recording of a human voice. Following the appeal, participants completed a posttest attitude survey and a series of questionnaires designed to assess perceptions of speech qualities, perceptions of the speaker, and perceptions of the message. The human voice was generally perceived more favorably than the computer-synthesized voice, and the speaker was perceived more favorably when the voice was a human voice than when it was computer synthesized. There was, however, no evidence that computerized speech, as compared with the human voice, affected persuasion or perceptions of the message. Actual or potential applications of this research include issues that should be considered when designing synthetic speech systems.

Comparison of the South African Spondaic and CID W-1 wordlists for measuring speech recognition threshold

PubMed Central

Soer, Maggi; Pottas, Lidia

2015-01-01

Background The home language of most audiologists in South Africa is either English or Afrikaans, whereas most South Africans speak an African language as their home language. The use of an English wordlist, the South African Spondaic (SAS) wordlist, which is familiar to the English Second Language (ESL) population, was developed by the author for testing the speech recognition threshold (SRT) of ESL speakers. Objectives The aim of this study was to compare the pure-tone average (PTA)/SRT correlation results of ESL participants when using the SAS wordlist (list A) and the CID W-1 spondaic wordlist (list B – less familiar; list C – more familiar CID W-1 words). Method A mixed-group correlational, quantitative design was adopted. PTA and SRT measurements were compared for lists A, B and C for 101 (197 ears) ESL participants with normal hearing or a minimal hearing loss (<26 dBHL; mean age 33.3). Results The Pearson correlation analysis revealed a strong PTA/SRT correlation when using list A (right 0.65; left 0.58) and list C (right 0.63; left 0.56). The use of list B revealed weak correlations (right 0.30; left 0.32). Paired sample t-tests indicated a statistically significantly stronger PTA/SRT correlation when list A was used, rather than list B or list C, at a 95% level of confidence. Conclusions The use of the SAS wordlist yielded a stronger PTA/SRT correlation than the use of the CID W-1 wordlist, when performing SRT testing on South African ESL speakers with normal hearing, or minimal hearing loss (<26 dBHL). PMID:26304218

Action Unit Models of Facial Expression of Emotion in the Presence of Speech

PubMed Central

Shah, Miraj; Cooper, David G.; Cao, Houwei; Gur, Ruben C.; Nenkova, Ani; Verma, Ragini

2014-01-01

Automatic recognition of emotion using facial expressions in the presence of speech poses a unique challenge because talking reveals clues for the affective state of the speaker but distorts the canonical expression of emotion on the face. We introduce a corpus of acted emotion expression where speech is either present (talking) or absent (silent). The corpus is uniquely suited for analysis of the interplay between the two conditions. We use a multimodal decision level fusion classifier to combine models of emotion from talking and silent faces as well as from audio to recognize five basic emotions: anger, disgust, fear, happy and sad. Our results strongly indicate that emotion prediction in the presence of speech from action unit facial features is less accurate when the person is talking. Modeling talking and silent expressions separately and fusing the two models greatly improves accuracy of prediction in the talking setting. The advantages are most pronounced when silent and talking face models are fused with predictions from audio features. In this multi-modal prediction both the combination of modalities and the separate models of talking and silent facial expression of emotion contribute to the improvement. PMID:25525561

Using Flanagan's phase vocoder to improve cochlear implant performance

NASA Astrophysics Data System (ADS)

Zeng, Fan-Gang

2004-10-01

The cochlear implant has restored partial hearing to more than 100000 deaf people worldwide, allowing the average user to talk on the telephone in quiet environment. However, significant difficulty still remains for speech recognition in noise, music perception, and tonal language understanding. This difficulty may be related to speech processing strategies in current cochlear implants that emphasized the extraction and encoding of the temporal envelope while ignoring the temporal fine structure in speech sounds. A novel strategy was developed based on Flanagan's phase vocoder [Flanagan and Golden, Bell Syst. Tech. 45, 1493-1509 (1966)], in which frequency modulation was extracted from the temporal fine structure and then added to amplitude modulation in the current cochlear implants. Acoustic simulation results showed that amplitude and frequency modulation contributed complementarily to speech perception with amplitude modulation contributing mainly to intelligibility whereas frequency modulation contributed to speaker identification and auditory grouping. The results also showed that the novel strategy significantly improved cochlear implant performance under realistic listening situations. Overall, the present result demonstrated that Flanagan's classic work on phase vocoder still shed insight on current problems of both theoretical and practical importance. [Work supported by NIH.

The Queen's English: an alternative, biosocial hypothesis for the distinctive features of "gay speech".

PubMed

Rendall, Drew; Vasey, Paul L; McKenzie, Jared

2008-02-01

Popular stereotypes concerning the speech of homosexuals typically attribute speech patterns characteristic of the opposite-sex, i.e., broadly feminized speech in gay men and broadly masculinized speech in lesbian women. A small body of recent empirical research has begun to address the subject more systematically and to consider specific mechanistic hypotheses to account for the potentially distinctive features of homosexual speech. Results do not yet fully endorse the stereotypes but they do not entirely discount them either; nor do they cleanly favor any single mechanistic hypothesis. To contribute to this growing body of research, we report acoustic analyses of 2,875 vowel sounds from a balanced set of 125 speakers representing heterosexual and homosexual individuals of each sex from southern Alberta, Canada. Analyses focused on voice pitch and formant frequencies which together determine the principle perceptual features of vowels. There was no significant difference in mean voice pitch between heterosexual and homosexual men or between heterosexual and homosexual women, but there were significant differences in the formant frequencies of vowels produced by both homosexual groups compared to their heterosexual counterparts. Formant frequency differences were specific to only certain vowel sounds and some could be attributed to basic differences in body size between heterosexual and homosexual speakers. The remaining formant frequency differences were not obviously due to differences in vocal tract anatomy between heterosexual and homosexual speakers, nor did they reflect global feminization or masculinization of vowel production patterns in homosexual men and women, respectively. The vowel-specific differences observed could reflect social modeling processes in which only certain speech patterns of the opposite-sex, or of same-sex homosexuals, are selectively adopted. However, we introduce an alternative biosocial hypothesis, specifically that the distinctive, vowel-specific features of homosexual speakers relative to heterosexual speakers arise incidentally as a product of broader psychobehavioral differences between the two groups that are, in turn, continuous with and flow from the physiological processes that affect sexual orientation to begin with.

Embodied Communication: Speakers' Gestures Affect Listeners' Actions

ERIC Educational Resources Information Center

Cook, Susan Wagner; Tanenhaus, Michael K.

2009-01-01

We explored how speakers and listeners use hand gestures as a source of perceptual-motor information during naturalistic communication. After solving the Tower of Hanoi task either with real objects or on a computer, speakers explained the task to listeners. Speakers' hand gestures, but not their speech, reflected properties of the particular…

Lexical Effects on Second Language Acquisition

ERIC Educational Resources Information Center

Kemp, Renee Lorraine

2017-01-01

Speech production and perception are inextricably linked systems. Speakers modify their speech in response to listener characteristics, such as age, hearing ability, and language background. Listener-oriented modifications in speech production, commonly referred to as clear speech, have also been found to affect speech perception by enhancing…

Neural decoding of attentional selection in multi-speaker environments without access to clean sources

NASA Astrophysics Data System (ADS)

O'Sullivan, James; Chen, Zhuo; Herrero, Jose; McKhann, Guy M.; Sheth, Sameer A.; Mehta, Ashesh D.; Mesgarani, Nima

2017-10-01

Objective. People who suffer from hearing impairments can find it difficult to follow a conversation in a multi-speaker environment. Current hearing aids can suppress background noise; however, there is little that can be done to help a user attend to a single conversation amongst many without knowing which speaker the user is attending to. Cognitively controlled hearing aids that use auditory attention decoding (AAD) methods are the next step in offering help. Translating the successes in AAD research to real-world applications poses a number of challenges, including the lack of access to the clean sound sources in the environment with which to compare with the neural signals. We propose a novel framework that combines single-channel speech separation algorithms with AAD. Approach. We present an end-to-end system that (1) receives a single audio channel containing a mixture of speakers that is heard by a listener along with the listener’s neural signals, (2) automatically separates the individual speakers in the mixture, (3) determines the attended speaker, and (4) amplifies the attended speaker’s voice to assist the listener. Main results. Using invasive electrophysiology recordings, we identified the regions of the auditory cortex that contribute to AAD. Given appropriate electrode locations, our system is able to decode the attention of subjects and amplify the attended speaker using only the mixed audio. Our quality assessment of the modified audio demonstrates a significant improvement in both subjective and objective speech quality measures. Significance. Our novel framework for AAD bridges the gap between the most recent advancements in speech processing technologies and speech prosthesis research and moves us closer to the development of cognitively controlled hearable devices for the hearing impaired.

Unilateral Hearing Loss: Understanding Speech Recognition and Localization Variability - Implications for Cochlear Implant Candidacy

PubMed Central

Firszt, Jill B.; Reeder, Ruth M.; Holden, Laura K.

2016-01-01

Objectives At a minimum, unilateral hearing loss (UHL) impairs sound localization ability and understanding speech in noisy environments, particularly if the loss is severe to profound. Accompanying the numerous negative consequences of UHL is considerable unexplained individual variability in the magnitude of its effects. Identification of co-variables that affect outcome and contribute to variability in UHLs could augment counseling, treatment options, and rehabilitation. Cochlear implantation as a treatment for UHL is on the rise yet little is known about factors that could impact performance or whether there is a group at risk for poor cochlear implant outcomes when hearing is near-normal in one ear. The overall goal of our research is to investigate the range and source of variability in speech recognition in noise and localization among individuals with severe to profound UHL and thereby help determine factors relevant to decisions regarding cochlear implantation in this population. Design The present study evaluated adults with severe to profound UHL and adults with bilateral normal hearing. Measures included adaptive sentence understanding in diffuse restaurant noise, localization, roving-source speech recognition (words from 1 of 15 speakers in a 140° arc) and an adaptive speech-reception threshold psychoacoustic task with varied noise types and noise-source locations. There were three age-gender-matched groups: UHL (severe to profound hearing loss in one ear and normal hearing in the contralateral ear), normal hearing listening bilaterally, and normal hearing listening unilaterally. Results Although the normal-hearing-bilateral group scored significantly better and had less performance variability than UHLs on all measures, some UHL participants scored within the range of the normal-hearing-bilateral group on all measures. The normal-hearing participants listening unilaterally had better monosyllabic word understanding than UHLs for words presented on the blocked/deaf side but not the open/hearing side. In contrast, UHLs localized better than the normal hearing unilateral listeners for stimuli on the open/hearing side but not the blocked/deaf side. This suggests that UHLs had learned strategies for improved localization on the side of the intact ear. The UHL and unilateral normal hearing participant groups were not significantly different for speech-in-noise measures. UHL participants with childhood rather than recent hearing loss onset localized significantly better; however, these two groups did not differ for speech recognition in noise. Age at onset in UHL adults appears to affect localization ability differently than understanding speech in noise. Hearing thresholds were significantly correlated with speech recognition for UHL participants but not the other two groups. Conclusions Auditory abilities of UHLs varied widely and could be explained only in part by hearing threshold levels. Age at onset and length of hearing loss influenced performance on some, but not all measures. Results support the need for a revised and diverse set of clinical measures, including sound localization, understanding speech in varied environments and careful consideration of functional abilities as individuals with severe to profound UHL are being considered potential cochlear implant candidates. PMID:28067750

An oscillator model of the timing of turn-taking.

PubMed

Wilson, Margaret; Wilson, Thomas P

2005-12-01

When humans talk without conventionalized arrangements, they engage in conversation--that is, a continuous and largely nonsimultaneous exchange in which speakers take turns. Turn-taking is ubiquitous in conversation and is the normal case against which alternatives, such as interruptions, are treated as violations that warrant repair. Furthermore, turn-taking involves highly coordinated timing, including a cyclic rise and fall in the probability of initiating speech during brief silences, and involves the notable rarity, especially in two-party conversations, of two speakers' breaking a silence at once. These phenomena, reported by conversation analysts, have been neglected by cognitive psychologists, and to date there has been no adequate cognitive explanation. Here, we propose that, during conversation, endogenous oscillators in the brains of the speaker and the listeners become mutually entrained, on the basis of the speaker's rate of syllable production. This entrained cyclic pattern governs the potential for initiating speech at any given instant for the speaker and also for the listeners (as potential next speakers). Furthermore, the readiness functions of the listeners are counterphased with that of the speaker, minimizing the likelihood of simultaneous starts by a listener and the previous speaker. This mutual entrainment continues for a brief period when the speech stream ceases, accounting for the cyclic property of silences. This model not only captures the timing phenomena observed inthe literature on conversation analysis, but also converges with findings from the literatures on phoneme timing, syllable organization, and interpersonal coordination.

Factors affecting the perception of Korean-accented American English

NASA Astrophysics Data System (ADS)

Cho, Kwansun; Harris, John G.; Shrivastav, Rahul

2005-09-01

This experiment examines the relative contribution of two factors, intonation and articulation errors, on the perception of foreign accent in Korean-accented American English. Ten native speakers of Korean and ten native speakers of American English were asked to read ten English sentences. These sentences were then modified using high-quality speech resynthesis techniques [STRAIGHT Kawahara et al., Speech Commun. 27, 187-207 (1999)] to generate four sets of stimuli. In the first two sets of stimuli, the intonation patterns of the Korean speakers and American speakers were switched with one another. The articulatory errors for each speaker were not modified. In the final two sets, the sentences from the Korean and American speakers were resynthesized without any modifications. Fifteen listeners were asked to rate all the stimuli for the degree of foreign accent. Preliminary results show that, for native speakers of American English, articulation errors may play a greater role in the perception of foreign accent than errors in intonation patterns. [Work supported by KAIM.

Teachers' perceptions of students with speech sound disorders: a quantitative and qualitative analysis.

PubMed

Overby, Megan; Carrell, Thomas; Bernthal, John

2007-10-01

This study examined 2nd-grade teachers' perceptions of the academic, social, and behavioral competence of students with speech sound disorders (SSDs). Forty-eight 2nd-grade teachers listened to 2 groups of sentences differing by intelligibility and pitch but spoken by a single 2nd grader. For each sentence group, teachers rated the speaker's academic, social, and behavioral competence using an adapted version of the Teacher Rating Scale of the Self-Perception Profile for Children (S. Harter, 1985) and completed 3 open-ended questions. The matched-guise design controlled for confounding speaker and stimuli variables that were inherent in prior studies. Statistically significant differences in teachers' expectations of children's academic, social, and behavioral performances were found between moderately intelligible and normal intelligibility speech. Teachers associated moderately intelligible low-pitched speech with more behavior problems than moderately intelligible high-pitched speech or either pitch with normal intelligibility. One third of the teachers reported that they could not accurately predict a child's school performance based on the child's speech skills, one third of the teachers causally related school difficulty to SSD, and one third of the teachers made no comment. Intelligibility and speaker pitch appear to be speech variables that influence teachers' perceptions of children's school performance.

Speech and Pause Characteristics Associated with Voluntary Rate Reduction in Parkinson's Disease and Multiple Sclerosis

ERIC Educational Resources Information Center

Tjaden, Kris; Wilding, Greg

2011-01-01

The primary purpose of this study was to investigate how speakers with Parkinson's disease (PD) and Multiple Sclerosis (MS) accomplish voluntary reductions in speech rate. A group of talkers with no history of neurological disease was included for comparison. This study was motivated by the idea that knowledge of how speakers with dysarthria…

Perception of Melodic Contour and Intonation in Autism Spectrum Disorder: Evidence From Mandarin Speakers.

PubMed

Jiang, Jun; Liu, Fang; Wan, Xuan; Jiang, Cunmei

2015-07-01

Tone language experience benefits pitch processing in music and speech for typically developing individuals. No known studies have examined pitch processing in individuals with autism who speak a tone language. This study investigated discrimination and identification of melodic contour and speech intonation in a group of Mandarin-speaking individuals with high-functioning autism. Individuals with autism showed superior melodic contour identification but comparable contour discrimination relative to controls. In contrast, these individuals performed worse than controls on both discrimination and identification of speech intonation. These findings provide the first evidence for differential pitch processing in music and speech in tone language speakers with autism, suggesting that tone language experience may not compensate for speech intonation perception deficits in individuals with autism.

Prediction and constraint in audiovisual speech perception.

PubMed

Peelle, Jonathan E; Sommers, Mitchell S

2015-07-01

During face-to-face conversational speech listeners must efficiently process a rapid and complex stream of multisensory information. Visual speech can serve as a critical complement to auditory information because it provides cues to both the timing of the incoming acoustic signal (the amplitude envelope, influencing attention and perceptual sensitivity) and its content (place and manner of articulation, constraining lexical selection). Here we review behavioral and neurophysiological evidence regarding listeners' use of visual speech information. Multisensory integration of audiovisual speech cues improves recognition accuracy, particularly for speech in noise. Even when speech is intelligible based solely on auditory information, adding visual information may reduce the cognitive demands placed on listeners through increasing the precision of prediction. Electrophysiological studies demonstrate that oscillatory cortical entrainment to speech in auditory cortex is enhanced when visual speech is present, increasing sensitivity to important acoustic cues. Neuroimaging studies also suggest increased activity in auditory cortex when congruent visual information is available, but additionally emphasize the involvement of heteromodal regions of posterior superior temporal sulcus as playing a role in integrative processing. We interpret these findings in a framework of temporally-focused lexical competition in which visual speech information affects auditory processing to increase sensitivity to acoustic information through an early integration mechanism, and a late integration stage that incorporates specific information about a speaker's articulators to constrain the number of possible candidates in a spoken utterance. Ultimately it is words compatible with both auditory and visual information that most strongly determine successful speech perception during everyday listening. Thus, audiovisual speech perception is accomplished through multiple stages of integration, supported by distinct neuroanatomical mechanisms. Copyright © 2015 Elsevier Ltd. All rights reserved.

Feedforward and feedback control in apraxia of speech: effects of noise masking on vowel production.

PubMed

Maas, Edwin; Mailend, Marja-Liisa; Guenther, Frank H

2015-04-01

This study was designed to test two hypotheses about apraxia of speech (AOS) derived from the Directions Into Velocities of Articulators (DIVA) model (Guenther et al., 2006): the feedforward system deficit hypothesis and the feedback system deficit hypothesis. The authors used noise masking to minimize auditory feedback during speech. Six speakers with AOS and aphasia, 4 with aphasia without AOS, and 2 groups of speakers without impairment (younger and older adults) participated. Acoustic measures of vowel contrast, variability, and duration were analyzed. Younger, but not older, speakers without impairment showed significantly reduced vowel contrast with noise masking. Relative to older controls, the AOS group showed longer vowel durations overall (regardless of masking condition) and a greater reduction in vowel contrast under masking conditions. There were no significant differences in variability. Three of the 6 speakers with AOS demonstrated the group pattern. Speakers with aphasia without AOS did not differ from controls in contrast, duration, or variability. The greater reduction in vowel contrast with masking noise for the AOS group is consistent with the feedforward system deficit hypothesis but not with the feedback system deficit hypothesis; however, effects were small and not present in all individual speakers with AOS. Theoretical implications and alternative interpretations of these findings are discussed.

Feedforward and Feedback Control in Apraxia of Speech: Effects of Noise Masking on Vowel Production

PubMed Central

Mailend, Marja-Liisa; Guenther, Frank H.

2015-01-01

Purpose This study was designed to test two hypotheses about apraxia of speech (AOS) derived from the Directions Into Velocities of Articulators (DIVA) model (Guenther et al., 2006): the feedforward system deficit hypothesis and the feedback system deficit hypothesis. Method The authors used noise masking to minimize auditory feedback during speech. Six speakers with AOS and aphasia, 4 with aphasia without AOS, and 2 groups of speakers without impairment (younger and older adults) participated. Acoustic measures of vowel contrast, variability, and duration were analyzed. Results Younger, but not older, speakers without impairment showed significantly reduced vowel contrast with noise masking. Relative to older controls, the AOS group showed longer vowel durations overall (regardless of masking condition) and a greater reduction in vowel contrast under masking conditions. There were no significant differences in variability. Three of the 6 speakers with AOS demonstrated the group pattern. Speakers with aphasia without AOS did not differ from controls in contrast, duration, or variability. Conclusion The greater reduction in vowel contrast with masking noise for the AOS group is consistent with the feedforward system deficit hypothesis but not with the feedback system deficit hypothesis; however, effects were small and not present in all individual speakers with AOS. Theoretical implications and alternative interpretations of these findings are discussed. PMID:25565143

Pronunciation difficulty, temporal regularity, and the speech-to-song illusion.

PubMed

Margulis, Elizabeth H; Simchy-Gross, Rhimmon; Black, Justin L

2015-01-01

The speech-to-song illusion (Deutsch et al., 2011) tracks the perceptual transformation from speech to song across repetitions of a brief spoken utterance. Because it involves no change in the stimulus itself, but a dramatic change in its perceived affiliation to speech or to music, it presents a unique opportunity to comparatively investigate the processing of language and music. In this study, native English-speaking participants were presented with brief spoken utterances that were subsequently repeated ten times. The utterances were drawn either from languages that are relatively difficult for a native English speaker to pronounce, or languages that are relatively easy for a native English speaker to pronounce. Moreover, the repetition could occur at regular or irregular temporal intervals. Participants rated the utterances before and after the repetitions on a 5-point Likert-like scale ranging from "sounds exactly like speech" to "sounds exactly like singing." The difference in ratings before and after was taken as a measure of the strength of the speech-to-song illusion in each case. The speech-to-song illusion occurred regardless of whether the repetitions were spaced at regular temporal intervals or not; however, it occurred more readily if the utterance was spoken in a language difficult for a native English speaker to pronounce. Speech circuitry seemed more liable to capture native and easy-to-pronounce languages, and more reluctant to relinquish them to perceived song across repetitions.

Automatic voice recognition using traditional and artificial neural network approaches

NASA Technical Reports Server (NTRS)

Botros, Nazeih M.

1989-01-01

The main objective of this research is to develop an algorithm for isolated-word recognition. This research is focused on digital signal analysis rather than linguistic analysis of speech. Features extraction is carried out by applying a Linear Predictive Coding (LPC) algorithm with order of 10. Continuous-word and speaker independent recognition will be considered in future study after accomplishing this isolated word research. To examine the similarity between the reference and the training sets, two approaches are explored. The first is implementing traditional pattern recognition techniques where a dynamic time warping algorithm is applied to align the two sets and calculate the probability of matching by measuring the Euclidean distance between the two sets. The second is implementing a backpropagation artificial neural net model with three layers as the pattern classifier. The adaptation rule implemented in this network is the generalized least mean square (LMS) rule. The first approach has been accomplished. A vocabulary of 50 words was selected and tested. The accuracy of the algorithm was found to be around 85 percent. The second approach is in progress at the present time.

Speech and pause characteristics in multiple sclerosis: A preliminary study of speakers with high and low neuropsychological test performance

PubMed Central

FEENAUGHTY, LYNDA; TJADEN, KRIS; BENEDICT, RALPH H.B.; WEINSTOCK-GUTTMAN, BIANCA

2017-01-01

This preliminary study investigated how cognitive-linguistic status in multiple sclerosis (MS) is reflected in two speech tasks (i.e. oral reading, narrative) that differ in cognitive-linguistic demand. Twenty individuals with MS were selected to comprise High and Low performance groups based on clinical tests of executive function and information processing speed and efficiency. Ten healthy controls were included for comparison. Speech samples were audio-recorded and measures of global speech timing were obtained. Results indicated predicted differences in global speech timing (i.e. speech rate and pause characteristics) for speech tasks differing in cognitive-linguistic demand, but the magnitude of these task-related differences was similar for all speaker groups. Findings suggest that assumptions concerning the cognitive-linguistic demands of reading aloud as compared to spontaneous speech may need to be re-considered for individuals with cognitive impairment. Qualitative trends suggest that additional studies investigating the association between cognitive-linguistic and speech motor variables in MS are warranted. PMID:23294227

Visual Feedback of Tongue Movement for Novel Speech Sound Learning

PubMed Central

Katz, William F.; Mehta, Sonya

2015-01-01

Pronunciation training studies have yielded important information concerning the processing of audiovisual (AV) information. Second language (L2) learners show increased reliance on bottom-up, multimodal input for speech perception (compared to monolingual individuals). However, little is known about the role of viewing one's own speech articulation processes during speech training. The current study investigated whether real-time, visual feedback for tongue movement can improve a speaker's learning of non-native speech sounds. An interactive 3D tongue visualization system based on electromagnetic articulography (EMA) was used in a speech training experiment. Native speakers of American English produced a novel speech sound (/ɖ/; a voiced, coronal, palatal stop) before, during, and after trials in which they viewed their own speech movements using the 3D model. Talkers' productions were evaluated using kinematic (tongue-tip spatial positioning) and acoustic (burst spectra) measures. The results indicated a rapid gain in accuracy associated with visual feedback training. The findings are discussed with respect to neural models for multimodal speech processing. PMID:26635571

Prosody in the hands of the speaker

PubMed Central

Guellaï, Bahia; Langus, Alan; Nespor, Marina

2014-01-01

In everyday life, speech is accompanied by gestures. In the present study, two experiments tested the possibility that spontaneous gestures accompanying speech carry prosodic information. Experiment 1 showed that gestures provide prosodic information, as adults are able to perceive the congruency between low-pass filtered—thus unintelligible—speech and the gestures of the speaker. Experiment 2 shows that in the case of ambiguous sentences (i.e., sentences with two alternative meanings depending on their prosody) mismatched prosody and gestures lead participants to choose more often the meaning signaled by gestures. Our results demonstrate that the prosody that characterizes speech is not a modality specific phenomenon: it is also perceived in the spontaneous gestures that accompany speech. We draw the conclusion that spontaneous gestures and speech form a single communication system where the suprasegmental aspects of spoken language are mapped to the motor-programs responsible for the production of both speech sounds and hand gestures. PMID:25071666

A Joint Time-Frequency and Matrix Decomposition Feature Extraction Methodology for Pathological Voice Classification

NASA Astrophysics Data System (ADS)

Ghoraani, Behnaz; Krishnan, Sridhar

2009-12-01

The number of people affected by speech problems is increasing as the modern world places increasing demands on the human voice via mobile telephones, voice recognition software, and interpersonal verbal communications. In this paper, we propose a novel methodology for automatic pattern classification of pathological voices. The main contribution of this paper is extraction of meaningful and unique features using Adaptive time-frequency distribution (TFD) and nonnegative matrix factorization (NMF). We construct Adaptive TFD as an effective signal analysis domain to dynamically track the nonstationarity in the speech and utilize NMF as a matrix decomposition (MD) technique to quantify the constructed TFD. The proposed method extracts meaningful and unique features from the joint TFD of the speech, and automatically identifies and measures the abnormality of the signal. Depending on the abnormality measure of each signal, we classify the signal into normal or pathological. The proposed method is applied on the Massachusetts Eye and Ear Infirmary (MEEI) voice disorders database which consists of 161 pathological and 51 normal speakers, and an overall classification accuracy of 98.6% was achieved.

Adaptation to an electropalatograph palate: acoustic, impressionistic, and perceptual data.

PubMed

McLeod, Sharynne; Searl, Jeff

2006-05-01

The purpose of this study was to evaluate adaptation to the electropalatograph (EPG) from the perspective of consonant acoustics, listener perceptions, and speaker ratings. Seven adults with typical speech wore an EPG and pseudo-EPG palate over 2 days and produced syllables, read a passage, counted, and rated their adaptation to the palate. Consonant acoustics, listener ratings, and speaker ratings were analyzed. The spectral mean for the burst (/t/) and frication (/s/) was reduced for the first 60-120 min of wearing the pseudo-EPG palate. Temporal features (stop gap, frication, and syllable duration) were unaffected by wearing the pseudo-EPG palate. The EPG palate had a similar effect on consonant acoustics as the pseudo-EPG palate. Expert listener ratings indicated minimal to no change in speech naturalness or distortion from the pseudo-EPG or EPG palate. The sounds [see text] were most likely to be affected. Speaker self-ratings related to oral comfort, speech, tongue movement, appearance, and oral sensation were negatively affected by the presence of the palatal devices. Speakers detected a substantial difference when wearing a palatal device, but the effects on speech were minimal based on listener ratings. Spectral features of consonants were initially affected, although adaptation occurred. Wearing an EPG or pseudo-EPG palate for approximately 2 hr results in relatively normal-sounding speech with acoustic features similar to a no-palate condition.

Respiratory Control in Stuttering Speakers: Evidence from Respiratory High-Frequency Oscillations.

ERIC Educational Resources Information Center

Denny, Margaret; Smith, Anne

2000-01-01

This study examined whether stuttering speakers (N=10) differed from fluent speakers in relations between the neural control systems for speech and life support. It concluded that in some stuttering speakers the relations between respiratory controllers are atypical, but that high participation by the high frequency oscillation-producing circuitry…

Speech Characteristics Associated with Three Genotypes of Ataxia

ERIC Educational Resources Information Center

Sidtis, John J.; Ahn, Ji Sook; Gomez, Christopher; Sidtis, Diana

2011-01-01

Purpose: Advances in neurobiology are providing new opportunities to investigate the neurological systems underlying motor speech control. This study explores the perceptual characteristics of the speech of three genotypes of spino-cerebellar ataxia (SCA) as manifest in four different speech tasks. Methods: Speech samples from 26 speakers with SCA…

Dynamic Encoding of Acoustic Features in Neural Responses to Continuous Speech.

PubMed

Khalighinejad, Bahar; Cruzatto da Silva, Guilherme; Mesgarani, Nima

2017-02-22

Humans are unique in their ability to communicate using spoken language. However, it remains unclear how the speech signal is transformed and represented in the brain at different stages of the auditory pathway. In this study, we characterized electroencephalography responses to continuous speech by obtaining the time-locked responses to phoneme instances (phoneme-related potential). We showed that responses to different phoneme categories are organized by phonetic features. We found that each instance of a phoneme in continuous speech produces multiple distinguishable neural responses occurring as early as 50 ms and as late as 400 ms after the phoneme onset. Comparing the patterns of phoneme similarity in the neural responses and the acoustic signals confirms a repetitive appearance of acoustic distinctions of phonemes in the neural data. Analysis of the phonetic and speaker information in neural activations revealed that different time intervals jointly encode the acoustic similarity of both phonetic and speaker categories. These findings provide evidence for a dynamic neural transformation of low-level speech features as they propagate along the auditory pathway, and form an empirical framework to study the representational changes in learning, attention, and speech disorders. SIGNIFICANCE STATEMENT We characterized the properties of evoked neural responses to phoneme instances in continuous speech. We show that each instance of a phoneme in continuous speech produces several observable neural responses at different times occurring as early as 50 ms and as late as 400 ms after the phoneme onset. Each temporal event explicitly encodes the acoustic similarity of phonemes, and linguistic and nonlinguistic information are best represented at different time intervals. Finally, we show a joint encoding of phonetic and speaker information, where the neural representation of speakers is dependent on phoneme category. These findings provide compelling new evidence for dynamic processing of speech sounds in the auditory pathway. Copyright © 2017 Khalighinejad et al.

Speech Skill Learning of Persons Who Stutter and Fluent Speakers under Single and Dual Task Conditions

ERIC Educational Resources Information Center

Smits-Bandstra, Sarah; De Nil, Luc

2009-01-01

Two studies compared the accuracy and efficiency of initiating oral reading of nonsense syllables by persons who stutter (PWS) and fluent speakers (PNS) over practise. Findings of Study One, comparing 12 PWS and 12 PNS, replicated previous findings of slow speech sequence initiation over practise by PWS relative to PNS. In Study Two, nine PWS and…

The Wildcat Corpus of Native- and Foreign-Accented English: Communicative Efficiency across Conversational Dyads with Varying Language Alignment Profiles

ERIC Educational Resources Information Center

Van Engen, Kristin J.; Baese-Berk, Melissa; Baker, Rachel E.; Choi, Arim; Kim, Midam; Bradlow, Ann R.

2010-01-01

This paper describes the development of the Wildcat Corpus of native- and foreign-accented English, a corpus containing scripted and spontaneous speech recordings from 24 native speakers of American English and 52 non-native speakers of English. The core element of this corpus is a set of spontaneous speech recordings, for which a new method of…

Opening up to Native Speaker Norms: The Use of /?/ in the Speech of Canadian French Immersion Students

ERIC Educational Resources Information Center

Nadasdi, Terry; Vickerman, Alison

2017-01-01

Our study examines the extent to which French immersion students use lax /?/ in the same linguistic context as native speakers of Canadian French. Our results show that the lax variant is vanishingly rare in the speech of immersion students and is used by only a small minority of individuals. This is interpreted as a limitation of French immersion…

An Acoustic and Social Dialect Analysis of Perceptual Variables in Listener Identification and Rating of Negro Speakers. Final Report.

ERIC Educational Resources Information Center

Bryden, James D.

The purpose of this study was to specify variables which function significantly in the racial identification and speech quality rating of Negro and white speakers by Negro and white listeners. Ninety-one adults served as subjects for the speech task; 86 of these subjects, 43 Negro and 43 white, provided the listener responses. Subjects were chosen…

Respiratory Constraints in Verbal and Non-verbal Communication.

PubMed

Włodarczak, Marcin; Heldner, Mattias

2017-01-01

In the present paper we address the old question of respiratory planning in speech production. We recast the problem in terms of speakers' communicative goals and propose that speakers try to minimize respiratory effort in line with the H&H theory. We analyze respiratory cycles coinciding with no speech (i.e., silence), short verbal feedback expressions (SFE's) as well as longer vocalizations in terms of parameters of the respiratory cycle and find little evidence for respiratory planning in feedback production. We also investigate timing of speech and SFEs in the exhalation and contrast it with nods. We find that while speech is strongly tied to the exhalation onset, SFEs are distributed much more uniformly throughout the exhalation and are often produced on residual air. Given that nods, which do not have any respiratory constraints, tend to be more frequent toward the end of an exhalation, we propose a mechanism whereby respiratory patterns are determined by the trade-off between speakers' communicative goals and respiratory constraints.

Facilities to assist people to research into stammered speech

PubMed Central

Howell, Peter; Huckvale, Mark

2008-01-01

The purpose of this article is to indicate how access can be obtained, through Stammering Research, to audio recordings and transcriptions of spontaneous speech data from speakers who stammer. Selections of the first author’s data are available in several formats. We describe where to obtain free software for manipulation and analysis of the data in their respective formats. Papers reporting analyses of these data are invited as submissions to this section of Stammering Research. It is intended that subsequent analyses that employ these data will be published in Stammering Research on an on-going basis. Plans are outlined to provide similar data from young speakers (ones developing fluently and ones who stammer), follow-up data from speakers who stammer, data from speakers who stammer who do not speak English and from speakers who have other speech disorders, for comparison, all through the pages of Stammering Research. The invitation is extended to those promulgating evidence-based practice approaches (see the Journal of Fluency Disorders, volume 28, number 4 which is a special issue devoted to this topic) and anyone with other interesting data related to stammering to prepare them in a form that can be made accessible to others via Stammering Research. PMID:18418475

Age-Related Differences in Lexical Access Relate to Speech Recognition in Noise

PubMed Central

Carroll, Rebecca; Warzybok, Anna; Kollmeier, Birger; Ruigendijk, Esther

2016-01-01

Vocabulary size has been suggested as a useful measure of “verbal abilities” that correlates with speech recognition scores. Knowing more words is linked to better speech recognition. How vocabulary knowledge translates to general speech recognition mechanisms, how these mechanisms relate to offline speech recognition scores, and how they may be modulated by acoustical distortion or age, is less clear. Age-related differences in linguistic measures may predict age-related differences in speech recognition in noise performance. We hypothesized that speech recognition performance can be predicted by the efficiency of lexical access, which refers to the speed with which a given word can be searched and accessed relative to the size of the mental lexicon. We tested speech recognition in a clinical German sentence-in-noise test at two signal-to-noise ratios (SNRs), in 22 younger (18–35 years) and 22 older (60–78 years) listeners with normal hearing. We also assessed receptive vocabulary, lexical access time, verbal working memory, and hearing thresholds as measures of individual differences. Age group, SNR level, vocabulary size, and lexical access time were significant predictors of individual speech recognition scores, but working memory and hearing threshold were not. Interestingly, longer accessing times were correlated with better speech recognition scores. Hierarchical regression models for each subset of age group and SNR showed very similar patterns: the combination of vocabulary size and lexical access time contributed most to speech recognition performance; only for the younger group at the better SNR (yielding about 85% correct speech recognition) did vocabulary size alone predict performance. Our data suggest that successful speech recognition in noise is mainly modulated by the efficiency of lexical access. This suggests that older adults’ poorer performance in the speech recognition task may have arisen from reduced efficiency in lexical access; with an average vocabulary size similar to that of younger adults, they were still slower in lexical access. PMID:27458400

Age-Related Differences in Lexical Access Relate to Speech Recognition in Noise.

PubMed

Carroll, Rebecca; Warzybok, Anna; Kollmeier, Birger; Ruigendijk, Esther

2016-01-01

Vocabulary size has been suggested as a useful measure of "verbal abilities" that correlates with speech recognition scores. Knowing more words is linked to better speech recognition. How vocabulary knowledge translates to general speech recognition mechanisms, how these mechanisms relate to offline speech recognition scores, and how they may be modulated by acoustical distortion or age, is less clear. Age-related differences in linguistic measures may predict age-related differences in speech recognition in noise performance. We hypothesized that speech recognition performance can be predicted by the efficiency of lexical access, which refers to the speed with which a given word can be searched and accessed relative to the size of the mental lexicon. We tested speech recognition in a clinical German sentence-in-noise test at two signal-to-noise ratios (SNRs), in 22 younger (18-35 years) and 22 older (60-78 years) listeners with normal hearing. We also assessed receptive vocabulary, lexical access time, verbal working memory, and hearing thresholds as measures of individual differences. Age group, SNR level, vocabulary size, and lexical access time were significant predictors of individual speech recognition scores, but working memory and hearing threshold were not. Interestingly, longer accessing times were correlated with better speech recognition scores. Hierarchical regression models for each subset of age group and SNR showed very similar patterns: the combination of vocabulary size and lexical access time contributed most to speech recognition performance; only for the younger group at the better SNR (yielding about 85% correct speech recognition) did vocabulary size alone predict performance. Our data suggest that successful speech recognition in noise is mainly modulated by the efficiency of lexical access. This suggests that older adults' poorer performance in the speech recognition task may have arisen from reduced efficiency in lexical access; with an average vocabulary size similar to that of younger adults, they were still slower in lexical access.

Speaker information affects false recognition of unstudied lexical-semantic associates.

PubMed

Luthra, Sahil; Fox, Neal P; Blumstein, Sheila E

2018-05-01

Recognition of and memory for a spoken word can be facilitated by a prior presentation of that word spoken by the same talker. However, it is less clear whether this speaker congruency advantage generalizes to facilitate recognition of unheard related words. The present investigation employed a false memory paradigm to examine whether information about a speaker's identity in items heard by listeners could influence the recognition of novel items (critical intruders) phonologically or semantically related to the studied items. In Experiment 1, false recognition of semantically associated critical intruders was sensitive to speaker information, though only when subjects attended to talker identity during encoding. Results from Experiment 2 also provide some evidence that talker information affects the false recognition of critical intruders. Taken together, the present findings indicate that indexical information is able to contact the lexical-semantic network to affect the processing of unheard words.

Vocal Age Disguise: The Role of Fundamental Frequency and Speech Rate and Its Perceived Effects

PubMed Central

Skoog Waller, Sara; Eriksson, Mårten

2016-01-01

The relationship between vocal characteristics and perceived age is of interest in various contexts, as is the possibility to affect age perception through vocal manipulation. A few examples of such situations are when age is staged by actors, when ear witnesses make age assessments based on vocal cues only or when offenders (e.g., online groomers) disguise their voice to appear younger or older. This paper investigates how speakers spontaneously manipulate two age related vocal characteristics (f0 and speech rate) in attempt to sound younger versus older than their true age, and if the manipulations correspond to actual age related changes in f0 and speech rate (Study 1). Further aims of the paper is to determine how successful vocal age disguise is by asking listeners to estimate the age of generated speech samples (Study 2) and to examine whether or not listeners use f0 and speech rate as cues to perceived age. In Study 1, participants from three age groups (20–25, 40–45, and 60–65 years) agreed to read a short text under three voice conditions. There were 12 speakers in each age group (six women and six men). They used their natural voice in one condition, attempted to sound 20 years younger in another and 20 years older in a third condition. In Study 2, 60 participants (listeners) listened to speech samples from the three voice conditions in Study 1 and estimated the speakers’ age. Each listener was exposed to all three voice conditions. The results from Study 1 indicated that the speakers increased fundamental frequency (f0) and speech rate when attempting to sound younger and decreased f0 and speech rate when attempting to sound older. Study 2 showed that the voice manipulations had an effect in the sought-after direction, although the achieved mean effect was only 3 years, which is far less than the intended effect of 20 years. Moreover, listeners used speech rate, but not f0, as a cue to speaker age. It was concluded that age disguise by voice can be achieved by naïve speakers even though the perceived effect was smaller than intended. PMID:27917144

Should visual speech cues (speechreading) be considered when fitting hearing aids?

NASA Astrophysics Data System (ADS)

Grant, Ken

2002-05-01

When talker and listener are face-to-face, visual speech cues become an important part of the communication environment, and yet, these cues are seldom considered when designing hearing aids. Models of auditory-visual speech recognition highlight the importance of complementary versus redundant speech information for predicting auditory-visual recognition performance. Thus, for hearing aids to work optimally when visual speech cues are present, it is important to know whether the cues provided by amplification and the cues provided by speechreading complement each other. In this talk, data will be reviewed that show nonmonotonicity between auditory-alone speech recognition and auditory-visual speech recognition, suggesting that efforts designed solely to improve auditory-alone recognition may not always result in improved auditory-visual recognition. Data will also be presented showing that one of the most important speech cues for enhancing auditory-visual speech recognition performance, voicing, is often the cue that benefits least from amplification.

Acoustics of Clear Speech: Effect of Instruction

ERIC Educational Resources Information Center

Lam, Jennifer; Tjaden, Kris; Wilding, Greg

2012-01-01

Purpose: This study investigated how different instructions for eliciting clear speech affected selected acoustic measures of speech. Method: Twelve speakers were audio-recorded reading 18 different sentences from the Assessment of Intelligibility of Dysarthric Speech (Yorkston & Beukelman, 1984). Sentences were produced in habitual, clear,…

Children's comprehension of an unfamiliar speaker accent: a review.

PubMed

Harte, Jennifer; Oliveira, Ana; Frizelle, Pauline; Gibbon, Fiona

2016-05-01

The effect of speaker accent on listeners' comprehension has become a key focus of research given the increasing cultural diversity of society and the increased likelihood of an individual encountering a clinician with an unfamiliar accent. To review the studies exploring the effect of an unfamiliar accent on language comprehension in typically developing (TD) children and in children with speech and language difficulties. This review provides a methodological analysis of the relevant studies by exploring the challenges facing this field of research and highlighting the current gaps in the literature. A total of nine studies were identified using a systematic search and organized under studies investigating the effect of speaker accent on language comprehension in (1) TD children and (2) children with speech and/or language difficulties. This review synthesizes the evidence that an unfamiliar speaker accent may lead to a breakdown in language comprehension in TD children and in children with speech difficulties. Moreover, it exposes the inconsistencies found in this field of research and highlights the lack of studies investigating the effect of speaker accent in children with language deficits. Overall, research points towards a developmental trend in children's ability to comprehend accent-related variations in speech. Vocabulary size, language exposure, exposure to different accents and adequate processing resources (e.g. attention) seem to play a key role in children's ability to understand unfamiliar accents. This review uncovered some inconsistencies in the literature that highlight the methodological issues that must be considered when conducting research in this field. It explores how such issues may be controlled in order to increase the validity and reliability of future research. Key clinical implications are also discussed. © 2016 Royal College of Speech and Language Therapists.

Intoxicated Speech Detection: A Fusion Framework with Speaker-Normalized Hierarchical Functionals and GMM Supervectors

PubMed Central

Bone, Daniel; Li, Ming; Black, Matthew P.; Narayanan, Shrikanth S.

2013-01-01

Segmental and suprasegmental speech signal modulations offer information about paralinguistic content such as affect, age and gender, pathology, and speaker state. Speaker state encompasses medium-term, temporary physiological phenomena influenced by internal or external biochemical actions (e.g., sleepiness, alcohol intoxication). Perceptual and computational research indicates that detecting speaker state from speech is a challenging task. In this paper, we present a system constructed with multiple representations of prosodic and spectral features that provided the best result at the Intoxication Subchallenge of Interspeech 2011 on the Alcohol Language Corpus. We discuss the details of each classifier and show that fusion improves performance. We additionally address the question of how best to construct a speaker state detection system in terms of robust and practical marginalization of associated variability such as through modeling speakers, utterance type, gender, and utterance length. As is the case in human perception, speaker normalization provides significant improvements to our system. We show that a held-out set of baseline (sober) data can be used to achieve comparable gains to other speaker normalization techniques. Our fused frame-level statistic-functional systems, fused GMM systems, and final combined system achieve unweighted average recalls (UARs) of 69.7%, 65.1%, and 68.8%, respectively, on the test set. More consistent numbers compared to development set results occur with matched-prompt training, where the UARs are 70.4%, 66.2%, and 71.4%, respectively. The combined system improves over the Challenge baseline by 5.5% absolute (8.4% relative), also improving upon our previously best result. PMID:24376305

Cross-language identification of long-term average speech spectra in Korean and English: toward a better understanding of the quantitative difference between two languages.

PubMed

Noh, Heil; Lee, Dong-Hee

2012-01-01

To identify the quantitative differences between Korean and English in long-term average speech spectra (LTASS). Twenty Korean speakers, who lived in the capital of Korea and spoke standard Korean as their first language, were compared with 20 native English speakers. For the Korean speakers, a passage from a novel and a passage from a leading newspaper article were chosen. For the English speakers, the Rainbow Passage was used. The speech was digitally recorded using GenRad 1982 Precision Sound Level Meter and GoldWave® software and analyzed using MATLAB program. There was no significant difference in the LTASS between the Korean subjects reading a news article or a novel. For male subjects, the LTASS of Korean speakers was significantly lower than that of English speakers above 1.6 kHz except at 4 kHz and its difference was more than 5 dB, especially at higher frequencies. For women, the LTASS of Korean speakers showed significantly lower levels at 0.2, 0.5, 1, 1.25, 2, 2.5, 6.3, 8, and 10 kHz, but the differences were less than 5 dB. Compared with English speakers, the LTASS of Korean speakers showed significantly lower levels in frequencies above 2 kHz except at 4 kHz. The difference was less than 5 dB between 2 and 5 kHz but more than 5 dB above 6 kHz. To adjust the formula for fitting hearing aids for Koreans, our results based on the LTASS analysis suggest that one needs to raise the gain in high-frequency regions.

Evaluation of Speakers with Foreign-Accented Speech in Japan: The Effect of Accent Produced by English Native Speakers

ERIC Educational Resources Information Center

Tsurutani, Chiharu

2012-01-01

Foreign-accented speakers are generally regarded as less educated, less reliable and less interesting than native speakers and tend to be associated with cultural stereotypes of their country of origin. This discrimination against foreign accents has, however, been discussed mainly using accented English in English-speaking countries. This study…

Accent Attribution in Speakers with Foreign Accent Syndrome

ERIC Educational Resources Information Center

Verhoeven, Jo; De Pauw, Guy; Pettinato, Michele; Hirson, Allen; Van Borsel, John; Marien, Peter

2013-01-01

Purpose: The main aim of this experiment was to investigate the perception of Foreign Accent Syndrome in comparison to speakers with an authentic foreign accent. Method: Three groups of listeners attributed accents to conversational speech samples of 5 FAS speakers which were embedded amongst those of 5 speakers with a real foreign accent and 5…

Measures to Evaluate the Effects of DBS on Speech Production

PubMed Central

Weismer, Gary; Yunusova, Yana; Bunton, Kate

2011-01-01

The purpose of this paper is to review and evaluate measures of speech production that could be used to document effects of Deep Brain Stimulation (DBS) on speech performance, especially in persons with Parkinson disease (PD). A small set of evaluative criteria for these measures is presented first, followed by consideration of several speech physiology and speech acoustic measures that have been studied frequently and reported on in the literature on normal speech production, and speech production affected by neuromotor disorders (dysarthria). Each measure is reviewed and evaluated against the evaluative criteria. Embedded within this review and evaluation is a presentation of new data relating speech motions to speech intelligibility measures in speakers with PD, amyotrophic lateral sclerosis (ALS), and control speakers (CS). These data are used to support the conclusion that at the present time the slope of second formant transitions (F2 slope), an acoustic measure, is well suited to make inferences to speech motion and to predict speech intelligibility. The use of other measures should not be ruled out, however, and we encourage further development of evaluative criteria for speech measures designed to probe the effects of DBS or any treatment with potential effects on speech production and communication skills. PMID:24932066

Analysis of False Starts in Spontaneous Speech.

ERIC Educational Resources Information Center

O'Shaughnessy, Douglas

A primary difference between spontaneous speech and read speech concerns the use of false starts, where a speaker interrupts the flow of speech to restart his or her utterance. A study examined the acoustic aspects of such restarts in a widely-used speech database, examining approximately 1000 utterances, about 10% of which contained a restart.…

Effects of a metronome on the filled pauses of fluent speakers.

PubMed

Christenfeld, N

1996-12-01

Filled pauses (the "ums" and "uhs" that litter spontaneous speech) seem to be a product of the speaker paying deliberate attention to the normally automatic act of talking. This is the same sort of explanation that has been offered for stuttering. In this paper we explore whether a manipulation that has long been known to decrease stuttering, synchronizing speech to the beats of a metronome, will then also decrease filled pauses. Two experiments indicate that a metronome has a dramatic effect on the production of filled pauses. This effect is not due to any simplification or slowing of the speech and supports the view that a metronome causes speakers to attend more to how they are talking and less to what they are saying. It also lends support to the connection between stutters and filled pauses.

Developmental changes in sensitivity to vocal paralanguage

PubMed Central

Friend, Margaret

2017-01-01

Developmental changes in children’s sensitivity to the role of acoustic variation in the speech stream in conveying speaker affect (vocal paralanguage) were examined. Four-, 7- and 10-year-olds heard utterances in three formats: low-pass filtered, reiterant, and normal speech. The availability of lexical and paralinguistic information varied across these three formats in a way that required children to base their judgments of speaker affect on different configurations of cues in each format. Across ages, the best performance was obtained when a rich array of acoustic cues was present and when there was no competing lexical information. Four-year-olds performed at chance when judgments had to be based solely on speech prosody in the filtered format and they were unable to selectively attend to paralanguage when discrepant lexical cues were present in normal speech. Seven-year-olds were significantly more sensitive to the paralinguistic role of speech prosody in filtered speech than were 4-year-olds and there was a trend toward greater attention to paralanguage when lexical and paralinguistic cues were inconsistent in normal speech. An integration of the ability to utilize prosodic cues to speaker affect with attention to paralanguage in cases of lexical/paralinguistic discrepancy was observed for 10-year-olds. The results are discussed in terms of the development of a perceptual bias emerging out of selective attention to language. PMID:28713218

Cortical encoding and neurophysiological tracking of intensity and pitch cues signaling English stress patterns in native and nonnative speakers.

PubMed

Chung, Wei-Lun; Bidelman, Gavin M

2016-01-01

We examined cross-language differences in neural encoding and tracking of intensity and pitch cues signaling English stress patterns. Auditory mismatch negativities (MMNs) were recorded in English and Mandarin listeners in response to contrastive English pseudowords whose primary stress occurred either on the first or second syllable (i.e., "nocTICity" vs. "NOCticity"). The contrastive syllable stress elicited two consecutive MMNs in both language groups, but English speakers demonstrated larger responses to stress patterns than Mandarin speakers. Correlations between the amplitude of ERPs and continuous changes in the running intensity and pitch of speech assessed how well each language group's brain activity tracked these salient acoustic features of lexical stress. We found that English speakers' neural responses tracked intensity changes in speech more closely than Mandarin speakers (higher brain-acoustic correlation). Findings demonstrate more robust and precise processing of English stress (intensity) patterns in early auditory cortical responses of native relative to nonnative speakers. Copyright © 2016 Elsevier Inc. All rights reserved.

Orthographic effects in spoken word recognition: Evidence from Chinese.

PubMed

Qu, Qingqing; Damian, Markus F

2017-06-01

Extensive evidence from alphabetic languages demonstrates a role of orthography in the processing of spoken words. Because alphabetic systems explicitly code speech sounds, such effects are perhaps not surprising. However, it is less clear whether orthographic codes are involuntarily accessed from spoken words in languages with non-alphabetic systems, in which the sound-spelling correspondence is largely arbitrary. We investigated the role of orthography via a semantic relatedness judgment task: native Mandarin speakers judged whether or not spoken word pairs were related in meaning. Word pairs were either semantically related, orthographically related, or unrelated. Results showed that relatedness judgments were made faster for word pairs that were semantically related than for unrelated word pairs. Critically, orthographic overlap on semantically unrelated word pairs induced a significant increase in response latencies. These findings indicate that orthographic information is involuntarily accessed in spoken-word recognition, even in a non-alphabetic language such as Chinese.

Retrospective Analysis of Clinical Performance of an Estonian Speech Recognition System for Radiology: Effects of Different Acoustic and Language Models.

PubMed

Paats, A; Alumäe, T; Meister, E; Fridolin, I

2018-04-30

The aim of this study was to analyze retrospectively the influence of different acoustic and language models in order to determine the most important effects to the clinical performance of an Estonian language-based non-commercial radiology-oriented automatic speech recognition (ASR) system. An ASR system was developed for Estonian language in radiology domain by utilizing open-source software components (Kaldi toolkit, Thrax). The ASR system was trained with the real radiology text reports and dictations collected during development phases. The final version of the ASR system was tested by 11 radiologists who dictated 219 reports in total, in spontaneous manner in a real clinical environment. The audio files collected in the final phase were used to measure the performance of different versions of the ASR system retrospectively. ASR system versions were evaluated by word error rate (WER) for each speaker and modality and by WER difference for the first and the last version of the ASR system. Total average WER for the final version throughout all material was improved from 18.4% of the first version (v1) to 5.8% of the last (v8) version which corresponds to relative improvement of 68.5%. WER improvement was strongly related to modality and radiologist. In summary, the performance of the final ASR system version was close to optimal, delivering similar results to all modalities and being independent on user, the complexity of the radiology reports, user experience, and speech characteristics.

Changes in Speech Production Associated with Alphabet Supplementation

ERIC Educational Resources Information Center

Hustad, Katherine C.; Lee, Jimin

2008-01-01

Purpose: This study examined the effect of alphabet supplementation (AS) on temporal and spectral features of speech production in individuals with cerebral palsy and dysarthria. Method: Twelve speakers with dysarthria contributed speech samples using habitual speech and while using AS. One hundred twenty listeners orthographically transcribed…

L'evaluation du francais des jeunes Anglo-montrealais par leurs pairs francophones (Evaluation of the French of Young Montreal Anglophones by Their Francophone Peers).

ERIC Educational Resources Information Center

Thibault, Pierrette; Sankoff, Gillian

1999-01-01

Analyzes the reactions of francophone Montrealers (n=116) to the recorded speech of English speakers using French. Particular focus is on finding out which linguistic traits of speech triggered the judgments on the speakers' competence and to what extent they met the judges expectations with regard to their job suitability. (Author/VWL)

A Cross-Cultural Comparative Study of Apology Strategies Employed by Iranian EFL Learners and English Native Speakers

ERIC Educational Resources Information Center

Abedi, Elham

2016-01-01

The development of speech-act theory has provided the hearers with a better understanding of what speakers intend to perform in the act of communication. One type of speech act is apologizing. When an action or utterance has resulted in an offense, the offender needs to apologize. In the present study, an attempt was made to compare the apology…

A Cross-Cultural Study of Offering Advice Speech Acts by Iranian EFL Learners and English Native Speakers: Pragmatic Transfer in Focus

ERIC Educational Resources Information Center

Babaie, Sherveh; Shahrokhi, Mohsen

2015-01-01

The purpose of the present study was to compare the speech act of offering advice as realized by Iranian EFL learners and English native speakers. The study, more specifically, attempted to find out whether there was any pragmatic transfer from Persian (L1) among Iranian EFL learners while offering advice in English. It also examined whether…

Variation in dual-task performance reveals late initiation of speech planning in turn-taking.

PubMed

Sjerps, Matthias J; Meyer, Antje S

2015-03-01

The smooth transitions between turns in natural conversation suggest that speakers often begin to plan their utterances while listening to their interlocutor. The presented study investigates whether this is indeed the case and, if so, when utterance planning begins. Two hypotheses were contrasted: that speakers begin to plan their turn as soon as possible (in our experiments less than a second after the onset of the interlocutor's turn), or that they do so close to the end of the interlocutor's turn. Turn-taking was combined with a finger tapping task to measure variations in cognitive load. We assumed that the onset of speech planning in addition to listening would be accompanied by deterioration in tapping performance. Two picture description experiments were conducted. In both experiments there were three conditions: (1) Tapping and Speaking, where participants tapped a complex pattern while taking over turns from a pre-recorded speaker, (2) Tapping and Listening, where participants carried out the tapping task while overhearing two pre-recorded speakers, and (3) Speaking Only, where participants took over turns as in the Tapping and Speaking condition but without tapping. The experiments differed in the amount of tapping training the participants received at the beginning of the session. In Experiment 2, the participants' eye-movements were recorded in addition to their speech and tapping. Analyses of the participants' tapping performance and eye movements showed that they initiated the cognitively demanding aspects of speech planning only shortly before the end of the turn of the preceding speaker. We argue that this is a smart planning strategy, which may be the speakers' default in many everyday situations. Copyright © 2014 Elsevier B.V. All rights reserved.

Artificially intelligent recognition of Arabic speaker using voice print-based local features

NASA Astrophysics Data System (ADS)

Mahmood, Awais; Alsulaiman, Mansour; Muhammad, Ghulam; Akram, Sheeraz

2016-11-01

Local features for any pattern recognition system are based on the information extracted locally. In this paper, a local feature extraction technique was developed. This feature was extracted in the time-frequency plain by taking the moving average on the diagonal directions of the time-frequency plane. This feature captured the time-frequency events producing a unique pattern for each speaker that can be viewed as a voice print of the speaker. Hence, we referred to this technique as voice print-based local feature. The proposed feature was compared to other features including mel-frequency cepstral coefficient (MFCC) for speaker recognition using two different databases. One of the databases used in the comparison is a subset of an LDC database that consisted of two short sentences uttered by 182 speakers. The proposed feature attained 98.35% recognition rate compared to 96.7% for MFCC using the LDC subset.

Invariant principles of speech motor control that are not language-specific.

PubMed

Chakraborty, Rahul

2012-12-01

Bilingual speakers must learn to modify their speech motor control mechanism based on the linguistic parameters and rules specified by the target language. This study examines if there are aspects of speech motor control which remain invariant regardless of the first (L1) and second (L2) language targets. Based on the age of academic exposure and proficiency in L2, 21 Bengali-English bilingual participants were classified into high (n = 11) and low (n = 10) L2 (English) proficiency groups. Using the Optotrak 3020 motion sensitive camera system, the lips and jaw movements were recorded while participants produced Bengali (L1) and English (L2) sentences. Based on kinematic analyses of the lip and jaw movements, two different variability measures (i.e., lip aperture and lower lip/jaw complex) were computed for English and Bengali sentences. Analyses demonstrated that the two groups of bilingual speakers produced lip aperture complexes (a higher order synergy) that were more consistent in co-ordination than were the lower lip/jaw complexes (a lower order synergy). Similar findings were reported earlier in monolingual English speakers by Smith and Zelaznik. Thus, this hierarchical organization may be viewed as a fundamental principle of speech motor control, since it is maintained even in bilingual speakers.

Multisensory and modality specific processing of visual speech in different regions of the premotor cortex

PubMed Central

Callan, Daniel E.; Jones, Jeffery A.; Callan, Akiko

2014-01-01

Behavioral and neuroimaging studies have demonstrated that brain regions involved with speech production also support speech perception, especially under degraded conditions. The premotor cortex (PMC) has been shown to be active during both observation and execution of action (“Mirror System” properties), and may facilitate speech perception by mapping unimodal and multimodal sensory features onto articulatory speech gestures. For this functional magnetic resonance imaging (fMRI) study, participants identified vowels produced by a speaker in audio-visual (saw the speaker's articulating face and heard her voice), visual only (only saw the speaker's articulating face), and audio only (only heard the speaker's voice) conditions with varying audio signal-to-noise ratios in order to determine the regions of the PMC involved with multisensory and modality specific processing of visual speech gestures. The task was designed so that identification could be made with a high level of accuracy from visual only stimuli to control for task difficulty and differences in intelligibility. The results of the functional magnetic resonance imaging (fMRI) analysis for visual only and audio-visual conditions showed overlapping activity in inferior frontal gyrus and PMC. The left ventral inferior premotor cortex (PMvi) showed properties of multimodal (audio-visual) enhancement with a degraded auditory signal. The left inferior parietal lobule and right cerebellum also showed these properties. The left ventral superior and dorsal premotor cortex (PMvs/PMd) did not show this multisensory enhancement effect, but there was greater activity for the visual only over audio-visual conditions in these areas. The results suggest that the inferior regions of the ventral premotor cortex are involved with integrating multisensory information, whereas, more superior and dorsal regions of the PMC are involved with mapping unimodal (in this case visual) sensory features of the speech signal with articulatory speech gestures. PMID:24860526

Listeners feel the beat: entrainment to English and French speech rhythms.

PubMed

Lidji, Pascale; Palmer, Caroline; Peretz, Isabelle; Morningstar, Michele

2011-12-01

Can listeners entrain to speech rhythms? Monolingual speakers of English and French and balanced English-French bilinguals tapped along with the beat they perceived in sentences spoken in a stress-timed language, English, and a syllable-timed language, French. All groups of participants tapped more regularly to English than to French utterances. Tapping performance was also influenced by the participants' native language: English-speaking participants and bilinguals tapped more regularly and at higher metrical levels than did French-speaking participants, suggesting that long-term linguistic experience with a stress-timed language can differentiate speakers' entrainment to speech rhythm.

The Impact of Feedback Frequency on Performance in a Novel Speech Motor Learning Task.

PubMed

Lowe, Mara Steinberg; Buchwald, Adam

2017-06-22

This study investigated whether whole nonword accuracy, phoneme accuracy, and acoustic duration measures were influenced by the amount of feedback speakers without impairment received during a novel speech motor learning task. Thirty-two native English speakers completed a nonword production task across 3 time points: practice, short-term retention, and long-term retention. During practice, participants received knowledge of results feedback according to a randomly assigned schedule (100%, 50%, 20%, or 0%). Changes in nonword accuracy, phoneme accuracy, nonword duration, and initial-cluster duration were compared among feedback groups, sessions, and stimulus properties. All participants improved phoneme and whole nonword accuracy at short-term and long-term retention time points. Participants also refined productions of nonwords, as indicated by a decrease in nonword duration across sessions. The 50% group exhibited the largest reduction in duration between practice and long-term retention for nonwords with native and nonnative clusters. All speakers, regardless of feedback schedule, learned new speech motor behaviors quickly with a high degree of accuracy and refined their speech motor skills for perceptually accurate productions. Acoustic measurements may capture more subtle, subperceptual changes that may occur during speech motor learning. https://doi.org/10.23641/asha.5116324.

Unvoiced Speech Recognition Using Tissue-Conductive Acoustic Sensor

NASA Astrophysics Data System (ADS)

Heracleous, Panikos; Kaino, Tomomi; Saruwatari, Hiroshi; Shikano, Kiyohiro

2006-12-01

We present the use of stethoscope and silicon NAM (nonaudible murmur) microphones in automatic speech recognition. NAM microphones are special acoustic sensors, which are attached behind the talker's ear and can capture not only normal (audible) speech, but also very quietly uttered speech (nonaudible murmur). As a result, NAM microphones can be applied in automatic speech recognition systems when privacy is desired in human-machine communication. Moreover, NAM microphones show robustness against noise and they might be used in special systems (speech recognition, speech transform, etc.) for sound-impaired people. Using adaptation techniques and a small amount of training data, we achieved for a 20 k dictation task a[InlineEquation not available: see fulltext.] word accuracy for nonaudible murmur recognition in a clean environment. In this paper, we also investigate nonaudible murmur recognition in noisy environments and the effect of the Lombard reflex on nonaudible murmur recognition. We also propose three methods to integrate audible speech and nonaudible murmur recognition using a stethoscope NAM microphone with very promising results.

Speech recognition technology: an outlook for human-to-machine interaction.

PubMed

Erdel, T; Crooks, S

2000-01-01

Speech recognition, as an enabling technology in healthcare-systems computing, is a topic that has been discussed for quite some time, but is just now coming to fruition. Traditionally, speech-recognition software has been constrained by hardware, but improved processors and increased memory capacities are starting to remove some of these limitations. With these barriers removed, companies that create software for the healthcare setting have the opportunity to write more successful applications. Among the criticisms of speech-recognition applications are the high rates of error and steep training curves. However, even in the face of such negative perceptions, there remains significant opportunities for speech recognition to allow healthcare providers and, more specifically, physicians, to work more efficiently and ultimately spend more time with their patients and less time completing necessary documentation. This article will identify opportunities for inclusion of speech-recognition technology in the healthcare setting and examine major categories of speech-recognition software--continuous speech recognition, command and control, and text-to-speech. We will discuss the advantages and disadvantages of each area, the limitations of the software today, and how future trends might affect them.

Brief Report: Relations between Prosodic Performance and Communication and Socialization Ratings in High Functioning Speakers with Autism Spectrum Disorders

ERIC Educational Resources Information Center

Paul, Rhea; Shriberg, Lawrence D.; McSweeny, Jane; Cicchetti, Domenic; Klin, Ami; Volkmar, Fred

2005-01-01

Shriberg "et al." [Shriberg, L. "et al." (2001). "Journal of Speech, Language and Hearing Research, 44," 1097-1115] described prosody-voice features of 30 high functioning speakers with autistic spectrum disorder (ASD) compared to age-matched control speakers. The present study reports additional information on the speakers with ASD, including…

The Dynamic Nature of Speech Perception

ERIC Educational Resources Information Center

McQueen, James M.; Norris, Dennis; Cutler, Anne

2006-01-01

The speech perception system must be flexible in responding to the variability in speech sounds caused by differences among speakers and by language change over the lifespan of the listener. Indeed, listeners use lexical knowledge to retune perception of novel speech (Norris, McQueen, & Cutler, 2003). In that study, Dutch listeners made…

Developing a Weighted Measure of Speech Sound Accuracy

ERIC Educational Resources Information Center

Preston, Jonathan L.; Ramsdell, Heather L.; Oller, D. Kimbrough; Edwards, Mary Louise; Tobin, Stephen J.

2011-01-01

Purpose: To develop a system for numerically quantifying a speaker's phonetic accuracy through transcription-based measures. With a focus on normal and disordered speech in children, the authors describe a system for differentially weighting speech sound errors on the basis of various levels of phonetic accuracy using a Weighted Speech Sound…

Impact of cognitive function and dysarthria on spoken language and perceived speech severity in multiple sclerosis

NASA Astrophysics Data System (ADS)

Feenaughty, Lynda

Purpose: The current study sought to investigate the separate effects of dysarthria and cognitive status on global speech timing, speech hesitation, and linguistic complexity characteristics and how these speech behaviors impose on listener impressions for three connected speech tasks presumed to differ in cognitive-linguistic demand for four carefully defined speaker groups; 1) MS with cognitive deficits (MSCI), 2) MS with clinically diagnosed dysarthria and intact cognition (MSDYS), 3) MS without dysarthria or cognitive deficits (MS), and 4) healthy talkers (CON). The relationship between neuropsychological test scores and speech-language production and perceptual variables for speakers with cognitive deficits was also explored. Methods: 48 speakers, including 36 individuals reporting a neurological diagnosis of MS and 12 healthy talkers participated. The three MS groups and control group each contained 12 speakers (8 women and 4 men). Cognitive function was quantified using standard clinical tests of memory, information processing speed, and executive function. A standard z-score of ≤ -1.50 indicated deficits in a given cognitive domain. Three certified speech-language pathologists determined the clinical diagnosis of dysarthria for speakers with MS. Experimental speech tasks of interest included audio-recordings of an oral reading of the Grandfather passage and two spontaneous speech samples in the form of Familiar and Unfamiliar descriptive discourse. Various measures of spoken language were of interest. Suprasegmental acoustic measures included speech and articulatory rate. Linguistic speech hesitation measures included pause frequency (i.e., silent and filled pauses), mean silent pause duration, grammatical appropriateness of pauses, and interjection frequency. For the two discourse samples, three standard measures of language complexity were obtained including subordination index, inter-sentence cohesion adequacy, and lexical diversity. Ten listeners judged each speech sample using the perceptual construct of Speech Severity using a visual analog scale. Additional measures obtained to describe participants included the Sentence Intelligibility Test (SIT), the 10-item Communication Participation Item Bank (CPIB), and standard biopsychosocial measures of depression (Beck Depression Inventory-Fast Screen; BDI-FS), fatigue (Fatigue Severity Scale; FSS), and overall disease severity (Expanded Disability Status Scale; EDSS). Healthy controls completed all measures, with the exception of the CPIB and EDSS. All data were analyzed using standard, descriptive and parametric statistics. For the MSCI group, the relationship between neuropsychological test scores and speech-language variables were explored for each speech task using Pearson correlations. The relationship between neuropsychological test scores and Speech Severity also was explored. Results and Discussion: Topic familiarity for descriptive discourse did not strongly influence speech production or perceptual variables; however, results indicated predicted task-related differences for some spoken language measures. With the exception of the MSCI group, all speaker groups produced the same or slower global speech timing (i.e., speech and articulatory rates), more silent and filled pauses, more grammatical and longer silent pause durations in spontaneous discourse compared to reading aloud. Results revealed no appreciable task differences for linguistic complexity measures. Results indicated group differences for speech rate. The MSCI group produced significantly faster speech rates compared to the MSDYS group. Both the MSDYS and the MSCI groups were judged to have significantly poorer perceived Speech Severity compared to typically aging adults. The Task x Group interaction was only significant for the number of silent pauses. The MSDYS group produced fewer silent pauses in spontaneous speech and more silent pauses in the reading task compared to other groups. Finally, correlation analysis revealed moderate relationships between neuropsychological test scores and speech hesitation measures, within the MSCI group. Slower information processing and poorer memory were significantly correlated with more silent pauses and poorer executive function was associated with fewer filled pauses in the Unfamiliar discourse task. Results have both clinical and theoretical implications. Overall, clinicians should demonstrate caution when interpreting global measures of speech timing and perceptual measures in the absence of information about cognitive ability. Results also have implications for a comprehensive model of spoken language incorporating cognitive, linguistic, and motor variables.

Applications of Hilbert Spectral Analysis for Speech and Sound Signals

NASA Technical Reports Server (NTRS)

Huang, Norden E.

2003-01-01

A new method for analyzing nonlinear and nonstationary data has been developed, and the natural applications are to speech and sound signals. The key part of the method is the Empirical Mode Decomposition method with which any complicated data set can be decomposed into a finite and often small number of Intrinsic Mode Functions (IMF). An IMF is defined as any function having the same numbers of zero-crossing and extrema, and also having symmetric envelopes defined by the local maxima and minima respectively. The IMF also admits well-behaved Hilbert transform. This decomposition method is adaptive, and, therefore, highly efficient. Since the decomposition is based on the local characteristic time scale of the data, it is applicable to nonlinear and nonstationary processes. With the Hilbert transform, the Intrinsic Mode Functions yield instantaneous frequencies as functions of time, which give sharp identifications of imbedded structures. This method invention can be used to process all acoustic signals. Specifically, it can process the speech signals for Speech synthesis, Speaker identification and verification, Speech recognition, and Sound signal enhancement and filtering. Additionally, as the acoustical signals from machinery are essentially the way the machines are talking to us. Therefore, the acoustical signals, from the machines, either from sound through air or vibration on the machines, can tell us the operating conditions of the machines. Thus, we can use the acoustic signal to diagnosis the problems of machines.

Speech-Language Pathologists' Assessment Practices for Children with Suspected Speech Sound Disorders: Results of a National Survey

ERIC Educational Resources Information Center

Skahan, Sarah M.; Watson, Maggie; Lof, Gregory L.

2007-01-01

Purpose: This study examined assessment procedures used by speech-language pathologists (SLPs) when assessing children suspected of having speech sound disorders (SSD). This national survey also determined the information participants obtained from clients' speech samples, evaluation of non-native English speakers, and time spent on assessment.…

The role of linguistic experience in the processing of probabilistic information in production.

PubMed

Gustafson, Erin; Goldrick, Matthew

2018-01-01

Speakers track the probability that a word will occur in a particular context and utilize this information during phonetic processing. For example, content words that have high probability within a discourse tend to be realized with reduced acoustic/articulatory properties. Such probabilistic information may influence L1 and L2 speech processing in distinct ways (reflecting differences in linguistic experience across groups and the overall difficulty of L2 speech processing). To examine this issue, L1 and L2 speakers performed a referential communication task, describing sequences of simple actions. The two groups of speakers showed similar effects of discourse-dependent probabilistic information on production, suggesting that L2 speakers can successfully track discourse-dependent probabilities and use such information to modulate phonetic processing.

Speaker verification using committee neural networks.

PubMed

Reddy, Narender P; Buch, Ojas A

2003-10-01

Security is a major problem in web based access or remote access to data bases. In the present study, the technique of committee neural networks was developed for speech based speaker verification. Speech data from the designated speaker and several imposters were obtained. Several parameters were extracted in the time and frequency domains, and fed to neural networks. Several neural networks were trained and the five best performing networks were recruited into the committee. The committee decision was based on majority voting of the member networks. The committee opinion was evaluated with further testing data. The committee correctly identified the designated speaker in (50 out of 50) 100% of the cases and rejected imposters in (150 out of 150) 100% of the cases. The committee decision was not unanimous in majority of the cases tested.

Comparison of Magnetic Resonance Imaging-based vocal tract area functions obtained from the same speaker in 1994 and 2002

PubMed Central

Story, Brad H.

2008-01-01

A new set of area functions for vowels has been obtained with Magnetic Resonance Imaging (MRI) from the same speaker as that previously reported in 1996 [Story, Titze, & Hoffman, JASA, 100, 537–554 (1996)]. The new area functions were derived from image data collected in 2002, whereas the previously reported area functions were based on MR images obtained in 1994. When compared, the new area function sets indicated a tendency toward a constricted pharyngeal region and expanded oral cavity relative to the previous set. Based on calculated formant frequencies and sensitivity functions, these morphological differences were shown to have the primary acoustic effect of systematically shifting the second formant (F2) downward in frequency. Multiple instances of target vocal tract shapes from a specific speaker provide additional sampling of the possible area functions that may be produced during speech production. This may be of benefit for understanding intra-speaker variability in vowel production and for further development of speech synthesizers and speech models that utilize area function information. PMID:18177162

Relationship between listeners' nonnative speech recognition and categorization abilities

PubMed Central

Atagi, Eriko; Bent, Tessa

2015-01-01

Enhancement of the perceptual encoding of talker characteristics (indexical information) in speech can facilitate listeners' recognition of linguistic content. The present study explored this indexical-linguistic relationship in nonnative speech processing by examining listeners' performance on two tasks: nonnative accent categorization and nonnative speech-in-noise recognition. Results indicated substantial variability across listeners in their performance on both the accent categorization and nonnative speech recognition tasks. Moreover, listeners' accent categorization performance correlated with their nonnative speech-in-noise recognition performance. These results suggest that having more robust indexical representations for nonnative accents may allow listeners to more accurately recognize the linguistic content of nonnative speech. PMID:25618098

Measurement of trained speech patterns in stuttering: interjudge and intrajudge agreement of experts by means of modified time-interval analysis.

PubMed

Alpermann, Anke; Huber, Walter; Natke, Ulrich; Willmes, Klaus

2010-09-01

Improved fluency after stuttering therapy is usually measured by the percentage of stuttered syllables. However, outcome studies rarely evaluate the use of trained speech patterns that speakers use to manage stuttering. This study investigated whether the modified time interval analysis can distinguish between trained speech patterns, fluent speech, and stuttered speech. Seventeen German experts on stuttering judged a speech sample on two occasions. Speakers of the sample were stuttering adults, who were not undergoing therapy, as well as participants in a fluency shaping and a stuttering modification therapy. Results showed satisfactory inter-judge and intra-judge agreement above 80%. Intervals with trained speech patterns were identified as consistently as stuttered and fluent intervals. We discuss limitations of the study, as well as implications of our findings for the development of training for identification of trained speech patterns and future outcome studies. The reader will be able to (a) explain different methods to measure the use of trained speech patterns, (b) evaluate whether German experts are able to discriminate intervals with trained speech patterns reliably from fluent and stuttered intervals and (c) describe how the measurement of trained speech patterns can contribute to outcome studies.

Method and apparatus for obtaining complete speech signals for speech recognition applications

NASA Technical Reports Server (NTRS)

Abrash, Victor (Inventor); Cesari, Federico (Inventor); Franco, Horacio (Inventor); George, Christopher (Inventor); Zheng, Jing (Inventor)

2009-01-01

The present invention relates to a method and apparatus for obtaining complete speech signals for speech recognition applications. In one embodiment, the method continuously records an audio stream comprising a sequence of frames to a circular buffer. When a user command to commence or terminate speech recognition is received, the method obtains a number of frames of the audio stream occurring before or after the user command in order to identify an augmented audio signal for speech recognition processing. In further embodiments, the method analyzes the augmented audio signal in order to locate starting and ending speech endpoints that bound at least a portion of speech to be processed for recognition. At least one of the speech endpoints is located using a Hidden Markov Model.

Speech rate reduction and "nasality" in normal speakers.

PubMed

Brancewicz, T M; Reich, A R

1989-12-01

This study explored the effects of reduced speech rate on nasal/voice accelerometric measures and nasality ratings. Nasal/voice accelerometric measures were obtained from normal adults for various speech stimuli and speaking rates. Stimuli included three sentences (one obstruent-loaded, one semivowel-loaded, and one containing a single nasal), and /pv/ syllable trains.. Speakers read the stimuli at their normal rate, half their normal rate, and as slowly as possible. In addition, a computer program paced each speaker at rates of 1, 2, and 3 syllables per second. The nasal/voice accelerometric values revealed significant stimulus effects but no rate effects. The nasality ratings of experienced listeners, evaluated as a function of stimulus and speaking rate, were compared to the accelerometric measures. The nasality scale values demonstrated small, but statistically significant, stimulus and rate effects. However, the nasality percepts were poorly correlated with the nasal/voice accelerometric measures.

Left hemisphere lateralization for lexical and acoustic pitch processing in Cantonese speakers as revealed by mismatch negativity.

PubMed

Gu, Feng; Zhang, Caicai; Hu, Axu; Zhao, Guoping

2013-12-01

For nontonal language speakers, speech processing is lateralized to the left hemisphere and musical processing is lateralized to the right hemisphere (i.e., function-dependent brain asymmetry). On the other hand, acoustic temporal processing is lateralized to the left hemisphere and spectral/pitch processing is lateralized to the right hemisphere (i.e., acoustic-dependent brain asymmetry). In this study, we examine whether the hemispheric lateralization of lexical pitch and acoustic pitch processing in tonal language speakers is consistent with the patterns of function- and acoustic-dependent brain asymmetry in nontonal language speakers. Pitch contrast in both speech stimuli (syllable /ji/ in Experiment 1) and nonspeech stimuli (harmonic tone in Experiment 1; pure tone in Experiment 2) was presented to native Cantonese speakers in passive oddball paradigms. We found that the mismatch negativity (MMN) elicited by lexical pitch contrast was lateralized to the left hemisphere, which is consistent with the pattern of function-dependent brain asymmetry (i.e., left hemisphere lateralization for speech processing) in nontonal language speakers. However, the MMN elicited by acoustic pitch contrast was also left hemisphere lateralized (harmonic tone in Experiment 1) or showed a tendency for left hemisphere lateralization (pure tone in Experiment 2), which is inconsistent with the pattern of acoustic-dependent brain asymmetry (i.e., right hemisphere lateralization for acoustic pitch processing) in nontonal language speakers. The consistent pattern of function-dependent brain asymmetry and the inconsistent pattern of acoustic-dependent brain asymmetry between tonal and nontonal language speakers can be explained by the hypothesis that the acoustic-dependent brain asymmetry is the consequence of a carryover effect from function-dependent brain asymmetry. Potential evolutionary implication of this hypothesis is discussed. © 2013.

The Effect of Speech Rate on Stuttering Frequency, Phonated Intervals, Speech Effort, and Speech Naturalness during Chorus Reading

ERIC Educational Resources Information Center

Davidow, Jason H.; Ingham, Roger J.

2013-01-01

Purpose: This study examined the effect of speech rate on phonated intervals (PIs), in order to test whether a reduction in the frequency of short PIs is an important part of the fluency-inducing mechanism of chorus reading. The influence of speech rate on stuttering frequency, speaker-judged speech effort, and listener-judged naturalness was also…

Temporal Sensitivity Measured Shortly After Cochlear Implantation Predicts 6-Month Speech Recognition Outcome.

PubMed

Erb, Julia; Ludwig, Alexandra Annemarie; Kunke, Dunja; Fuchs, Michael; Obleser, Jonas

2018-04-24

Psychoacoustic tests assessed shortly after cochlear implantation are useful predictors of the rehabilitative speech outcome. While largely independent, both spectral and temporal resolution tests are important to provide an accurate prediction of speech recognition. However, rapid tests of temporal sensitivity are currently lacking. Here, we propose a simple amplitude modulation rate discrimination (AMRD) paradigm that is validated by predicting future speech recognition in adult cochlear implant (CI) patients. In 34 newly implanted patients, we used an adaptive AMRD paradigm, where broadband noise was modulated at the speech-relevant rate of ~4 Hz. In a longitudinal study, speech recognition in quiet was assessed using the closed-set Freiburger number test shortly after cochlear implantation (t0) as well as the open-set Freiburger monosyllabic word test 6 months later (t6). Both AMRD thresholds at t0 (r = -0.51) and speech recognition scores at t0 (r = 0.56) predicted speech recognition scores at t6. However, AMRD and speech recognition at t0 were uncorrelated, suggesting that those measures capture partially distinct perceptual abilities. A multiple regression model predicting 6-month speech recognition outcome with deafness duration and speech recognition at t0 improved from adjusted R = 0.30 to adjusted R = 0.44 when AMRD threshold was added as a predictor. These findings identify AMRD thresholds as a reliable, nonredundant predictor above and beyond established speech tests for CI outcome. This AMRD test could potentially be developed into a rapid clinical temporal-resolution test to be integrated into the postoperative test battery to improve the reliability of speech outcome prognosis.

How Psychological Stress Affects Emotional Prosody.

PubMed

Paulmann, Silke; Furnes, Desire; Bøkenes, Anne Ming; Cozzolino, Philip J

2016-01-01

We explored how experimentally induced psychological stress affects the production and recognition of vocal emotions. In Study 1a, we demonstrate that sentences spoken by stressed speakers are judged by naïve listeners as sounding more stressed than sentences uttered by non-stressed speakers. In Study 1b, negative emotions produced by stressed speakers are generally less well recognized than the same emotions produced by non-stressed speakers. Multiple mediation analyses suggest this poorer recognition of negative stimuli was due to a mismatch between the variation of volume voiced by speakers and the range of volume expected by listeners. Together, this suggests that the stress level of the speaker affects judgments made by the receiver. In Study 2, we demonstrate that participants who were induced with a feeling of stress before carrying out an emotional prosody recognition task performed worse than non-stressed participants. Overall, findings suggest detrimental effects of induced stress on interpersonal sensitivity.

How Psychological Stress Affects Emotional Prosody

PubMed Central

Paulmann, Silke; Furnes, Desire; Bøkenes, Anne Ming; Cozzolino, Philip J.

2016-01-01

We explored how experimentally induced psychological stress affects the production and recognition of vocal emotions. In Study 1a, we demonstrate that sentences spoken by stressed speakers are judged by naïve listeners as sounding more stressed than sentences uttered by non-stressed speakers. In Study 1b, negative emotions produced by stressed speakers are generally less well recognized than the same emotions produced by non-stressed speakers. Multiple mediation analyses suggest this poorer recognition of negative stimuli was due to a mismatch between the variation of volume voiced by speakers and the range of volume expected by listeners. Together, this suggests that the stress level of the speaker affects judgments made by the receiver. In Study 2, we demonstrate that participants who were induced with a feeling of stress before carrying out an emotional prosody recognition task performed worse than non-stressed participants. Overall, findings suggest detrimental effects of induced stress on interpersonal sensitivity. PMID:27802287

[Speech fluency developmental profile in Brazilian Portuguese speakers].

PubMed

Martins, Vanessa de Oliveira; Andrade, Claudia Regina Furquim de

2008-01-01

speech fluency varies from one individual to the next, fluent or stutterer, depending on several factors. Studies that investigate the influence of age on fluency patterns have been identified; however these differences were investigated in isolated age groups. Studies about life span fluency variations were not found. to verify the speech fluency developmental profile. speech samples of 594 fluent participants of both genders, with ages between 2:0 and 99:11 years, speakers of the Brazilian Portuguese language, were analyzed. Participants were grouped as follows: pre-scholars, scholars, early adolescence, late adolescence, adults and elderlies. Speech samples were analyzed according to the Speech Fluency Profile variables and were compared regarding: typology of speech disruptions (typical and less typical), speech rate (words and syllables per minute) and frequency of speech disruptions (percentage of speech discontinuity). although isolated variations were identified, overall there was no significant difference between the age groups for the speech disruption indexes (typical and less typical speech disruptions and percentage of speech discontinuity). Significant differences were observed between the groups when considering speech rate. the development of the neurolinguistic system for speech fluency, in terms of speech disruptions, seems to stabilize itself during the first years of life, presenting no alterations during the life span. Indexes of speech rate present variations in the age groups, indicating patterns of acquisition, development, stabilization and degeneration.

Analysis of error type and frequency in apraxia of speech among Portuguese speakers.

PubMed

Cera, Maysa Luchesi; Minett, Thaís Soares Cianciarullo; Ortiz, Karin Zazo

2010-01-01

Most studies characterizing errors in the speech of patients with apraxia involve English language. To analyze the types and frequency of errors produced by patients with apraxia of speech whose mother tongue was Brazilian Portuguese. 20 adults with apraxia of speech caused by stroke were assessed. The types of error committed by patients were analyzed both quantitatively and qualitatively, and frequencies compared. We observed the presence of substitution, omission, trial-and-error, repetition, self-correction, anticipation, addition, reiteration and metathesis, in descending order of frequency, respectively. Omission type errors were one of the most commonly occurring whereas addition errors were infrequent. These findings differed to those reported in English speaking patients, probably owing to differences in the methodologies used for classifying error types; the inclusion of speakers with apraxia secondary to aphasia; and the difference in the structure of Portuguese language to English in terms of syllable onset complexity and effect on motor control. The frequency of omission and addition errors observed differed to the frequency reported for speakers of English.

Robust speaker's location detection in a vehicle environment using GMM models.

PubMed

Hu, Jwu-Sheng; Cheng, Chieh-Cheng; Liu, Wei-Han

2006-04-01

Abstract-Human-computer interaction (HCI) using speech communication is becoming increasingly important, especially in driving where safety is the primary concern. Knowing the speaker's location (i.e., speaker localization) not only improves the enhancement results of a corrupted signal, but also provides assistance to speaker identification. Since conventional speech localization algorithms suffer from the uncertainties of environmental complexity and noise, as well as from the microphone mismatch problem, they are frequently not robust in practice. Without a high reliability, the acceptance of speech-based HCI would never be realized. This work presents a novel speaker's location detection method and demonstrates high accuracy within a vehicle cabinet using a single linear microphone array. The proposed approach utilize Gaussian mixture models (GMM) to model the distributions of the phase differences among the microphones caused by the complex characteristic of room acoustic and microphone mismatch. The model can be applied both in near-field and far-field situations in a noisy environment. The individual Gaussian component of a GMM represents some general location-dependent but content and speaker-independent phase difference distributions. Moreover, the scheme performs well not only in nonline-of-sight cases, but also when the speakers are aligned toward the microphone array but at difference distances from it. This strong performance can be achieved by exploiting the fact that the phase difference distributions at different locations are distinguishable in the environment of a car. The experimental results also show that the proposed method outperforms the conventional multiple signal classification method (MUSIC) technique at various SNRs.

Audibility-based predictions of speech recognition for children and adults with normal hearing.

PubMed

McCreery, Ryan W; Stelmachowicz, Patricia G

2011-12-01

This study investigated the relationship between audibility and predictions of speech recognition for children and adults with normal hearing. The Speech Intelligibility Index (SII) is used to quantify the audibility of speech signals and can be applied to transfer functions to predict speech recognition scores. Although the SII is used clinically with children, relatively few studies have evaluated SII predictions of children's speech recognition directly. Children have required more audibility than adults to reach maximum levels of speech understanding in previous studies. Furthermore, children may require greater bandwidth than adults for optimal speech understanding, which could influence frequency-importance functions used to calculate the SII. Speech recognition was measured for 116 children and 19 adults with normal hearing. Stimulus bandwidth and background noise level were varied systematically in order to evaluate speech recognition as predicted by the SII and derive frequency-importance functions for children and adults. Results suggested that children required greater audibility to reach the same level of speech understanding as adults. However, differences in performance between adults and children did not vary across frequency bands. © 2011 Acoustical Society of America

An acoustic comparison of two women's infant- and adult-directed speech

NASA Astrophysics Data System (ADS)

Andruski, Jean; Katz-Gershon, Shiri

2003-04-01

In addition to having prosodic characteristics that are attractive to infant listeners, infant-directed (ID) speech shares certain characteristics of adult-directed (AD) clear speech, such as increased acoustic distance between vowels, that might be expected to make ID speech easier for adults to perceive in noise than AD conversational speech. However, perceptual tests of two women's ID productions by Andruski and Bessega [J. Acoust. Soc. Am. 112, 2355] showed that is not always the case. In a word identification task that compared ID speech with AD clear and conversational speech, one speaker's ID productions were less well-identified than AD clear speech, but better identified than AD conversational speech. For the second woman, ID speech was the least accurately identified of the three speech registers. For both speakers, hard words (infrequent words with many lexical neighbors) were also at an increased disadvantage relative to easy words (frequent words with few lexical neighbors) in speech registers that were less accurately perceived. This study will compare several acoustic properties of these women's productions, including pitch and formant-frequency characteristics. Results of the acoustic analyses will be examined with the original perceptual results to suggest reasons for differences in listener's accuracy in identifying these two women's ID speech in noise.

Normal-Hearing Listeners’ and Cochlear Implant Users’ Perception of Pitch Cues in Emotional Speech

PubMed Central

Fuller, Christina; Gilbers, Dicky; Broersma, Mirjam; Goudbeek, Martijn; Free, Rolien; Başkent, Deniz

2015-01-01

In cochlear implants (CIs), acoustic speech cues, especially for pitch, are delivered in a degraded form. This study’s aim is to assess whether due to degraded pitch cues, normal-hearing listeners and CI users employ different perceptual strategies to recognize vocal emotions, and, if so, how these differ. Voice actors were recorded pronouncing a nonce word in four different emotions: anger, sadness, joy, and relief. These recordings’ pitch cues were phonetically analyzed. The recordings were used to test 20 normal-hearing listeners’ and 20 CI users’ emotion recognition. In congruence with previous studies, high-arousal emotions had a higher mean pitch, wider pitch range, and more dominant pitches than low-arousal emotions. Regarding pitch, speakers did not differentiate emotions based on valence but on arousal. Normal-hearing listeners outperformed CI users in emotion recognition, even when presented with CI simulated stimuli. However, only normal-hearing listeners recognized one particular actor’s emotions worse than the other actors’. The groups behaved differently when presented with similar input, showing that they had to employ differing strategies. Considering the respective speaker’s deviating pronunciation, it appears that for normal-hearing listeners, mean pitch is a more salient cue than pitch range, whereas CI users are biased toward pitch range cues. PMID:27648210

Unconscious improvement in foreign language learning using mismatch negativity neurofeedback: A preliminary study.

PubMed

Chang, Ming; Iizuka, Hiroyuki; Kashioka, Hideki; Naruse, Yasushi; Furukawa, Masahiro; Ando, Hideyuki; Maeda, Taro

2017-01-01

When people learn foreign languages, they find it difficult to perceive speech sounds that are nonexistent in their native language, and extensive training is consequently necessary. Our previous studies have shown that by using neurofeedback based on the mismatch negativity event-related brain potential, participants could unconsciously achieve learning in the auditory discrimination of pure tones that could not be consciously discriminated without the neurofeedback. Here, we examined whether mismatch negativity neurofeedback is effective for helping someone to perceive new speech sounds in foreign language learning. We developed a task for training native Japanese speakers to discriminate between 'l' and 'r' sounds in English, as they usually cannot discriminate between these two sounds. Without participants attending to auditory stimuli or being aware of the nature of the experiment, neurofeedback training helped them to achieve significant improvement in unconscious auditory discrimination and recognition of the target words 'light' and 'right'. There was also improvement in the recognition of other words containing 'l' and 'r' (e.g., 'blight' and 'bright'), even though these words had not been presented during training. This method could be used to facilitate foreign language learning and can be extended to other fields of auditory and clinical research and even other senses.

Unconscious improvement in foreign language learning using mismatch negativity neurofeedback: A preliminary study

PubMed Central

Iizuka, Hiroyuki; Kashioka, Hideki; Naruse, Yasushi; Furukawa, Masahiro; Ando, Hideyuki; Maeda, Taro

2017-01-01

When people learn foreign languages, they find it difficult to perceive speech sounds that are nonexistent in their native language, and extensive training is consequently necessary. Our previous studies have shown that by using neurofeedback based on the mismatch negativity event-related brain potential, participants could unconsciously achieve learning in the auditory discrimination of pure tones that could not be consciously discriminated without the neurofeedback. Here, we examined whether mismatch negativity neurofeedback is effective for helping someone to perceive new speech sounds in foreign language learning. We developed a task for training native Japanese speakers to discriminate between ‘l’ and ‘r’ sounds in English, as they usually cannot discriminate between these two sounds. Without participants attending to auditory stimuli or being aware of the nature of the experiment, neurofeedback training helped them to achieve significant improvement in unconscious auditory discrimination and recognition of the target words ‘light’ and ‘right’. There was also improvement in the recognition of other words containing ‘l’ and ‘r’ (e.g., ‘blight’ and ‘bright’), even though these words had not been presented during training. This method could be used to facilitate foreign language learning and can be extended to other fields of auditory and clinical research and even other senses. PMID:28617861

The Suitability of Cloud-Based Speech Recognition Engines for Language Learning

ERIC Educational Resources Information Center

Daniels, Paul; Iwago, Koji

2017-01-01

As online automatic speech recognition (ASR) engines become more accurate and more widely implemented with call software, it becomes important to evaluate the effectiveness and the accuracy of these recognition engines using authentic speech samples. This study investigates two of the most prominent cloud-based speech recognition engines--Apple's…

Reaction Times of Normal Listeners to Laryngeal, Alaryngeal, and Synthetic Speech

ERIC Educational Resources Information Center

Evitts, Paul M.; Searl, Jeff

2006-01-01

The purpose of this study was to compare listener processing demands when decoding alaryngeal compared to laryngeal speech. Fifty-six listeners were presented with single words produced by 1 proficient speaker from 5 different modes of speech: normal, tracheosophageal (TE), esophageal (ES), electrolaryngeal (EL), and synthetic speech (SS).…

Breathing-Impaired Speech after Brain Haemorrhage: A Case Study

ERIC Educational Resources Information Center

Heselwood, Barry

2007-01-01

Results are presented from an auditory and acoustic analysis of the speech of an adult male with impaired prosody and articulation due to brain haemorrhage. They show marked effects on phonation, speech rate and articulator velocity, and a speech rhythm disrupted by "intrusive" stresses. These effects are discussed in relation to the speaker's…

Perceptual and Acoustic Reliability Estimates for the Speech Disorders Classification System (SDCS)

ERIC Educational Resources Information Center

Shriberg, Lawrence D.; Fourakis, Marios; Hall, Sheryl D.; Karlsson, Heather B.; Lohmeier, Heather L.; McSweeny, Jane L.; Potter, Nancy L.; Scheer-Cohen, Alison R.; Strand, Edythe A.; Tilkens, Christie M.; Wilson, David L.

2010-01-01

A companion paper describes three extensions to a classification system for paediatric speech sound disorders termed the Speech Disorders Classification System (SDCS). The SDCS uses perceptual and acoustic data reduction methods to obtain information on a speaker's speech, prosody, and voice. The present paper provides reliability estimates for…

Automated Discovery of Speech Act Categories in Educational Games

ERIC Educational Resources Information Center

Rus, Vasile; Moldovan, Cristian; Niraula, Nobal; Graesser, Arthur C.

2012-01-01

In this paper we address the important task of automated discovery of speech act categories in dialogue-based, multi-party educational games. Speech acts are important in dialogue-based educational systems because they help infer the student speaker's intentions (the task of speech act classification) which in turn is crucial to providing adequate…

The Effects of Direct and Indirect Speech Acts on Native English and ESL Speakers' Perception of Teacher Written Feedback

ERIC Educational Resources Information Center

Baker, Wendy; Hansen Bricker, Rachel

2010-01-01

This study explores how second language (L2) learners perceive indirect (hedging or indirect speech acts) and direct written teacher feedback. Though research suggests that indirect speech acts may be more difficult to interpret than direct speech acts ([Champagne, 2001] and [Holtgraves, 1999]), using indirect speech acts is often encouraged in…

The role of left inferior frontal cortex during audiovisual speech perception in infants.

PubMed

Altvater-Mackensen, Nicole; Grossmann, Tobias

2016-06-01

In the first year of life, infants' speech perception attunes to their native language. While the behavioral changes associated with native language attunement are fairly well mapped, the underlying mechanisms and neural processes are still only poorly understood. Using fNIRS and eye tracking, the current study investigated 6-month-old infants' processing of audiovisual speech that contained matching or mismatching auditory and visual speech cues. Our results revealed that infants' speech-sensitive brain responses in inferior frontal brain regions were lateralized to the left hemisphere. Critically, our results further revealed that speech-sensitive left inferior frontal regions showed enhanced responses to matching when compared to mismatching audiovisual speech, and that infants with a preference to look at the speaker's mouth showed an enhanced left inferior frontal response to speech compared to infants with a preference to look at the speaker's eyes. These results suggest that left inferior frontal regions play a crucial role in associating information from different modalities during native language attunement, fostering the formation of multimodal phonological categories. Copyright © 2016 Elsevier Inc. All rights reserved.

Robust matching for voice recognition

NASA Astrophysics Data System (ADS)

Higgins, Alan; Bahler, L.; Porter, J.; Blais, P.

1994-10-01

This paper describes an automated method of comparing a voice sample of an unknown individual with samples from known speakers in order to establish or verify the individual's identity. The method is based on a statistical pattern matching approach that employs a simple training procedure, requires no human intervention (transcription, work or phonetic marketing, etc.), and makes no assumptions regarding the expected form of the statistical distributions of the observations. The content of the speech material (vocabulary, grammar, etc.) is not assumed to be constrained in any way. An algorithm is described which incorporates frame pruning and channel equalization processes designed to achieve robust performance with reasonable computational resources. An experimental implementation demonstrating the feasibility of the concept is described.