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.

Analysis of human scream and its impact on text-independent speaker verification.

PubMed

Hansen, John H L; Nandwana, Mahesh Kumar; Shokouhi, Navid

2017-04-01

Scream is defined as sustained, high-energy vocalizations that lack phonological structure. Lack of phonological structure is how scream is identified from other forms of loud vocalization, such as "yell." This study investigates the acoustic aspects of screams and addresses those that are known to prevent standard speaker identification systems from recognizing the identity of screaming speakers. It is well established that speaker variability due to changes in vocal effort and Lombard effect contribute to degraded performance in automatic speech systems (i.e., speech recognition, speaker identification, diarization, etc.). However, previous research in the general area of speaker variability has concentrated on human speech production, whereas less is known about non-speech vocalizations. The UT-NonSpeech corpus is developed here to investigate speaker verification from scream samples. This study considers a detailed analysis in terms of fundamental frequency, spectral peak shift, frame energy distribution, and spectral tilt. It is shown that traditional speaker recognition based on the Gaussian mixture models-universal background model framework is unreliable when evaluated with screams.

On compensation of mismatched recording conditions in the Bayesian approach for forensic automatic speaker recognition.

PubMed

Botti, F; Alexander, A; Drygajlo, A

2004-12-02

This paper deals with a procedure to compensate for mismatched recording conditions in forensic speaker recognition, using a statistical score normalization. Bayesian interpretation of the evidence in forensic automatic speaker recognition depends on three sets of recordings in order to perform forensic casework: reference (R) and control (C) recordings of the suspect, and a potential population database (P), as well as a questioned recording (QR) . The requirement of similar recording conditions between suspect control database (C) and the questioned recording (QR) is often not satisfied in real forensic cases. The aim of this paper is to investigate a procedure of normalization of scores, which is based on an adaptation of the Test-normalization (T-norm) [2] technique used in the speaker verification domain, to compensate for the mismatch. Polyphone IPSC-02 database and ASPIC (an automatic speaker recognition system developed by EPFL and IPS-UNIL in Lausanne, Switzerland) were used in order to test the normalization procedure. Experimental results for three different recording condition scenarios are presented using Tippett plots and the effect of the compensation on the evaluation of the strength of the evidence is discussed.

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

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...DNNs trained with real Mixer 2 multichannel data perform only slightly better than DNNs trained with synthetic multichannel data for microphone SR on...Mixer 6. Large re- ductions in pooled error rates of 50% EER and 30% min DCF are achieved using DNNs trained on real Mixer 2 data. Nearly the same

Phoneme Error Pattern by Heritage Speakers of Spanish on an English Word Recognition Test.

PubMed

Shi, Lu-Feng

2017-04-01

Heritage speakers acquire their native language from home use in their early childhood. As the native language is typically a minority language in the society, these individuals receive their formal education in the majority language and eventually develop greater competency with the majority than their native language. To date, there have not been specific research attempts to understand word recognition by heritage speakers. It is not clear if and to what degree we may infer from evidence based on bilingual listeners in general. This preliminary study investigated how heritage speakers of Spanish perform on an English word recognition test and analyzed their phoneme errors. A prospective, cross-sectional, observational design was employed. Twelve normal-hearing adult Spanish heritage speakers (four men, eight women, 20-38 yr old) participated in the study. Their language background was obtained through the Language Experience and Proficiency Questionnaire. Nine English monolingual listeners (three men, six women, 20-41 yr old) were also included for comparison purposes. Listeners were presented with 200 Northwestern University Auditory Test No. 6 words in quiet. They repeated each word orally and in writing. Their responses were scored by word, word-initial consonant, vowel, and word-final consonant. Performance was compared between groups with Student's t test or analysis of variance. Group-specific error patterns were primarily descriptive, but intergroup comparisons were made using 95% or 99% confidence intervals for proportional data. The two groups of listeners yielded comparable scores when their responses were examined by word, vowel, and final consonant. However, heritage speakers of Spanish misidentified significantly more word-initial consonants and had significantly more difficulty with initial /p, b, h/ than their monolingual peers. The two groups yielded similar patterns for vowel and word-final consonants, but heritage speakers made significantly fewer errors with /e/ and more errors with word-final /p, k/. Data reported in the present study lead to a twofold conclusion. On the one hand, normal-hearing heritage speakers of Spanish may misidentify English phonemes in patterns different from those of English monolingual listeners. Not all phoneme errors can be readily understood by comparing Spanish and English phonology, suggesting that Spanish heritage speakers differ in performance from other Spanish-English bilingual listeners. On the other hand, the absolute number of errors and the error pattern of most phonemes were comparable between English monolingual listeners and Spanish heritage speakers, suggesting that audiologists may assess word recognition in quiet in the same way for these two groups of listeners, if diagnosis is based on words, not phonemes. American Academy of Audiology

Hemispheric lateralization of linguistic prosody recognition in comparison to speech and speaker recognition.

PubMed

Kreitewolf, Jens; Friederici, Angela D; von Kriegstein, Katharina

2014-11-15

Hemispheric specialization for linguistic prosody is a controversial issue. While it is commonly assumed that linguistic prosody and emotional prosody are preferentially processed in the right hemisphere, neuropsychological work directly comparing processes of linguistic prosody and emotional prosody suggests a predominant role of the left hemisphere for linguistic prosody processing. Here, we used two functional magnetic resonance imaging (fMRI) experiments to clarify the role of left and right hemispheres in the neural processing of linguistic prosody. In the first experiment, we sought to confirm previous findings showing that linguistic prosody processing compared to other speech-related processes predominantly involves the right hemisphere. Unlike previous studies, we controlled for stimulus influences by employing a prosody and speech task using the same speech material. The second experiment was designed to investigate whether a left-hemispheric involvement in linguistic prosody processing is specific to contrasts between linguistic prosody and emotional prosody or whether it also occurs when linguistic prosody is contrasted against other non-linguistic processes (i.e., speaker recognition). Prosody and speaker tasks were performed on the same stimulus material. In both experiments, linguistic prosody processing was associated with activity in temporal, frontal, parietal and cerebellar regions. Activation in temporo-frontal regions showed differential lateralization depending on whether the control task required recognition of speech or speaker: recognition of linguistic prosody predominantly involved right temporo-frontal areas when it was contrasted against speech recognition; when contrasted against speaker recognition, recognition of linguistic prosody predominantly involved left temporo-frontal areas. The results show that linguistic prosody processing involves functions of both hemispheres and suggest that recognition of linguistic prosody is based on an inter-hemispheric mechanism which exploits both a right-hemispheric sensitivity to pitch information and a left-hemispheric dominance in speech processing. Copyright © 2014 Elsevier Inc. All rights reserved.

Fifty years of progress in speech and speaker recognition

NASA Astrophysics Data System (ADS)

Furui, Sadaoki

2004-10-01

Speech and speaker recognition technology has made very significant progress in the past 50 years. The progress can be summarized by the following changes: (1) from template matching to corpus-base statistical modeling, e.g., HMM and n-grams, (2) from filter bank/spectral resonance to Cepstral features (Cepstrum + DCepstrum + DDCepstrum), (3) from heuristic time-normalization to DTW/DP matching, (4) from gdistanceh-based to likelihood-based methods, (5) from maximum likelihood to discriminative approach, e.g., MCE/GPD and MMI, (6) from isolated word to continuous speech recognition, (7) from small vocabulary to large vocabulary recognition, (8) from context-independent units to context-dependent units for recognition, (9) from clean speech to noisy/telephone speech recognition, (10) from single speaker to speaker-independent/adaptive recognition, (11) from monologue to dialogue/conversation recognition, (12) from read speech to spontaneous speech recognition, (13) from recognition to understanding, (14) from single-modality (audio signal only) to multi-modal (audio/visual) speech recognition, (15) from hardware recognizer to software recognizer, and (16) from no commercial application to many practical commercial applications. Most of these advances have taken place in both the fields of speech recognition and speaker recognition. The majority of technological changes have been directed toward the purpose of increasing robustness of recognition, including many other additional important techniques not noted above.

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.

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…

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.

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.

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.

Speech Clarity Index (Ψ): A Distance-Based Speech Quality Indicator and Recognition Rate Prediction for Dysarthric Speakers with Cerebral Palsy

NASA Astrophysics Data System (ADS)

Kayasith, Prakasith; Theeramunkong, Thanaruk

It is a tedious and subjective task to measure severity of a dysarthria by manually evaluating his/her speech using available standard assessment methods based on human perception. This paper presents an automated approach to assess speech quality of a dysarthric speaker with cerebral palsy. With the consideration of two complementary factors, speech consistency and speech distinction, a speech quality indicator called speech clarity index (Ψ) is proposed as a measure of the speaker's ability to produce consistent speech signal for a certain word and distinguished speech signal for different words. As an application, it can be used to assess speech quality and forecast speech recognition rate of speech made by an individual dysarthric speaker before actual exhaustive implementation of an automatic speech recognition system for the speaker. The effectiveness of Ψ as a speech recognition rate predictor is evaluated by rank-order inconsistency, correlation coefficient, and root-mean-square of difference. The evaluations had been done by comparing its predicted recognition rates with ones predicted by the standard methods called the articulatory and intelligibility tests based on the two recognition systems (HMM and ANN). The results show that Ψ is a promising indicator for predicting recognition rate of dysarthric speech. All experiments had been done on speech corpus composed of speech data from eight normal speakers and eight dysarthric speakers.

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.

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.

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…

Bilingual Language Switching: Production vs. Recognition

PubMed Central

Mosca, Michela; de Bot, Kees

2017-01-01

This study aims at assessing how bilinguals select words in the appropriate language in production and recognition while minimizing interference from the non-appropriate language. Two prominent models are considered which assume that when one language is in use, the other is suppressed. The Inhibitory Control (IC) model suggests that, in both production and recognition, the amount of inhibition on the non-target language is greater for the stronger compared to the weaker language. In contrast, the Bilingual Interactive Activation (BIA) model proposes that, in language recognition, the amount of inhibition on the weaker language is stronger than otherwise. To investigate whether bilingual language production and recognition can be accounted for by a single model of bilingual processing, we tested a group of native speakers of Dutch (L1), advanced speakers of English (L2) in a bilingual recognition and production task. Specifically, language switching costs were measured while participants performed a lexical decision (recognition) and a picture naming (production) task involving language switching. Results suggest that while in language recognition the amount of inhibition applied to the non-appropriate language increases along with its dominance as predicted by the IC model, in production the amount of inhibition applied to the non-relevant language is not related to language dominance, but rather it may be modulated by speakers' unconscious strategies to foster the weaker language. This difference indicates that bilingual language recognition and production might rely on different processing mechanisms and cannot be accounted within one of the existing models of bilingual language processing. PMID:28638361

Bilingual Language Switching: Production vs. Recognition.

PubMed

Mosca, Michela; de Bot, Kees

2017-01-01

This study aims at assessing how bilinguals select words in the appropriate language in production and recognition while minimizing interference from the non-appropriate language. Two prominent models are considered which assume that when one language is in use, the other is suppressed. The Inhibitory Control (IC) model suggests that, in both production and recognition, the amount of inhibition on the non-target language is greater for the stronger compared to the weaker language. In contrast, the Bilingual Interactive Activation (BIA) model proposes that, in language recognition, the amount of inhibition on the weaker language is stronger than otherwise. To investigate whether bilingual language production and recognition can be accounted for by a single model of bilingual processing, we tested a group of native speakers of Dutch (L1), advanced speakers of English (L2) in a bilingual recognition and production task. Specifically, language switching costs were measured while participants performed a lexical decision (recognition) and a picture naming (production) task involving language switching. Results suggest that while in language recognition the amount of inhibition applied to the non-appropriate language increases along with its dominance as predicted by the IC model, in production the amount of inhibition applied to the non-relevant language is not related to language dominance, but rather it may be modulated by speakers' unconscious strategies to foster the weaker language. This difference indicates that bilingual language recognition and production might rely on different processing mechanisms and cannot be accounted within one of the existing models of bilingual language processing.

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.

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.

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.

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.

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.

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

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.

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.

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.

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.

ERP Evidence of Hemispheric Independence in Visual Word Recognition

ERIC Educational Resources Information Center

Nemrodov, Dan; Harpaz, Yuval; Javitt, Daniel C.; Lavidor, Michal

2011-01-01

This study examined the capability of the left hemisphere (LH) and the right hemisphere (RH) to perform a visual recognition task independently as formulated by the Direct Access Model (Fernandino, Iacoboni, & Zaidel, 2007). Healthy native Hebrew speakers were asked to categorize nouns and non-words (created from nouns by transposing two middle…

Building Searchable Collections of Enterprise Speech Data.

ERIC Educational Resources Information Center

Cooper, James W.; Viswanathan, Mahesh; Byron, Donna; Chan, Margaret

The study has applied speech recognition and text-mining technologies to a set of recorded outbound marketing calls and analyzed the results. Since speaker-independent speech recognition technology results in a significantly lower recognition rate than that found when the recognizer is trained for a particular speaker, a number of post-processing…

The Development of Word Recognition in a Second Language.

ERIC Educational Resources Information Center

Muljani, D.; Koda, Keiko; Moates, Danny R.

1998-01-01

A study investigated differences in English word recognition in native speakers of Indonesian (an alphabetic language) and Chinese (a logographic languages) learning English as a Second Language. Results largely confirmed the hypothesis that an alphabetic first language would predict better word recognition in speakers of an alphabetic language,…

Voice Recognition Software Accuracy with Second Language Speakers of English.

ERIC Educational Resources Information Center

Coniam, D.

1999-01-01

Explores the potential of the use of voice-recognition technology with second-language speakers of English. Involves the analysis of the output produced by a small group of very competent second-language subjects reading a text into the voice recognition software Dragon Systems "Dragon NaturallySpeaking." (Author/VWL)

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.

Data Selection for Within-Class Covariance Estimation

DTIC Science & Technology

2016-09-08

recognition performance. While developers have typically exploited the vast archive of speaker labeled data available from earlier NIST evaluations...utterances from a large population of speakers. Fortunately, participants in NIST evaluations have access to a vast repository of legacy data from earlier...previous NIST evaluations. Training data for the UBM and T-matrix was obtained from the NIST Switchboard 2 phases 2-5 [12] and SRE04/05/06 utterances

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…

Bridge Health Monitoring Using a Machine Learning Strategy

DOT National Transportation Integrated Search

2017-01-01

The goal of this project was to cast the SHM problem within a statistical pattern recognition framework. Techniques borrowed from speaker recognition, particularly speaker verification, were used as this discipline deals with problems very similar to...

The search for common ground: Part I. Lexical performance by linguistically diverse learners.

PubMed

Windsor, Jennifer; Kohnert, Kathryn

2004-08-01

This study examines lexical performance by 3 groups of linguistically diverse school-age learners: English-only speakers with primary language impairment (LI), typical English-only speakers (EO), and typical bilingual Spanish-English speakers (BI). The accuracy and response time (RT) of 100 8- to 13-year-old children in word recognition and picture-naming tasks were analyzed. Within each task, stimulus difficulty was manipulated to include very easy stimuli (words that were high frequency/had an early age of acquisition in English) and more difficult stimuli (words of low frequency/late age of acquisition [AOA]). There was no difference among groups in real-word recognition accuracy or RT; all 3 groups showed lower accuracy with low-frequency words. In picture naming, all 3 groups showed a longer RT for words with a late AOA, although AOA had a disproportionate negative impact on BI performance. The EO group was faster and more accurate than both LI and BI groups in conditions with later acquired stimuli. Results are discussed in terms of quantitative differences separating EO children from the other 2 groups and qualitative similarities linking monolingual children with and without LI.

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.

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.

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

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.

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.

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.

Translation Ambiguity but Not Word Class Predicts Translation Performance

ERIC Educational Resources Information Center

Prior, Anat; Kroll, Judith F.; Macwhinney, Brian

2013-01-01

We investigated the influence of word class and translation ambiguity on cross-linguistic representation and processing. Bilingual speakers of English and Spanish performed translation production and translation recognition tasks on nouns and verbs in both languages. Words either had a single translation or more than one translation. Translation…

Bilingual Computerized Speech Recognition Screening for Depression Symptoms

ERIC Educational Resources Information Center

Gonzalez, Gerardo; Carter, Colby; Blanes, Erika

2007-01-01

The Voice-Interactive Depression Assessment System (VIDAS) is a computerized speech recognition application for screening depression based on the Center for Epidemiological Studies--Depression scale in English and Spanish. Study 1 included 50 English and 47 Spanish speakers. Study 2 involved 108 English and 109 Spanish speakers. Participants…

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.

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

Functional connectivity between face-movement and speech-intelligibility areas during auditory-only speech perception.

PubMed

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.

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

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.

Speech-on-speech masking with variable access to the linguistic content of the masker speech for native and nonnative english speakers.

PubMed

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

2014-04-01

Masking release for an English sentence-recognition task in the presence of foreign-accented English speech compared with native-accented English speech was reported in Calandruccio et al (2010a). 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. 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 Affiliationect masking release. A mixed-model design with within-subject (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. Three listener groups were tested, including monolingual English speakers with normal hearing, nonnative English speakers with normal hearing, and monolingual English speakers with hearing loss. The nonnative English speakers were from various native language backgrounds, not including Mandarin (or any other Chinese dialect). Listeners with hearing loss had symmetric mild sloping to moderate sensorineural hearing loss. 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 key words within the sentences (100 key words per masker condition). A mixed-model regression analysis was used to analyze the difference in performance scores between the masker conditions and listener groups. Monolingual English speakers with normal hearing benefited when the competing speech signal was foreign accented compared with native accented, allowing for improved speech recognition. Various levels of intelligibility across the foreign-accented speech maskers did not influence results. Neither the nonnative English-speaking 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. Slight modifications between the target and the masker speech allowed monolingual English speakers 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. American Academy of Audiology.

Reducing computation in an i-vector speaker recognition system using a tree-structured universal background model

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

McClanahan, Richard; De Leon, Phillip L.

The majority of state-of-the-art speaker recognition systems (SR) utilize speaker models that are derived from an adapted universal background model (UBM) in the form of a Gaussian mixture model (GMM). This is true for GMM supervector systems, joint factor analysis systems, and most recently i-vector systems. In all of the identified systems, the posterior probabilities and sufficient statistics calculations represent a computational bottleneck in both enrollment and testing. We propose a multi-layered hash system, employing a tree-structured GMM–UBM which uses Runnalls’ Gaussian mixture reduction technique, in order to reduce the number of these calculations. Moreover, with this tree-structured hash, wemore » can trade-off reduction in computation with a corresponding degradation of equal error rate (EER). As an example, we also reduce this computation by a factor of 15× while incurring less than 10% relative degradation of EER (or 0.3% absolute EER) when evaluated with NIST 2010 speaker recognition evaluation (SRE) telephone data.« less

Reducing computation in an i-vector speaker recognition system using a tree-structured universal background model

DOE PAGES

McClanahan, Richard; De Leon, Phillip L.

2014-08-20

The majority of state-of-the-art speaker recognition systems (SR) utilize speaker models that are derived from an adapted universal background model (UBM) in the form of a Gaussian mixture model (GMM). This is true for GMM supervector systems, joint factor analysis systems, and most recently i-vector systems. In all of the identified systems, the posterior probabilities and sufficient statistics calculations represent a computational bottleneck in both enrollment and testing. We propose a multi-layered hash system, employing a tree-structured GMM–UBM which uses Runnalls’ Gaussian mixture reduction technique, in order to reduce the number of these calculations. Moreover, with this tree-structured hash, wemore » can trade-off reduction in computation with a corresponding degradation of equal error rate (EER). As an example, we also reduce this computation by a factor of 15× while incurring less than 10% relative degradation of EER (or 0.3% absolute EER) when evaluated with NIST 2010 speaker recognition evaluation (SRE) telephone data.« less

The Use of Voice Cues for Speaker Gender Recognition in Cochlear Implant Recipients

ERIC Educational Resources Information Center

Meister, Hartmut; Fürsen, Katrin; Streicher, Barbara; Lang-Roth, Ruth; Walger, Martin

2016-01-01

Purpose: The focus of this study was to examine the influence of fundamental frequency (F0) and vocal tract length (VTL) modifications on speaker gender recognition in cochlear implant (CI) recipients for different stimulus types. Method: Single words and sentences were manipulated using isolated or combined F0 and VTL cues. Using an 11-point…

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.

Lexical constraints in second language learning: Evidence on grammatical gender in German*

PubMed Central

BOBB, SUSAN C.; KROLL, JUDITH F.; JACKSON, CARRIE N.

2015-01-01

The present study asked whether or not the apparent insensitivity of second language (L2) learners to grammatical gender violations reflects an inability to use grammatical information during L2 lexical processing. Native German speakers and English speakers with intermediate to advanced L2 proficiency in German performed a translation-recognition task. On critical trials, an incorrect translation was presented that either matched or mismatched the grammatical gender of the correct translation. Results show interference for native German speakers in conditions in which the incorrect translation matched the gender of the correct translation. Native English speakers, regardless of German proficiency, were insensitive to the gender mismatch. In contrast, these same participants were correctly able to assign gender to critical items. These findings suggest a dissociation between explicit knowledge and the ability to use that information under speeded processing conditions and demonstrate the difficulty of L2 gender processing at the lexical level. PMID:26346327

``The perceptual bases of speaker identity'' revisited

NASA Astrophysics Data System (ADS)

Voiers, William D.

2003-10-01

A series of experiments begun 40 years ago [W. D. Voiers, J. Acoust. Soc. Am. 36, 1065-1073 (1964)] was concerned with identifying the perceived voice traits (PVTs) on which human recognition of voices depends. It culminated with the development of a voice taxonomy based on 20 PVTs and a set of highly reliable rating scales for classifying voices with respect to those PVTs. The development of a perceptual voice taxonomy was motivated by the need for a practical method of evaluating speaker recognizability in voice communication systems. The Diagnostic Speaker Recognition Test (DSRT) evaluates the effects of systems on speaker recognizability as reflected in changes in the inter-listener reliability of voice ratings on the 20 PVTs. The DSRT thus provides a qualitative, as well as quantitative, evaluation of the effects of a system on speaker recognizability. A fringe benefit of this project is PVT rating data for a sample of 680 voices. [Work partially supported by USAFRL.

DOMAIN MISMATCH COMPENSATION FOR SPEAKER RECOGNITION USING A LIBRARY OF WHITENERS

DTIC Science & Technology

2015-05-29

DOMAIN MISMATCH COMPENSATION FOR SPEAKER RECOGNITION USING A LIBRARY OF WHITENERS Elliot Singer and Douglas Reynolds Massachusetts Institute of...development data is assumed to be unavailable. The method is based on a generalization of data whitening used in association with i-vector length...normalization and utilizes a library of whitening transforms trained at system development time using strictly out-of-domain data. The approach is

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.

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.

Processing Lexical and Speaker Information in Repetition and Semantic/Associative Priming

ERIC Educational Resources Information Center

Lee, Chao-Yang; Zhang, Yu

2018-01-01

The purpose of this study is to investigate the interaction between processing lexical and speaker-specific information in spoken word recognition. The specific question is whether repetition and semantic/associative priming is reduced when the prime and target are produced by different speakers. In Experiment 1, the prime and target were repeated…

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

Automatic speech recognition technology development at ITT Defense Communications Division

NASA Technical Reports Server (NTRS)

White, George M.

1977-01-01

An assessment of the applications of automatic speech recognition to defense communication systems is presented. Future research efforts include investigations into the following areas: (1) dynamic programming; (2) recognition of speech degraded by noise; (3) speaker independent recognition; (4) large vocabulary recognition; (5) word spotting and continuous speech recognition; and (6) isolated word recognition.

Effects of low speed wind on the recognition/identification and pass-through communication tasks of auditory situation awareness afforded by military hearing protection/enhancement devices and tactical communication and protective systems.

PubMed

Lee, Kichol; Casali, John G

2016-01-01

To investigate the effect of controlled low-speed wind-noise on the auditory situation awareness performance afforded by military hearing protection/enhancement devices (HPED) and tactical communication and protective systems (TCAPS). Recognition/identification and pass-through communications tasks were separately conducted under three wind conditions (0, 5, and 10 mph). Subjects wore two in-ear-type TCAPS, one earmuff-type TCAPS, a Combat Arms Earplug in its 'open' or pass-through setting, and an EB-15LE electronic earplug. Devices with electronic gain systems were tested under two gain settings: 'unity' and 'max'. Testing without any device (open ear) was conducted as a control. Ten subjects were recruited from the student population at Virginia Tech. Audiometric requirements were 25 dBHL or better at 500, 1000, 2000, 4000, and 8000 Hz in both ears. Performance on the interaction of communication task-by-device was significantly different only in 0 mph wind speed. The between-device performance differences varied with azimuthal speaker locations. It is evident from this study that stable (non-gusting) wind speeds up to 10 mph did not significantly degrade recognition/identification task performance and pass-through communication performance of the group of HPEDs and TCAPS tested. However, the various devices performed differently as the test sound signal speaker location was varied and it appears that physical as well as electronic features may have contributed to this directional result.

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.

Security training symposium: Meeting the challenge: Firearms and explosives recognition and detection

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

Not Available

1990-09-01

These conference proceedings have been prepared in support of the US Nuclear Regulatory Commission's Security Training Symposium on Meeting the Challenge -- Firearms and Explosives Recognition and Detection,'' November 28 through 30, 1989, in Bethesda, Maryland. This document contains the edited transcripts of the guest speakers. It also contains some of the speakers' formal papers that were distributed and some of the slides that were shown at the symposium (Appendix A).

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.

Fast Morphological Effects in First and Second Language Word Recognition

ERIC Educational Resources Information Center

Diependaele, Kevin; Dunabeitia, Jon Andoni; Morris, Joanna; Keuleers, Emmanuel

2011-01-01

In three experiments we compared the performance of native English speakers to that of Spanish-English and Dutch-English bilinguals on a masked morphological priming lexical decision task. The results do not show significant differences across the three experiments. In line with recent meta-analyses, we observed a graded pattern of facilitation…

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.

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.

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.

Vocal Identity Recognition in Autism Spectrum Disorder

PubMed Central

Lin, I-Fan; Yamada, Takashi; Komine, Yoko; Kato, Nobumasa; Kato, Masaharu; Kashino, Makio

2015-01-01

Voices can convey information about a speaker. When forming an abstract representation of a speaker, it is important to extract relevant features from acoustic signals that are invariant to the modulation of these signals. This study investigated the way in which individuals with autism spectrum disorder (ASD) recognize and memorize vocal identity. The ASD group and control group performed similarly in a task when asked to choose the name of the newly-learned speaker based on his or her voice, and the ASD group outperformed the control group in a subsequent familiarity test when asked to discriminate the previously trained voices and untrained voices. These findings suggest that individuals with ASD recognized and memorized voices as well as the neurotypical individuals did, but they categorized voices in a different way: individuals with ASD categorized voices quantitatively based on the exact acoustic features, while neurotypical individuals categorized voices qualitatively based on the acoustic patterns correlated to the speakers' physical and mental properties. PMID:26070199

Vocal Identity Recognition in Autism Spectrum Disorder.

PubMed

Lin, I-Fan; Yamada, Takashi; Komine, Yoko; Kato, Nobumasa; Kato, Masaharu; Kashino, Makio

2015-01-01

Voices can convey information about a speaker. When forming an abstract representation of a speaker, it is important to extract relevant features from acoustic signals that are invariant to the modulation of these signals. This study investigated the way in which individuals with autism spectrum disorder (ASD) recognize and memorize vocal identity. The ASD group and control group performed similarly in a task when asked to choose the name of the newly-learned speaker based on his or her voice, and the ASD group outperformed the control group in a subsequent familiarity test when asked to discriminate the previously trained voices and untrained voices. These findings suggest that individuals with ASD recognized and memorized voices as well as the neurotypical individuals did, but they categorized voices in a different way: individuals with ASD categorized voices quantitatively based on the exact acoustic features, while neurotypical individuals categorized voices qualitatively based on the acoustic patterns correlated to the speakers' physical and mental properties.

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

Speaker Verification Using SVM

DTIC Science & Technology

2010-11-01

application the required resources are provided by the phone itself. Speaker recognition can be used in many areas, like: • homeland security: airport ... security , strengthening the national borders, in travel documents, visas; • enterprise-wide network security infrastructures; • secure electronic

Memory for syntax despite amnesia.

PubMed

Ferreira, Victor S; Bock, Kathryn; Wilson, Michael P; Cohen, Neal J

2008-09-01

Syntactic persistence is a tendency for speakers to reproduce sentence structures independently of accompanying meanings, words, or sounds. The memory mechanisms behind syntactic persistence are not fully understood. Although some properties of syntactic persistence suggest a role for procedural memory, current evidence suggests that procedural memory (unlike declarative memory) does not maintain the abstract, relational features that are inherent to syntactic structures. In a study evaluating the contribution of procedural memory to syntactic persistence, patients with anterograde amnesia and matched control speakers reproduced prime sentences with different syntactic structures; reproduced 0, 1, 6, or 10 neutral sentences; then spontaneously described pictures that elicited the primed structures; and finally made recognition judgments for the prime sentences. Amnesic and control speakers showed significant and equivalent syntactic persistence, despite the amnesic speakers' profoundly impaired recognition memory for the primes. Thus, syntax is maintained by procedural-memory mechanisms. This result reveals that procedural memory is capable of supporting abstract, relational knowledge.

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.

Quantity Recognition among Speakers of an Anumeric Language

ERIC Educational Resources Information Center

Everett, Caleb; Madora, Keren

2012-01-01

Recent research has suggested that the Piraha, an Amazonian tribe with a number-less language, are able to match quantities greater than 3 if the matching task does not require recall or spatial transposition. This finding contravenes previous work among the Piraha. In this study, we re-tested the Pirahas' performance in the crucial one-to-one…

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.

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.

"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.

Semantic Ambiguity Effects in L2 Word Recognition.

PubMed

Ishida, Tomomi

2018-06-01

The present study examined the ambiguity effects in second language (L2) word recognition. Previous studies on first language (L1) lexical processing have observed that ambiguous words are recognized faster and more accurately than unambiguous words on lexical decision tasks. In this research, L1 and L2 speakers of English were asked whether a letter string on a computer screen was an English word or not. An ambiguity advantage was found for both groups and greater ambiguity effects were found for the non-native speaker group when compared to the native speaker group. The findings imply that the larger ambiguity advantage for L2 processing is due to their slower response time in producing adequate feedback activation from the semantic level to the orthographic level.

[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.

Attempting to "Increase Intake from the Input": Attention and Word Learning in Children with Autism.

PubMed

Tenenbaum, Elena J; Amso, Dima; Righi, Giulia; Sheinkopf, Stephen J

2017-06-01

Previous work has demonstrated that social attention is related to early language abilities. We explored whether we can facilitate word learning among children with autism by directing attention to areas of the scene that have been demonstrated as relevant for successful word learning. We tracked eye movements to faces and objects while children watched videos of a woman teaching them new words. Test trials measured participants' recognition of these novel word-object pairings. Results indicate that for children with autism and typically developing children, pointing to the speaker's mouth while labeling a novel object impaired performance, likely because it distracted participants from the target object. In contrast, for children with autism, holding the object close to the speaker's mouth improved performance.

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%.

Mark My Words: Tone of Voice Changes Affective Word Representations in Memory

PubMed Central

Schirmer, Annett

2010-01-01

The present study explored the effect of speaker prosody on the representation of words in memory. To this end, participants were presented with a series of words and asked to remember the words for a subsequent recognition test. During study, words were presented auditorily with an emotional or neutral prosody, whereas during test, words were presented visually. Recognition performance was comparable for words studied with emotional and neutral prosody. However, subsequent valence ratings indicated that study prosody changed the affective representation of words in memory. Compared to words with neutral prosody, words with sad prosody were later rated as more negative and words with happy prosody were later rated as more positive. Interestingly, the participants' ability to remember study prosody failed to predict this effect, suggesting that changes in word valence were implicit and associated with initial word processing rather than word retrieval. Taken together these results identify a mechanism by which speakers can have sustained effects on listener attitudes towards word referents. PMID:20169154

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.

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.

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.

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.

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.

NATIONAL PREPAREDNESS: Integrating New and Existing Technology and Information Sharing into an Effective Homeland Security Strategy

DTIC Science & Technology

2002-06-07

Continue to Develop and Refine Emerging Technology • Some of the emerging biometric devices, such as iris scans and facial recognition systems...such as iris scans and facial recognition systems, facial recognition systems, and speaker verification systems. (976301)

A Limited-Vocabulary, Multi-Speaker Automatic Isolated Word Recognition System.

ERIC Educational Resources Information Center

Paul, James E., Jr.

Techniques for automatic recognition of isolated words are investigated, and a computer simulation of a word recognition system is effected. Considered in detail are data acquisition and digitizing, word detection, amplitude and time normalization, short-time spectral estimation including spectral windowing, spectral envelope approximation,…

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).

Depression recognition and capacity for self-report among ethnically diverse nursing homes residents: Evidence of disparities in screening.

PubMed

Chun, Audrey; Reinhardt, Joann P; Ramirez, Mildred; Ellis, Julie M; Silver, Stephanie; Burack, Orah; Eimicke, Joseph P; Cimarolli, Verena; Teresi, Jeanne A

2017-12-01

To examine agreement between Minimum Data Set clinician ratings and researcher assessments of depression among ethnically diverse nursing home residents using the 9-item Patient Health Questionnaire. Although depression is common among nursing homes residents, its recognition remains a challenge. Observational baseline data from a longitudinal intervention study. Sample of 155 residents from 12 long-term care units in one US facility; 50 were interviewed in Spanish. Convergence between clinician and researcher ratings was examined for (i) self-report capacity, (ii) suicidal ideation, (iii) at least moderate depression, (iv) Patient Health Questionnaire severity scores. Experiences by clinical raters using the depression assessment were analysed. The intraclass correlation coefficient was used to examine concordance and Cohen's kappa to examine agreement between clinicians and researchers. Moderate agreement (κ = 0.52) was observed in determination of capacity and poor to fair agreement in reporting suicidal ideation (κ = 0.10-0.37) across time intervals. Poor agreement was observed in classification of at least moderate depression (κ = -0.02 to 0.24), lower than the maximum kappa obtainable (0.58-0.85). Eight assessors indicated problems assessing Spanish-speaking residents. Among Spanish speakers, researchers identified 16% with Patient Health Questionnaire scores of 10 or greater, and 14% with thoughts of self-harm whilst clinicians identified 6% and 0%, respectively. This study advances the field of depression recognition in long-term care by identification of possible challenges in assessing Spanish speakers. Use of the Patient Health Questionnaire requires further investigation, particularly among non-English speakers. Depression screening for ethnically diverse nursing home residents is required, as underreporting of depression and suicidal ideation among Spanish speakers may result in lack of depression recognition and referral for evaluation and treatment. Training in depression recognition is imperative to improve the recognition, evaluation and treatment of depression in older people living in nursing homes. © 2017 John Wiley & Sons Ltd.

Gender Differences in the Recognition of Vocal Emotions

PubMed Central

Lausen, Adi; Schacht, Annekathrin

2018-01-01

The conflicting findings from the few studies conducted with regard to gender differences in the recognition of vocal expressions of emotion have left the exact nature of these differences unclear. Several investigators have argued that a comprehensive understanding of gender differences in vocal emotion recognition can only be achieved by replicating these studies while accounting for influential factors such as stimulus type, gender-balanced samples, number of encoders, decoders, and emotional categories. This study aimed to account for these factors by investigating whether emotion recognition from vocal expressions differs as a function of both listeners' and speakers' gender. A total of N = 290 participants were randomly and equally allocated to two groups. One group listened to words and pseudo-words, while the other group listened to sentences and affect bursts. Participants were asked to categorize the stimuli with respect to the expressed emotions in a fixed-choice response format. Overall, females were more accurate than males when decoding vocal emotions, however, when testing for specific emotions these differences were small in magnitude. Speakers' gender had a significant impact on how listeners' judged emotions from the voice. The group listening to words and pseudo-words had higher identification rates for emotions spoken by male than by female actors, whereas in the group listening to sentences and affect bursts the identification rates were higher when emotions were uttered by female than male actors. The mixed pattern for emotion-specific effects, however, indicates that, in the vocal channel, the reliability of emotion judgments is not systematically influenced by speakers' gender and the related stereotypes of emotional expressivity. Together, these results extend previous findings by showing effects of listeners' and speakers' gender on the recognition of vocal emotions. They stress the importance of distinguishing these factors to explain recognition ability in the processing of emotional prosody. PMID:29922202

ICPR-2016 - International Conference on Pattern Recognition

Science.gov Websites

Learning for Scene Understanding" Speakers ICPR2016 PAPER AWARDS Best Piero Zamperoni Student Paper -Paced Dictionary Learning for Cross-Domain Retrieval and Recognition Xu, Dan; Song, Jingkuan; Alameda discussions on recent advances in the fields of Pattern Recognition, Machine Learning and Computer Vision, and

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.

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

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

L2 Word Recognition: Influence of L1 Orthography on Multi-syllabic Word Recognition.

PubMed

Hamada, Megumi

2017-10-01

L2 reading research suggests that L1 orthographic experience influences L2 word recognition. Nevertheless, the findings on multi-syllabic words in English are still limited despite the fact that a vast majority of words are multi-syllabic. The study investigated whether L1 orthography influences the recognition of multi-syllabic words, focusing on the position of an embedded word. The participants were Arabic ESL learners, Chinese ESL learners, and native speakers of English. The task was a word search task, in which the participants identified a target word embedded in a pseudoword at the initial, middle, or final position. The search accuracy and speed indicated that all groups showed a strong preference for the initial position. The accuracy data further indicated group differences. The Arabic group showed higher accuracy in the final than middle, while the Chinese group showed the opposite and the native speakers showed no difference between the two positions. The findings suggest that L2 multi-syllabic word recognition involves unique processes.

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.

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.

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.

The Resolution of Visual Noise in Word Recognition

ERIC Educational Resources Information Center

Pae, Hye K.; Lee, Yong-Won

2015-01-01

This study examined lexical processing in English by native speakers of Korean and Chinese, compared to that of native speakers of English, using normal, alternated, and inverse fonts. Sixty four adult students participated in a lexical decision task. The findings demonstrated similarities and differences in accuracy and latency among the three L1…

Design and performance of a large vocabulary discrete word recognition system. Volume 1: Technical report. [real time computer technique for voice data processing

NASA Technical Reports Server (NTRS)

1973-01-01

The development, construction, and test of a 100-word vocabulary near real time word recognition system are reported. Included are reasonable replacement of any one or all 100 words in the vocabulary, rapid learning of a new speaker, storage and retrieval of training sets, verbal or manual single word deletion, continuous adaptation with verbal or manual error correction, on-line verification of vocabulary as spoken, system modes selectable via verification display keyboard, relationship of classified word to neighboring word, and a versatile input/output interface to accommodate a variety of applications.

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.

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.

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.

Second language experience modulates word retrieval effort in bilinguals: evidence from pupillometry

PubMed Central

Schmidtke, Jens

2014-01-01

Bilingual speakers often have less language experience compared to monolinguals as a result of speaking two languages and/or a later age of acquisition of the second language. This may result in weaker and less precise phonological representations of words in memory, which may cause greater retrieval effort during spoken word recognition. To gauge retrieval effort, the present study compared the effects of word frequency, neighborhood density (ND), and level of English experience by testing monolingual English speakers and native Spanish speakers who differed in their age of acquisition of English (early/late). In the experimental paradigm, participants heard English words and matched them to one of four pictures while the pupil size, an indication of cognitive effort, was recorded. Overall, both frequency and ND effects could be observed in the pupil response, indicating that lower frequency and higher ND were associated with greater retrieval effort. Bilingual speakers showed an overall delayed pupil response and a larger ND effect compared to the monolingual speakers. The frequency effect was the same in early bilinguals and monolinguals but was larger in late bilinguals. Within the group of bilingual speakers, higher English proficiency was associated with an earlier pupil response in addition to a smaller frequency and ND effect. These results suggest that greater retrieval effort associated with bilingualism may be a consequence of reduced language experience rather than constitute a categorical bilingual disadvantage. Future avenues for the use of pupillometry in the field of spoken word recognition are discussed. PMID:24600428

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

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.

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.

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

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

ELF on a Mushroom: The Overnight Growth in English as a Lingua Franca

ERIC Educational Resources Information Center

Sowden, Colin

2012-01-01

In an effort to curtail native-speaker dominance of global English, and in recognition of the growing role of the language among non-native speakers from different first-language backgrounds, some academics have been urging the teaching of English as a Lingua Franca (ELF). Although at first this proposal seems to offer a plausible alternative to…

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.

Speaker gender identification based on majority vote classifiers

NASA Astrophysics Data System (ADS)

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

2017-03-01

Speaker gender identification is considered among the most important tools in several multimedia applications namely in automatic speech recognition, interactive voice response systems and audio browsing systems. Gender identification systems performance is closely linked to the selected feature set and the employed classification model. Typical techniques are based on selecting the best performing classification method or searching optimum tuning of one classifier parameters through experimentation. In this paper, we consider a relevant and rich set of features involving pitch, MFCCs as well as other temporal and frequency-domain descriptors. Five classification models including decision tree, discriminant analysis, nave Bayes, support vector machine and k-nearest neighbor was experimented. The three best perming classifiers among the five ones will contribute by majority voting between their scores. Experimentations were performed on three different datasets spoken in three languages: English, German and Arabic in order to validate language independency of the proposed scheme. Results confirm that the presented system has reached a satisfying accuracy rate and promising classification performance thanks to the discriminating abilities and diversity of the used features combined with mid-level statistics.

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.

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.

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.

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.

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.

Domain-specific impairment of source memory following a right posterior medial temporal lobe lesion.

PubMed

Peters, Jan; Koch, Benno; Schwarz, Michael; Daum, Irene

2007-01-01

This single case analysis of memory performance in a patient with an ischemic lesion affecting posterior but not anterior right medial temporal lobe (MTL) indicates that source memory can be disrupted in a domain-specific manner. The patient showed normal recognition memory for gray-scale photos of objects (visual condition) and spoken words (auditory condition). While memory for visual source (texture/color of the background against which pictures appeared) was within the normal range, auditory source memory (male/female speaker voice) was at chance level, a performance pattern significantly different from the control group. This dissociation is consistent with recent fMRI evidence of anterior/posterior MTL dissociations depending upon the nature of source information (visual texture/color vs. auditory speaker voice). The findings are in good agreement with the view of dissociable memory processing by the perirhinal cortex (anterior MTL) and parahippocampal cortex (posterior MTL), depending upon the neocortical input that these regions receive. (c) 2007 Wiley-Liss, Inc.

Processing of Acoustic Cues in Lexical-Tone Identification by Pediatric Cochlear-Implant Recipients

ERIC Educational Resources Information Center

Peng, Shu-Chen; Lu, Hui-Ping; Lu, Nelson; Lin, Yung-Song; Deroche, Mickael L. D.; Chatterjee, Monita

2017-01-01

Purpose: The objective was to investigate acoustic cue processing in lexical-tone recognition by pediatric cochlear-implant (CI) recipients who are native Mandarin speakers. Method: Lexical-tone recognition was assessed in pediatric CI recipients and listeners with normal hearing (NH) in 2 tasks. In Task 1, participants identified naturally…

L2 Gender Facilitation and Inhibition in Spoken Word Recognition

ERIC Educational Resources Information Center

Behney, Jennifer N.

2011-01-01

This dissertation investigates the role of grammatical gender facilitation and inhibition in second language (L2) learners' spoken word recognition. Native speakers of languages that have grammatical gender are sensitive to gender marking when hearing and recognizing a word. Gender facilitation refers to when a given noun that is preceded by an…

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.

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.

Gay- and Lesbian-Sounding Auditory Cues Elicit Stereotyping and Discrimination.

PubMed

Fasoli, Fabio; Maass, Anne; Paladino, Maria Paola; Sulpizio, Simone

2017-07-01

The growing body of literature on the recognition of sexual orientation from voice ("auditory gaydar") is silent on the cognitive and social consequences of having a gay-/lesbian- versus heterosexual-sounding voice. We investigated this issue in four studies (overall N = 276), conducted in Italian language, in which heterosexual listeners were exposed to single-sentence voice samples of gay/lesbian and heterosexual speakers. In all four studies, listeners were found to make gender-typical inferences about traits and preferences of heterosexual speakers, but gender-atypical inferences about those of gay or lesbian speakers. Behavioral intention measures showed that listeners considered lesbian and gay speakers as less suitable for a leadership position, and male (but not female) listeners took distance from gay speakers. Together, this research demonstrates that having a gay/lesbian rather than heterosexual-sounding voice has tangible consequences for stereotyping and discrimination.

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

Multifunctional microcontrollable interface module

NASA Astrophysics Data System (ADS)

Spitzer, Mark B.; Zavracky, Paul M.; Rensing, Noa M.; Crawford, J.; Hockman, Angela H.; Aquilino, P. D.; Girolamo, Henry J.

2001-08-01

This paper reports the development of a complete eyeglass- mounted computer interface system including display, camera and audio subsystems. The display system provides an SVGA image with a 20 degree horizontal field of view. The camera system has been optimized for face recognition and provides a 19 degree horizontal field of view. A microphone and built-in pre-amp optimized for voice recognition and a speaker on an articulated arm are included for audio. An important feature of the system is a high degree of adjustability and reconfigurability. The system has been developed for testing by the Military Police, in a complete system comprising the eyeglass-mounted interface, a wearable computer, and an RF link. Details of the design, construction, and performance of the eyeglass-based system are discussed.

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.

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

Factors Impacting Recognition of False Collo­cations by Speakers of English as L1 and L2

ERIC Educational Resources Information Center

Makinina, Olga

2017-01-01

Currently there is a general uncertainty about what makes collocations (i.e., fixed word combinations with specific, not easily interpreted relations between their components) hard for ESL learners to master, and about how to improve collocation recognition and learning process. This study explored and designed a comparative classification of…

The Impact of Orthographic Connectivity on Visual Word Recognition in Arabic: A Cross-Sectional Study

ERIC Educational Resources Information Center

Khateb, Asaid; Khateb-Abdelgani, Manal; Taha, Haitham Y.; Ibrahim, Raphiq

2014-01-01

This study aimed at assessing the effects of letters' connectivity in Arabic on visual word recognition. For this purpose, reaction times (RTs) and accuracy scores were collected from ninety-third, sixth and ninth grade native Arabic speakers during a lexical decision task, using fully connected (Cw), partially connected (PCw) and…

Detailed Phonetic Labeling of Multi-language Database for Spoken Language Processing Applications

DTIC Science & Technology

2015-03-01

which contains about 60 interfering speakers as well as background music in a bar. The top panel is again clean training /noisy testing settings, and...recognition system for Mandarin was developed and tested. Character recognition rates as high as 88% were obtained, using an approximately 40 training ...Tool_ComputeFeat.m) .............................................................................................................. 50 6.3. Training

Semantic Ambiguity Effects in L2 Word Recognition

ERIC Educational Resources Information Center

Ishida, Tomomi

2018-01-01

The present study examined the ambiguity effects in second language (L2) word recognition. Previous studies on first language (L1) lexical processing have observed that ambiguous words are recognized faster and more accurately than unambiguous words on lexical decision tasks. In this research, L1 and L2 speakers of English were asked whether a…

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…

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.

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…

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…

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.

Advanced Subspace Techniques for Modeling Channel and Session Variability in a Speaker Recognition System

DTIC Science & Technology

2012-03-01

with each SVM discriminating between a pair of the N total speakers in the data set. The (( + 1))/2 classifiers then vote on the final...classification of a test sample. The Random Forest classifier is an ensemble classifier that votes amongst decision trees generated with each node using...Forest vote , and the effects of overtraining will be mitigated by the fact that each decision tree is overtrained differently (due to the random

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.

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.

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.

Channel Compensation for Speaker Recognition using MAP Adapted PLDA and Denoising DNNs

DTIC Science & Technology

2016-06-21

improvement has been the availability of large quantities of speaker-labeled data from telephone recordings. For new data applications, such as audio from...mi- crophone channels to the telephone channel. Audio files were rejected if the alignment process failed. At the end of the pro- cess a total of 873...Microphone 01 AT3035 ( Audio Technica Studio Mic) 02 MX418S (Shure Gooseneck Mic) 03 Crown PZM Soundgrabber II 04 AT Pro45 ( Audio Technica Hanging Mic

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…

A Prerequisite to L1 Homophone Effects in L2 Spoken-Word Recognition

ERIC Educational Resources Information Center

Nakai, Satsuki; Lindsay, Shane; Ota, Mitsuhiko

2015-01-01

When both members of a phonemic contrast in L2 (second language) are perceptually mapped to a single phoneme in one's L1 (first language), L2 words containing a member of that contrast can spuriously activate L2 words in spoken-word recognition. For example, upon hearing cattle, Dutch speakers of English are reported to experience activation…

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.

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

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.

Improving Speaker Recognition by Biometric Voice Deconstruction

PubMed Central

Mazaira-Fernandez, Luis Miguel; Álvarez-Marquina, Agustín; Gómez-Vilda, Pedro

2015-01-01

Person identification, especially in critical environments, has always been a subject of great interest. However, it has gained a new dimension in a world threatened by a new kind of terrorism that uses social networks (e.g., YouTube) to broadcast its message. In this new scenario, classical identification methods (such as fingerprints or face recognition) have been forcedly replaced by alternative biometric characteristics such as voice, as sometimes this is the only feature available. The present study benefits from the advances achieved during last years in understanding and modeling voice production. The paper hypothesizes that a gender-dependent characterization of speakers combined with the use of a set of features derived from the components, resulting from the deconstruction of the voice into its glottal source and vocal tract estimates, will enhance recognition rates when compared to classical approaches. A general description about the main hypothesis and the methodology followed to extract the gender-dependent extended biometric parameters is given. Experimental validation is carried out both on a highly controlled acoustic condition database, and on a mobile phone network recorded under non-controlled acoustic conditions. PMID:26442245

Improving Speaker Recognition by Biometric Voice Deconstruction.

PubMed

Mazaira-Fernandez, Luis Miguel; Álvarez-Marquina, Agustín; Gómez-Vilda, Pedro

2015-01-01

Person identification, especially in critical environments, has always been a subject of great interest. However, it has gained a new dimension in a world threatened by a new kind of terrorism that uses social networks (e.g., YouTube) to broadcast its message. In this new scenario, classical identification methods (such as fingerprints or face recognition) have been forcedly replaced by alternative biometric characteristics such as voice, as sometimes this is the only feature available. The present study benefits from the advances achieved during last years in understanding and modeling voice production. The paper hypothesizes that a gender-dependent characterization of speakers combined with the use of a set of features derived from the components, resulting from the deconstruction of the voice into its glottal source and vocal tract estimates, will enhance recognition rates when compared to classical approaches. A general description about the main hypothesis and the methodology followed to extract the gender-dependent extended biometric parameters is given. Experimental validation is carried out both on a highly controlled acoustic condition database, and on a mobile phone network recorded under non-controlled acoustic conditions.

Optimization of multilayer neural network parameters for speaker recognition

NASA Astrophysics Data System (ADS)

Tovarek, Jaromir; Partila, Pavol; Rozhon, Jan; Voznak, Miroslav; Skapa, Jan; Uhrin, Dominik; Chmelikova, Zdenka

2016-05-01

This article discusses the impact of multilayer neural network parameters for speaker identification. The main task of speaker identification is to find a specific person in the known set of speakers. It means that the voice of an unknown speaker (wanted person) belongs to a group of reference speakers from the voice database. One of the requests was to develop the text-independent system, which means to classify wanted person regardless of content and language. Multilayer neural network has been used for speaker identification in this research. Artificial neural network (ANN) needs to set parameters like activation function of neurons, steepness of activation functions, learning rate, the maximum number of iterations and a number of neurons in the hidden and output layers. ANN accuracy and validation time are directly influenced by the parameter settings. Different roles require different settings. Identification accuracy and ANN validation time were evaluated with the same input data but different parameter settings. The goal was to find parameters for the neural network with the highest precision and shortest validation time. Input data of neural networks are a Mel-frequency cepstral coefficients (MFCC). These parameters describe the properties of the vocal tract. Audio samples were recorded for all speakers in a laboratory environment. Training, testing and validation data set were split into 70, 15 and 15 %. The result of the research described in this article is different parameter setting for the multilayer neural network for four speakers.

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.

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.

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

Factor analysis of auto-associative neural networks with application in speaker verification.

PubMed

Garimella, Sri; Hermansky, Hynek

2013-04-01

Auto-associative neural network (AANN) is a fully connected feed-forward neural network, trained to reconstruct its input at its output through a hidden compression layer, which has fewer numbers of nodes than the dimensionality of input. AANNs are used to model speakers in speaker verification, where a speaker-specific AANN model is obtained by adapting (or retraining) the universal background model (UBM) AANN, an AANN trained on multiple held out speakers, using corresponding speaker data. When the amount of speaker data is limited, this adaptation procedure may lead to overfitting as all the parameters of UBM-AANN are adapted. In this paper, we introduce and develop the factor analysis theory of AANNs to alleviate this problem. We hypothesize that only the weight matrix connecting the last nonlinear hidden layer and the output layer is speaker-specific, and further restrict it to a common low-dimensional subspace during adaptation. The subspace is learned using large amounts of development data, and is held fixed during adaptation. Thus, only the coordinates in a subspace, also known as i-vector, need to be estimated using speaker-specific data. The update equations are derived for learning both the common low-dimensional subspace and the i-vectors corresponding to speakers in the subspace. The resultant i-vector representation is used as a feature for the probabilistic linear discriminant analysis model. The proposed system shows promising results on the NIST-08 speaker recognition evaluation (SRE), and yields a 23% relative improvement in equal error rate over the previously proposed weighted least squares-based subspace AANNs system. The experiments on NIST-10 SRE confirm that these improvements are consistent and generalize across datasets.

Recognition of English and German Borrowings in the Russian Language (Based on Lexical Borrowings in the Field of Economics)

ERIC Educational Resources Information Center

Ashrapova, Alsu; Alendeeva, Svetlana

2014-01-01

This article is the result of a study of the influence of English and German on the Russian language during the English learning based on lexical borrowings in the field of economics. This paper discusses the use and recognition of borrowings from the English and German languages by Russian native speakers. The use of lexical borrowings from…

Performance-intensity functions of Mandarin word recognition tests in noise: test dialect and listener language effects.

PubMed

Liu, Danzheng; Shi, Lu-Feng

2013-06-01

This study established the performance-intensity function for Beijing and Taiwan Mandarin bisyllabic word recognition tests in noise in native speakers of Wu Chinese. Effects of the test dialect and listeners' first language on psychometric variables (i.e., slope and 50%-correct threshold) were analyzed. Thirty-two normal-hearing Wu-speaking adults who used Mandarin since early childhood were compared to 16 native Mandarin-speaking adults. Both Beijing and Taiwan bisyllabic word recognition tests were presented at 8 signal-to-noise ratios (SNRs) in 4-dB steps (-12 dB to +16 dB). At each SNR, a half list (25 words) was presented in speech-spectrum noise to listeners' right ear. The order of the test, SNR, and half list was randomized across listeners. Listeners responded orally and in writing. Overall, the Wu-speaking listeners performed comparably to the Mandarin-speaking listeners on both tests. Compared to the Taiwan test, the Beijing test yielded a significantly lower threshold for both the Mandarin- and Wu-speaking listeners, as well as a significantly steeper slope for the Wu-speaking listeners. Both Mandarin tests can be used to evaluate Wu-speaking listeners. Of the 2, the Taiwan Mandarin test results in more comparable functions across listener groups. Differences in the performance-intensity function between listener groups and between tests indicate a first language and dialectal effect, respectively.

Amplitude (vu and rms) and Temporal (msec) Measures of Two Northwestern University Auditory Test No. 6 Recordings.

PubMed

Wilson, Richard H

2015-04-01

In 1940, a cooperative effort by the radio networks and Bell Telephone produced the volume unit (vu) meter that has been the mainstay instrument for monitoring the level of speech signals in commercial broadcasting and research laboratories. With the use of computers, today the amplitude of signals can be quantified easily using the root mean square (rms) algorithm. Researchers had previously reported that amplitude estimates of sentences and running speech were 4.8 dB higher when measured with a vu meter than when calculated with rms. This study addresses the vu-rms relation as applied to the carrier phrase and target word paradigm used to assess word-recognition abilities, the premise being that by definition the word-recognition paradigm is a special and different case from that described previously. The purpose was to evaluate the vu and rms amplitude relations for the carrier phrases and target words commonly used to assess word-recognition abilities. In addition, the relations with the target words between rms level and recognition performance were examined. Descriptive and correlational. Two recoded versions of the Northwestern University Auditory Test No. 6 were evaluated, the Auditec of St. Louis (Auditec) male speaker and the Department of Veterans Affairs (VA) female speaker. Using both visual and auditory cues from a waveform editor, the temporal onsets and offsets were defined for each carrier phrase and each target word. The rms amplitudes for those segments then were computed and expressed in decibels with reference to the maximum digitization range. The data were maintained for each of the four Northwestern University Auditory Test No. 6 word lists. Descriptive analyses were used with linear regressions used to evaluate the reliability of the measurement technique and the relation between the rms levels of the target words and recognition performances. Although there was a 1.3 dB difference between the calibration tones, the mean levels of the carrier phrases for the two recordings were -14.8 dB (Auditec) and -14.1 dB (VA) with standard deviations <1 dB. For the target words, the mean amplitudes were -19.9 dB (Auditec) and -18.3 dB (VA) with standard deviations ranging from 1.3 to 2.4 dB. The mean durations for the carrier phrases of both recordings were 593-594 msec, with the mean durations of the target words a little different, 509 msec (Auditec) and 528 msec (VA). Random relations were observed between the recognition performances and rms levels of the target words. Amplitude and temporal data for the individual words are provided. The rms levels of the carrier phrases closely approximated (±1 dB) the rms levels of the calibration tones, both of which were set to 0 vu (dB). The rms levels of the target words were 5-6 dB below the levels of the carrier phrases and were substantially more variable than the levels of the carrier phrases. The relation between the rms levels of the target words and recognition performances on the words was random. American Academy of Audiology.

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

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

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

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…

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.

Effect of Vowel Context on the Recognition of Initial Consonants in Kannada.

PubMed

Kalaiah, Mohan Kumar; Bhat, Jayashree S

2017-09-01

The present study was carried out to investigate the effect of vowel context on the recognition of Kannada consonants in quiet for young adults. A total of 17 young adults with normal hearing in both ears participated in the study. The stimuli included consonant-vowel syllables, spoken by 12 native speakers of Kannada. Consonant recognition task was carried out as a closed-set (fourteen-alternative forced-choice). The present study showed an effect of vowel context on the perception of consonants. Maximum consonant recognition score was obtained in the /o/ vowel context, followed by the /a/ and /u/ vowel contexts, and then the /e/ context. Poorest consonant recognition score was obtained in the vowel context /i/. Vowel context has an effect on the recognition of Kannada consonants, and the vowel effect was unique for Kannada consonants.

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.

Benefits for Voice Learning Caused by Concurrent Faces Develop over Time.

PubMed

Zäske, Romi; Mühl, Constanze; Schweinberger, Stefan R

2015-01-01

Recognition of personally familiar voices benefits from the concurrent presentation of the corresponding speakers' faces. This effect of audiovisual integration is most pronounced for voices combined with dynamic articulating faces. However, it is unclear if learning unfamiliar voices also benefits from audiovisual face-voice integration or, alternatively, is hampered by attentional capture of faces, i.e., "face-overshadowing". In six study-test cycles we compared the recognition of newly-learned voices following unimodal voice learning vs. bimodal face-voice learning with either static (Exp. 1) or dynamic articulating faces (Exp. 2). Voice recognition accuracies significantly increased for bimodal learning across study-test cycles while remaining stable for unimodal learning, as reflected in numerical costs of bimodal relative to unimodal voice learning in the first two study-test cycles and benefits in the last two cycles. This was independent of whether faces were static images (Exp. 1) or dynamic videos (Exp. 2). In both experiments, slower reaction times to voices previously studied with faces compared to voices only may result from visual search for faces during memory retrieval. A general decrease of reaction times across study-test cycles suggests facilitated recognition with more speaker repetitions. Overall, our data suggest two simultaneous and opposing mechanisms during bimodal face-voice learning: while attentional capture of faces may initially impede voice learning, audiovisual integration may facilitate it thereafter.

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.

How Captain Amerika uses neural networks to fight crime

NASA Technical Reports Server (NTRS)

Rogers, Steven K.; Kabrisky, Matthew; Ruck, Dennis W.; Oxley, Mark E.

1994-01-01

Artificial neural network models can make amazing computations. These models are explained along with their application in problems associated with fighting crime. Specific problems addressed are identification of people using face recognition, speaker identification, and fingerprint and handwriting analysis (biometric authentication).

Reading component skills of learners in adult basic education.

PubMed

MacArthur, Charles A; Konold, Timothy R; Glutting, Joseph J; Alamprese, Judith A

2010-01-01

The purposes of this study were to investigate the reliability and construct validity of measures of reading component skills with a sample of adult basic education (ABE) learners, including both native and nonnative English speakers, and to describe the performance of those learners on the measures. Investigation of measures of reading components is needed because available measures were neither developed for nor normed on ABE populations or with nonnative speakers of English. The study included 486 students, 334 born or educated in the United States (native) and 152 not born or educated in the United States (nonnative) but who spoke English well enough to participate in English reading classes. All students had scores on 11 measures covering five constructs: decoding, word recognition, spelling, fluency, and comprehension. Confirmatory factor analysis (CFA) was used to test three models: a two-factor model with print and meaning factors; a three-factor model that separated out a fluency factor; and a five-factor model based on the hypothesized constructs. The five-factor model fit best. In addition, the CFA model fit both native and nonnative populations equally well without modification, showing that the tests measure the same constructs with the same accuracy for both groups. Group comparisons found no difference between the native and nonnative samples on word recognition, but the native sample scored higher on fluency and comprehension and lower on decoding than did the nonnative sample. Students with self-reported learning disabilities scored lower on all reading components. Differences by age and gender were also analyzed.

Partially supervised speaker clustering.

PubMed

Tang, Hao; Chu, Stephen Mingyu; Hasegawa-Johnson, Mark; Huang, Thomas S

2012-05-01

Content-based multimedia indexing, retrieval, and processing as well as multimedia databases demand the structuring of the media content (image, audio, video, text, etc.), one significant goal being to associate the identity of the content to the individual segments of the signals. In this paper, we specifically address the problem of speaker clustering, the task of assigning every speech utterance in an audio stream to its speaker. We offer a complete treatment to the idea of partially supervised speaker clustering, which refers to the use of our prior knowledge of speakers in general to assist the unsupervised speaker clustering process. By means of an independent training data set, we encode the prior knowledge at the various stages of the speaker clustering pipeline via 1) learning a speaker-discriminative acoustic feature transformation, 2) learning a universal speaker prior model, and 3) learning a discriminative speaker subspace, or equivalently, a speaker-discriminative distance metric. We study the directional scattering property of the Gaussian mixture model (GMM) mean supervector representation of utterances in the high-dimensional space, and advocate exploiting this property by using the cosine distance metric instead of the euclidean distance metric for speaker clustering in the GMM mean supervector space. We propose to perform discriminant analysis based on the cosine distance metric, which leads to a novel distance metric learning algorithm—linear spherical discriminant analysis (LSDA). We show that the proposed LSDA formulation can be systematically solved within the elegant graph embedding general dimensionality reduction framework. Our speaker clustering experiments on the GALE database clearly indicate that 1) our speaker clustering methods based on the GMM mean supervector representation and vector-based distance metrics outperform traditional speaker clustering methods based on the “bag of acoustic features” representation and statistical model-based distance metrics, 2) our advocated use of the cosine distance metric yields consistent increases in the speaker clustering performance as compared to the commonly used euclidean distance metric, 3) our partially supervised speaker clustering concept and strategies significantly improve the speaker clustering performance over the baselines, and 4) our proposed LSDA algorithm further leads to state-of-the-art speaker clustering performance.

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

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.

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.

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

The non-trusty clown attack on model-based speaker recognition systems

NASA Astrophysics Data System (ADS)

Farrokh Baroughi, Alireza; Craver, Scott

2015-03-01

Biometric detectors for speaker identification commonly employ a statistical model for a subject's voice, such as a Gaussian Mixture Model, that combines multiple means to improve detector performance. This allows a malicious insider to amend or append a component of a subject's statistical model so that a detector behaves normally except under a carefully engineered circumstance. This allows an attacker to force a misclassification of his or her voice only when desired, by smuggling data into a database far in advance of an attack. Note that the attack is possible if attacker has access to database even for a limited time to modify victim's model. We exhibit such an attack on a speaker identification, in which an attacker can force a misclassification by speaking in an unusual voice, and replacing the least weighted component of victim's model by the most weighted competent of the unusual voice of the attacker's model. The reason attacker make his or her voice unusual during the attack is because his or her normal voice model can be in database, and by attacking with unusual voice, the attacker has the option to be recognized as himself or herself when talking normally or as the victim when talking in the unusual manner. By attaching an appropriately weighted vector to a victim's model, we can impersonate all users in our simulations, while avoiding unwanted false rejections.

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

Processing of Acoustic Cues in Lexical-Tone Identification by Pediatric Cochlear-Implant Recipients

PubMed Central

Peng, Shu-Chen; Lu, Hui-Ping; Lu, Nelson; Lin, Yung-Song; Deroche, Mickael L. D.

2017-01-01

Purpose The objective was to investigate acoustic cue processing in lexical-tone recognition by pediatric cochlear-implant (CI) recipients who are native Mandarin speakers. Method Lexical-tone recognition was assessed in pediatric CI recipients and listeners with normal hearing (NH) in 2 tasks. In Task 1, participants identified naturally uttered words that were contrastive in lexical tones. For Task 2, a disyllabic word (yanjing) was manipulated orthogonally, varying in fundamental-frequency (F0) contours and duration patterns. Participants identified each token with the second syllable jing pronounced with Tone 1 (a high level tone) as eyes or with Tone 4 (a high falling tone) as eyeglasses. Results CI participants' recognition accuracy was significantly lower than NH listeners' in Task 1. In Task 2, CI participants' reliance on F0 contours was significantly less than that of NH listeners; their reliance on duration patterns, however, was significantly higher than that of NH listeners. Both CI and NH listeners' performance in Task 1 was significantly correlated with their reliance on F0 contours in Task 2. Conclusion For pediatric CI recipients, lexical-tone recognition using naturally uttered words is primarily related to their reliance on F0 contours, although duration patterns may be used as an additional cue. PMID:28388709

Morphological learning in a novel language: A cross-language comparison.

PubMed

Havas, Viktória; Waris, Otto; Vaquero, Lucía; Rodríguez-Fornells, Antoni; Laine, Matti

2015-01-01

Being able to extract and interpret the internal structure of complex word forms such as the English word dance+r+s is crucial for successful language learning. We examined whether the ability to extract morphological information during word learning is affected by the morphological features of one's native tongue. Spanish and Finnish adult participants performed a word-picture associative learning task in an artificial language where the target words included a suffix marking the gender of the corresponding animate object. The short exposure phase was followed by a word recognition task and a generalization task for the suffix. The participants' native tongues vary greatly in terms of morphological structure, leading to two opposing hypotheses. On the one hand, Spanish speakers may be more effective in identifying gender in a novel language because this feature is present in Spanish but not in Finnish. On the other hand, Finnish speakers may have an advantage as the abundance of bound morphemes in their language calls for continuous morphological decomposition. The results support the latter alternative, suggesting that lifelong experience on morphological decomposition provides an advantage in novel morphological learning.

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.

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.

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.

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.

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…

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…

Engaging spaces: Intimate electro-acoustic display in alternative performance venues

NASA Astrophysics Data System (ADS)

Bahn, Curtis; Moore, Stephan

2004-05-01

In past presentations to the ASA, we have described the design and construction of four generations of unique spherical speakers (multichannel, outward-radiating geodesic speaker arrays) and Sensor-Speaker-Arrays, (SenSAs: combinations of various sensor devices with outward-radiating multichannel speaker arrays). This presentation will detail the ways in which arrays of these speakers have been employed in alternative performance venues-providing presence and intimacy in the performance of electro-acoustic chamber music and sound installation, while engaging natural and unique acoustical qualities of various locations. We will present documentation of the use of multichannel sonic diffusion arrays in small clubs, ``black-box'' theaters, planetariums, and art galleries.

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.

Event identification by acoustic signature recognition

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

Dress, W.B.; Kercel, S.W.

1995-07-01

Many events of interest to the security commnnity produce acoustic emissions that are, in principle, identifiable as to cause. Some obvious examples are gunshots, breaking glass, takeoffs and landings of small aircraft, vehicular engine noises, footsteps (high frequencies when on gravel, very low frequencies. when on soil), and voices (whispers to shouts). We are investigating wavelet-based methods to extract unique features of such events for classification and identification. We also discuss methods of classification and pattern recognition specifically tailored for acoustic signatures obtained by wavelet analysis. The paper is divided into three parts: completed work, work in progress, and futuremore » applications. The completed phase has led to the successful recognition of aircraft types on landing and takeoff. Both small aircraft (twin-engine turboprop) and large (commercial airliners) were included in the study. The project considered the design of a small, field-deployable, inexpensive device. The techniques developed during the aircraft identification phase were then adapted to a multispectral electromagnetic interference monitoring device now deployed in a nuclear power plant. This is a general-purpose wavelet analysis engine, spanning 14 octaves, and can be adapted for other specific tasks. Work in progress is focused on applying the methods previously developed to speaker identification. Some of the problems to be overcome include recognition of sounds as voice patterns and as distinct from possible background noises (e.g., music), as well as identification of the speaker from a short-duration voice sample. A generalization of the completed work and the work in progress is a device capable of classifying any number of acoustic events-particularly quasi-stationary events such as engine noises and voices and singular events such as gunshots and breaking glass. We will show examples of both kinds of events and discuss their recognition likelihood.« less

Effects of Steady-State Noise on Verbal Working Memory in Young Adults

PubMed Central

Alt, Mary; DeDe, Gayle; Olson, Sarah; Shehorn, James

2015-01-01

Purpose We set out to examine the impact of perceptual, linguistic, and capacity demands on performance of verbal working-memory tasks. The Ease of Language Understanding model (Rönnberg et al., 2013) provides a framework for testing the dynamics of these interactions within the auditory-cognitive system. Methods Adult native speakers of English (n = 45) participated in verbal working-memory tasks requiring processing and storage of words involving different linguistic demands (closed/open set). Capacity demand ranged from 2 to 7 words per trial. Participants performed the tasks in quiet and in speech-spectrum-shaped noise. Separate groups of participants were tested at different signal-to-noise ratios. Word-recognition measures were obtained to determine effects of noise on intelligibility. Results Contrary to predictions, steady-state noise did not have an adverse effect on working-memory performance in every situation. Noise negatively influenced performance for the task with high linguistic demand. Of particular importance is the finding that the adverse effects of background noise were not confined to conditions involving declines in recognition. Conclusions Perceptual, linguistic, and cognitive demands can dynamically affect verbal working-memory performance even in a population of healthy young adults. Results suggest that researchers and clinicians need to carefully analyze task demands to understand the independent and combined auditory-cognitive factors governing performance in everyday listening situations. PMID:26384291

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.

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.

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.

Parallel Processing of Large Scale Microphone Arrays for Sound Capture

NASA Astrophysics Data System (ADS)

Jan, Ea-Ee.

1995-01-01

Performance of microphone sound pick up is degraded by deleterious properties of the acoustic environment, such as multipath distortion (reverberation) and ambient noise. The degradation becomes more prominent in a teleconferencing environment in which the microphone is positioned far away from the speaker. Besides, the ideal teleconference should feel as easy and natural as face-to-face communication with another person. This suggests hands-free sound capture with no tether or encumbrance by hand-held or body-worn sound equipment. Microphone arrays for this application represent an appropriate approach. This research develops new microphone array and signal processing techniques for high quality hands-free sound capture in noisy, reverberant enclosures. The new techniques combine matched-filtering of individual sensors and parallel processing to provide acute spatial volume selectivity which is capable of mitigating the deleterious effects of noise interference and multipath distortion. The new method outperforms traditional delay-and-sum beamformers which provide only directional spatial selectivity. The research additionally explores truncated matched-filtering and random distribution of transducers to reduce complexity and improve sound capture quality. All designs are first established by computer simulation of array performance in reverberant enclosures. The simulation is achieved by a room model which can efficiently calculate the acoustic multipath in a rectangular enclosure up to a prescribed order of images. It also calculates the incident angle of the arriving signal. Experimental arrays were constructed and their performance was measured in real rooms. Real room data were collected in a hard-walled laboratory and a controllable variable acoustics enclosure of similar size, approximately 6 x 6 x 3 m. An extensive speech database was also collected in these two enclosures for future research on microphone arrays. The simulation results are shown to be consistent with the real room data. Localization of sound sources has been explored using cross-power spectrum time delay estimation and has been evaluated using real room data under slightly, moderately and highly reverberant conditions. To improve the accuracy and reliability of the source localization, an outlier detector that removes incorrect time delay estimation has been invented. To provide speaker selectivity for microphone array systems, a hands-free speaker identification system has been studied. A recently invented feature using selected spectrum information outperforms traditional recognition methods. Measured results demonstrate the capabilities of speaker selectivity from a matched-filtered array. In addition, simulation utilities, including matched -filtering processing of the array and hands-free speaker identification, have been implemented on the massively -parallel nCube super-computer. This parallel computation highlights the requirements for real-time processing of array signals.

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.

English Speakers Attend More Strongly than Spanish Speakers to Manner of Motion when Classifying Novel Objects and Events

ERIC Educational Resources Information Center

Kersten, Alan W.; Meissner, Christian A.; Lechuga, Julia; Schwartz, Bennett L.; Albrechtsen, Justin S.; Iglesias, Adam

2010-01-01

Three experiments provide evidence that the conceptualization of moving objects and events is influenced by one's native language, consistent with linguistic relativity theory. Monolingual English speakers and bilingual Spanish/English speakers tested in an English-speaking context performed better than monolingual Spanish speakers and bilingual…

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.

Neural Processing of Vocal Emotion and Identity

ERIC Educational Resources Information Center

Spreckelmeyer, Katja N.; Kutas, Marta; Urbach, Thomas; Altenmuller, Eckart; Munte, Thomas F.

2009-01-01

The voice is a marker of a person's identity which allows individual recognition even if the person is not in sight. Listening to a voice also affords inferences about the speaker's emotional state. Both these types of personal information are encoded in characteristic acoustic feature patterns analyzed within the auditory cortex. In the present…

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.

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

Perceiving and Remembering Events Cross-Linguistically: Evidence from Dual-Task Paradigms

ERIC Educational Resources Information Center

Trueswell, John C.; Papafragou, Anna

2010-01-01

What role does language play during attention allocation in perceiving and remembering events? We recorded adults' eye movements as they studied animated motion events for a later recognition task. We compared native speakers of two languages that use different means of expressing motion (Greek and English). In Experiment 1, eye movements revealed…

An Analysis of Rapid Technology Transfer Solutions and Best Practices for Use by the Department of Defense

DTIC Science & Technology

2010-12-01

discovered that the NSA is concerned about speaker recognition being vulnerable to man- in-the-middle ( MITM ) attacks. The professional could tailor an MITM ...with the results of the test against the MITM threat. The Collective Acquisition framework comprises powerful search techniques found in the CRC

Effects of Speed of Word Processing on Semantic Access: The Case of Bilingualism

ERIC Educational Resources Information Center

Martin, Clara D.; Costa, Albert; Dering, Benjamin; Hoshino, Noriko; Wu, Yan Jing; Thierry, Guillaume

2012-01-01

Bilingual speakers generally manifest slower word recognition than monolinguals. We investigated the consequences of the word processing speed on semantic access in bilinguals. The paradigm involved a stream of English words and pseudowords presented in succession at a constant rate. English-Welsh bilinguals and English monolinguals were asked to…

Chinese-Mandarin: Basic Course. Volume VII: Lessons 72-79.

ERIC Educational Resources Information Center

Defense Language Inst., Monterey, CA.

This is the seventh of 16 volumes of audiolingual classroom instruction in Mandarin Chinese. The course is designed to train native English speakers to Level 3 Foreign Service Institute proficiency in comprehension and speaking, and to Level 2 proficiency in reading and writing Mandarin. Facility in the use and recognition of Chinese characters is…

Chinese-Mandarin: Basic Course. Volume IX: Lessons 88-95.

ERIC Educational Resources Information Center

Defense Language Inst., Monterey, CA.

This is the ninth of 16 volumes of audiolingual classroom instruction in Mandarin Chinese. The course is designed to train native English speakers to Level 3 Foreign Service Institute proficiency in comprehension and speaking, and to Level 2 proficiency in reading and writing Mandarin. Facility in the use and recognition of Chinese characters is…

Chinese-Mandarin: Basic Course. Volume VIII: Lessons 80-87.

ERIC Educational Resources Information Center

Defense Language Inst., Monterey, CA.

This is the eighth of 16 volumes of audiolingual classroom instruction in Mandarin Chinese. The course is designed to train native English speakers to Level 3 Foreign Service Institute proficiency in comprehension and speaking, and to Level 2 proficiency in reading and writing Mandarin. Facility in the use and recognition of Chinese characters is…

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…

Not “Pulling up the Ladder”: Women Who Organize Conference Symposia Provide Greater Opportunities for Women to Speak at Conservation Conferences

PubMed Central

Sardelis, Stephanie; Drew, Joshua A.

2016-01-01

The scientific community faces numerous challenges in achieving gender equality among its participants. One method of highlighting the contributions made by female scientists is through their selection as featured speakers in symposia held at the conferences of professional societies. Because they are specially invited, symposia speakers obtain a prestigious platform from which to display their scientific research, which can elevate the recognition of female scientists. We investigated the number of female symposium speakers in two professional societies (the Society of Conservation Biology (SCB) from 1999 to 2015, and the American Society of Ichthyologists and Herpetologists (ASIH) from 2005 to 2015), in relation to the number of female symposium organizers. Overall, we found that 36.4% of symposia organizers and 31.7% of symposia speakers were women at the Society of Conservation Biology conferences, while 19.1% of organizers and 28% of speakers were women at the American Society of Ichthyologists and Herpetologists conferences. For each additional female organizer at the SCB and ASIH conferences, there was an average increase of 95% and 70% female speakers, respectively. As such, we found a significant positive relationship between the number of women organizing a symposium and the number of women speaking in that symposium. We did not, however, find a significant increase in the number of women speakers or organizers per symposium over time at either conference, suggesting a need for revitalized efforts to diversify our scientific societies. To further those ends, we suggest facilitating gender equality in professional societies by removing barriers to participation, including assisting with travel, making conferences child-friendly, and developing thorough, mandatory Codes of Conduct for all conferences. PMID:27467580

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

Shiraz Verbal Learning Test (SVLT): Normative Data for Neurologically Intact Speakers of Persian.

PubMed

Rahmani, Fahimeh; Haghshenas, Hassan; Mehrabanpour, Abdolrasoul; Mani, Arash; Mahmoodi, Mohammad

2017-08-01

Memory assessment plays an important role in the diagnosis of neurodegenerative disorders. Several tests, such as the California Verbal Learning Test (CVLT), have been developed for this purpose, yet a variety of different factors can affect one's performance on such tests, the most important of which are demographic and cultural variables. The present study examined the norming process performed on the CVLT-revised and aimed to devise a new test, the Shiraz Verbal Learning Test (SVLT), to better meet the needs of speakers of Persian. In order to collect normative data, a group of 1275 Persian-speaking individuals consisting of both sexes (676 women and 599 men) aged 20-89 years old were selected for this study. The results of Pearson's Correlation analysis indicated that there was a significant negative correlation between age and SVLT performance and a positive one between education and SVLT performance (p < .001) among the whole sample. Moreover, between-group analyses showed that the female participants performed significantly better than their male counterparts on nearly all subtests (Total Trails 1-5, Short-Delay Free Recall, Short-Delay Cued Recall, Long-Delay Free Recall, Long-Delay Cued Recall, and Total Learning Slope), with the only exception being Long-Delay Yes/No Recognition. These results suggest that the SVLT has the potential to be further developed among different culture and language groups. This test can also be used for clinical and research purposes for patients with neuropsychiatric disorders who need further neuropsychological assessment. © The Author 2017. Published by Oxford University Press. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.

Tension between scientific certainty and meaning complicates communication of IPCC reports

NASA Astrophysics Data System (ADS)

Hollin, G. J. S.; Pearce, W.

2015-08-01

Here we demonstrate that speakers at the press conference for the publication of the IPCC’s Fifth Assessment Report (Working Group 1; ref. ) attempted to make the documented level of certainty of anthropogenic global warming (AGW) more meaningful to the public. Speakers attempted to communicate this through reference to short-term temperature increases. However, when journalists enquired about the similarly short `pause’ in global temperature increase, the speakers dismissed the relevance of such timescales, thus becoming incoherent as to `what counts’ as scientific evidence for AGW. We call this the `IPCC’s certainty trap’. This incoherence led to confusion within the press conference and subsequent condemnation in the media. The speakers were well intentioned in their attempts to communicate the public implications of the report, but these attempts threatened to erode their scientific credibility. In this instance, the certainty trap was the result of the speakers’ failure to acknowledge the tensions between scientific and public meanings. Avoiding the certainty trap in the future will require a nuanced accommodation of uncertainties and a recognition that rightful demands for scientific credibility need to be balanced with public and political dialogue about the things we value and the actions we take to protect those things.

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.

Google Home: smart speaker as environmental control unit.

PubMed

Noda, Kenichiro

2017-08-23

Environmental Control Units (ECU) are devices or a system that allows a person to control appliances in their home or work environment. Such system can be utilized by clients with physical and/or functional disability to enhance their ability to control their environment, to promote independence and improve their quality of life. Over the last several years, there have been an emergence of several inexpensive, commercially-available, voice activated smart speakers into the market such as Google Home and Amazon Echo. These smart speakers are equipped with far field microphone that supports voice recognition, and allows for complete hand-free operation for various purposes, including for playing music, for information retrieval, and most importantly, for environmental control. Clients with disability could utilize these features to turn the unit into a simple ECU that is completely voice activated and wirelessly connected to appliances. Smart speakers, with their ease of setup, low cost and versatility, may be a more affordable and accessible alternative to the traditional ECU. Implications for Rehabilitation Environmental Control Units (ECU) enable independence for physically and functionally disabled clients, and reduce burden and frequency of demands on carers. Traditional ECU can be costly and may require clients to learn specialized skills to use. Smart speakers have the potential to be used as a new-age ECU by overcoming these barriers, and can be used by a wider range of clients.

Adaptation to novel accents by toddlers

PubMed Central

White, Katherine S.; Aslin, Richard N.

2010-01-01

Word recognition is a balancing act: listeners must be sensitive to phonetic detail to avoid confusing similar words, yet, at the same time, be flexible enough to adapt to phonetically variable pronunciations, such as those produced by speakers of different dialects or by non-native speakers. Recent work has demonstrated that young toddlers are sensitive to phonetic detail during word recognition; pronunciations that deviate from the typical phonological form lead to a disruption of processing. However, it is not known whether young word learners show the flexibility that is characteristic of adult word recognition. The present study explores whether toddlers can adapt to artificial accents in which there is a vowel category shift with respect to the native language. 18–20-month-olds heard mispronunciations of familiar words (e.g., vowels were shifted from [a] to [æ]: “dog” pronounced as “dag”). In test, toddlers were tolerant of mispronunciations if they had recently been exposed to the same vowel shift, but not if they had been exposed to standard pronunciations or other vowel shifts. The effects extended beyond particular items heard in exposure to words sharing the same vowels. These results indicate that, like adults, toddlers show flexibility in their interpretation of phonological detail. Moreover, they suggest that effects of top-down knowledge on the reinterpretation of phonological detail generalize across the phono-lexical system. PMID:21479106

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

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

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

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.

Influence of encoding focus and stereotypes on source monitoring event-related-potentials.

PubMed

Leynes, P Andrew; Nagovsky, Irina

2016-01-01

Source memory, memory for the origin of a memory, can be influenced by stereotypes and the information of focus during encoding processes. Participants studied words from two different speakers (male or female) using self-focus or other-focus encoding. Source judgments for the speaker׳s voice and Event-Related Potentials (ERPs) were recorded during test. Self-focus encoding increased dependence on stereotype information and the Late Posterior Negativity (LPN). The results link the LPN with an increase in systematic decision processes such as consulting prior knowledge to support an episodic memory judgment. In addition, other-focus encoding increased conditional source judgments and resulted in weaker old/new recognition relative to the self-focus encoding. The putative correlate of recollection (LPC) was absent during this condition and this was taken as evidence that recollection of partial information supported source judgments. Collectively, the results suggest that other-focus encoding changes source monitoring processing by altering the weight of specific memory features. Copyright © 2015 Elsevier B.V. All rights reserved.

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.

The Storage and Processing of Morphologically Complex Words in L2 Spanish

ERIC Educational Resources Information Center

Foote, Rebecca

2017-01-01

Research with native speakers indicates that, during word recognition, regularly inflected words undergo parsing that segments them into stems and affixes. In contrast, studies with learners suggest that this parsing may not take place in L2. This study's research questions are: Do L2 Spanish learners store and process regularly inflected,…

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…

Setting the Tone: An ERP Investigation of the Influences of Phonological Similarity on Spoken Word Recognition in Mandarin Chinese

ERIC Educational Resources Information Center

Malins, Jeffrey G.; Joanisse, Marc F.

2012-01-01

We investigated the influences of phonological similarity on the time course of spoken word processing in Mandarin Chinese. Event related potentials were recorded while adult native speakers of Mandarin ("N" = 19) judged whether auditory words matched or mismatched visually presented pictures. Mismatching words were of the following…

Experimental Pragmatics and What Is Said: A Response to Gibbs and Moise.

ERIC Educational Resources Information Center

Nicolle, Steve; Clark, Billy

1999-01-01

Attempted replication of Gibbs and Moise (1997) experiments regarding the recognition of a distinction between what is said and what is implicated. Results showed that, under certain conditions, subject selected implicatures when asked to select the paraphrase best reflecting what a speaker has said. Suggests that results can be explained with the…

Costs and Effects of Dual-Language Immersion in the Portland Public Schools

ERIC Educational Resources Information Center

Steele, Jennifer L.; Slater, Robert; Li, Jennifer; Zamarro, Gema; Miller, Trey

2015-01-01

Though it is estimated that about half of the world's population is bilingual, the estimate for the United States is well below 20% (Grosjean, 2010). Amid growing recognition of the need for second language skills to facilitate international commerce and national security and to enhance learning opportunities for non-native speakers of English,…

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

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

Improvements of ModalMax High-Fidelity Piezoelectric Audio Device

NASA Technical Reports Server (NTRS)

Woodard, Stanley E.

2005-01-01

ModalMax audio speakers have been enhanced by innovative means of tailoring the vibration response of thin piezoelectric plates to produce a high-fidelity audio response. The ModalMax audio speakers are 1 mm in thickness. The device completely supplants the need to have a separate driver and speaker cone. ModalMax speakers can perform the same applications of cone speakers, but unlike cone speakers, ModalMax speakers can function in harsh environments such as high humidity or extreme wetness. New design features allow the speakers to be completely submersed in salt water, making them well suited for maritime applications. The sound produced from the ModalMax audio speakers has sound spatial resolution that is readily discernable for headset users.

Orthographic neighborhood effects in recognition and recall tasks in a transparent orthography.

PubMed

Justi, Francis R R; Jaeger, Antonio

2017-04-01

The number of orthographic neighbors of a word influences its probability of being retrieved in recognition and free recall memory tests. Even though this phenomenon is well demonstrated for English words, it has yet to be demonstrated for languages with more predictable grapheme-phoneme mappings than English. To address this issue, 4 experiments were conducted to investigate effects of number of orthographic neighbors (N) and effects of frequency of occurrence of orthographic neighbors (NF) on memory retrieval of Brazilian Portuguese words. One hundred twenty-four Brazilian Portuguese speakers performed first a lexical-decision task (LDT) on words that were factorially manipulated according to N and NF, and intermixed with either nonpronounceable nonwords without orthographic neighbors (Experiments 1A and 2A), or with pronounceable nonwords with a large number of orthographic neighbors (Experiments 1B and 2B). The words were later used as probes on either recognition (Experiments 1A and 1B) or recall tests (Experiments 2A and 2B). Words with 1 orthographic neighbor were consistently better remembered than words with several orthographic neighbors in all recognition and recall tests. Notably, whereas in Experiment 1A higher false alarm rates were yielded for words with several rather than 1 orthographic neighbor, in Experiment 1B higher false alarm rates were yielded for words with 1 rather than several orthographic neighbors. Effects of NF, on the other hand, were not consistent among memory tasks. The effects of N on the recognition and recall tests conducted here are interpreted in light of dual process models of recognition. (PsycINFO Database Record (c) 2017 APA, all rights reserved).

The development of cross-cultural recognition of vocal emotion during childhood and adolescence.

PubMed

Chronaki, Georgia; Wigelsworth, Michael; Pell, Marc D; Kotz, Sonja A

2018-06-14

Humans have an innate set of emotions recognised universally. However, emotion recognition also depends on socio-cultural rules. Although adults recognise vocal emotions universally, they identify emotions more accurately in their native language. We examined developmental trajectories of universal vocal emotion recognition in children. Eighty native English speakers completed a vocal emotion recognition task in their native language (English) and foreign languages (Spanish, Chinese, and Arabic) expressing anger, happiness, sadness, fear, and neutrality. Emotion recognition was compared across 8-to-10, 11-to-13-year-olds, and adults. Measures of behavioural and emotional problems were also taken. Results showed that although emotion recognition was above chance for all languages, native English speaking children were more accurate in recognising vocal emotions in their native language. There was a larger improvement in recognising vocal emotion from the native language during adolescence. Vocal anger recognition did not improve with age for the non-native languages. This is the first study to demonstrate universality of vocal emotion recognition in children whilst supporting an "in-group advantage" for more accurate recognition in the native language. Findings highlight the role of experience in emotion recognition, have implications for child development in modern multicultural societies and address important theoretical questions about the nature of emotions.

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.

Referential first mention in narratives by mildly mentally retarded adults.

PubMed

Kernan, K T; Sabsay, S

1987-01-01

Referential first mentions in narrative reports of a short film by 40 mildly mentally retarded adults and 20 nonretarded adults were compared. The mentally retarded sample included equal numbers of male and female, and black and white speakers. The mentally retarded speakers made significantly fewer first mentions and significantly more errors in the form of the first mentions than did nonretarded speakers. A pattern of better performance by black males than by other mentally retarded speakers was found. It is suggested that task difficulty and incomplete mastery of the use of definite and indefinite forms for encoding old and new information, rather than some global type of egocentrism, accounted for the poorer performance by mentally retarded speakers.

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.

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.

The effect of voice quality and competing speakers in a passage comprehension task: performance in relation to cognitive functioning in children with normal hearing.

PubMed

von Lochow, Heike; Lyberg-Åhlander, Viveka; Sahlén, Birgitta; Kastberg, Tobias; Brännström, K Jonas

2018-04-01

This study explores the effect of voice quality and competing speaker/-s on children's performance in a passage comprehension task. Furthermore, it explores the interaction between passage comprehension and cognitive functioning. Forty-nine children (27 girls and 22 boys) with normal hearing (aged 7-12 years) participated. Passage comprehension was tested in six different listening conditions; a typical voice (non-dysphonic voice) in quiet, a typical voice with one competing speaker, a typical voice with four competing speakers, a dysphonic voice in quiet, a dysphonic voice with one competing speaker, and a dysphonic voice with four competing speakers. The children's working memory capacity and executive functioning were also assessed. The findings indicate no direct effect of voice quality on the children's performance, but a significant effect of background listening condition. Interaction effects were seen between voice quality, background listening condition, and executive functioning. The children's susceptibility to the effect of the dysphonic voice and the background listening conditions are related to the individual's executive functions. The findings have several implications for design of interventions in language learning environments such as classrooms.

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.

The Effect of Task Complexity on Functional Adequacy, Fluency and Lexical Diversity in Speaking Performances of Native and Non-Native Speakers

ERIC Educational Resources Information Center

De Jong, Nivja H.; Steinel, Margarita P.; Florijn, Arjen F.; Schoonen, Rob; Hulstijn, Jan H.

2012-01-01

This study investigated how task complexity affected native and non-native speakers' speaking performance in terms of a measure of communicative success (functional adequacy), three types of fluency (breakdown fluency, speed fluency, and repair fluency), and lexical diversity. Participants (208 non-native and 59 native speakers of Dutch) carried…

"That Sounds So Cooool": Entanglements of Children, Digital Tools, and Literacy Practices

ERIC Educational Resources Information Center

Toohey, Kelleen; Dagenais, Diane; Fodor, Andreea; Hof, Linda; Nuñez, Omar; Singh, Angelpreet; Schulze, Liz

2015-01-01

Many observers have argued that minority language speakers often have difficulty with school-based literacy and that the poorer school achievement of such learners occurs at least partly as a result of these difficulties. At the same time, many have argued for a recognition of the multiple literacies required for citizens in a 21st century world.…

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

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…

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…

Transitivity, Space, and Hand: The Spatial Grounding of Syntax

ERIC Educational Resources Information Center

Boiteau, Timothy W.; Almor, Amit

2017-01-01

Previous research has linked the concept of number and other ordinal series to space via a spatially oriented mental number line. In addition, it has been shown that in visual scene recognition and production, speakers of a language with a left-to-right orthography respond faster to and tend to draw images in which the agent of an action is…

Making the Implicit Explicit: Raising Pragmatic Awareness in Trainee Interpreters Using Semiauthentic Spontaneous Discourse Samples

ERIC Educational Resources Information Center

Sachtleben, Annette; Denny, Heather

2012-01-01

Following the recent interest in the teaching of pragmatics and the recognition of its importance for both cross-cultural communication and new speakers of an additional language, the authors carried out an action research project to evaluate the effectiveness of a new approach to the teaching of pragmatics. This involved the use of semiauthentic…

Modern Greek Language: Acquisition of Morphology and Syntax by Non-Native Speakers

ERIC Educational Resources Information Center

Andreou, Georgia; Karapetsas, Anargyros; Galantomos, Ioannis

2008-01-01

This study investigated the performance of native and non native speakers of Modern Greek language on morphology and syntax tasks. Non-native speakers of Greek whose native language was English, which is a language with strict word order and simple morphology, made more errors and answered more slowly than native speakers on morphology but not…

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.

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.

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.

Memory for vocal tempo and pitch.

PubMed

Boltz, Marilyn G

2017-11-01

Two experiments examined the ability to remember the vocal tempo and pitch of different individuals, and the way this information is encoded into the cognitive system. In both studies, participants engaged in an initial familiarisation phase while attending was systematically directed towards different aspects of speakers' voices. Afterwards, they received a tempo or pitch recognition task. Experiment 1 showed that tempo and pitch are both incidentally encoded into memory at levels comparable to intentional learning, and no performance deficit occurs with divided attending. Experiment 2 examined the ability to recognise pitch or tempo when the two dimensions co-varied and found that the presence of one influenced the other: performance was best when both dimensions were positively correlated with one another. As a set, these findings indicate that pitch and tempo are automatically processed in a holistic, integral fashion [Garner, W. R. (1974). The processing of information and structure. Potomac, MD: Erlbaum.] which has a number of cognitive implications.

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.

Vocabulary Knowledge Predicts Lexical Processing: Evidence from a Group of Participants with Diverse Educational Backgrounds

PubMed Central

Mainz, Nina; Shao, Zeshu; Brysbaert, Marc; Meyer, Antje S.

2017-01-01

Vocabulary knowledge is central to a speaker's command of their language. In previous research, greater vocabulary knowledge has been associated with advantages in language processing. In this study, we examined the relationship between individual differences in vocabulary and language processing performance more closely by (i) using a battery of vocabulary tests instead of just one test, and (ii) testing not only university students (Experiment 1) but young adults from a broader range of educational backgrounds (Experiment 2). Five vocabulary tests were developed, including multiple-choice and open antonym and synonym tests and a definition test, and administered together with two established measures of vocabulary. Language processing performance was measured using a lexical decision task. In Experiment 1, vocabulary and word frequency were found to predict word recognition speed while we did not observe an interaction between the effects. In Experiment 2, word recognition performance was predicted by word frequency and the interaction between word frequency and vocabulary, with high-vocabulary individuals showing smaller frequency effects. While overall the individual vocabulary tests were correlated and showed similar relationships with language processing as compared to a composite measure of all tests, they appeared to share less variance in Experiment 2 than in Experiment 1. Implications of our findings concerning the assessment of vocabulary size in individual differences studies and the investigation of individuals from more varied backgrounds are discussed. PMID:28751871

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…

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.

Children's Understanding That Utterances Emanate from Minds: Using Speaker Belief To Aid Interpretation.

ERIC Educational Resources Information Center

Mitchell, Peter; Robinson, Elizabeth J.; Thompson, Doreen E.

1999-01-01

Three experiments examined 3- to 6-year olds' ability to use a speaker's utterance based on false belief to identify which of several referents was intended. Found that many 4- to 5-year olds performed correctly only when it was unnecessary to consider the speaker's belief. When the speaker gave an ambiguous utterance, many 3- to 6-year olds…

U.S. Air Forces Escape and Evasion Society Recognition Act of 2014

THOMAS, 113th Congress

Rep. Tsongas, Niki [D-MA-3

2014-05-20

House - 05/20/2014 Referred to the Committee on Financial Services, and in addition to the Committee on House Administration, for a period to be subsequently determined by the Speaker, in each case for consideration of such provisions as fall within the jurisdiction of the committee... (All Actions) Tracker: This bill has the status IntroducedHere are the steps for Status of Legislation:

Recognition and Comprehension of "Narrow Focus" by Young Adults with Prelingual Hearing Loss Using Hearing Aids or Cochlear Implants

ERIC Educational Resources Information Center

Segal, Osnat; Kishon-Rabin, Liat

2017-01-01

Purpose: The stressed word in a sentence (narrow focus [NF]) conveys information about the intent of the speaker and is therefore important for processing spoken language and in social interactions. The ability of participants with severe-to-profound prelingual hearing loss to comprehend NF has rarely been investigated. The purpose of this study…

Spanish as the Second National Language of the United States: Fact, Future, Fiction, or Hope?

ERIC Educational Resources Information Center

Macías, Reynaldo F.

2014-01-01

The status of a language is very often described and measured by different factors, including the length of time it has been in use in a particular territory, the official recognition it has been given by governmental units, and the number and proportion of speakers. Spanish has a unique history and, so some argue status, in the contemporary…

Metalinguistic awareness and reading performance: a cross language comparison.

PubMed

Ibrahim, Raphiq; Eviatar, Zohar; Aharon-Peretz, Judith

2007-07-01

The study examined two questions: (1) do the greater phonological awareness skills of billinguals affect reading performance; (2) to what extent do the orthographic characteristics of a language influence reading performance and how does this interact with the effects of phonological awareness. We estimated phonological metalinguistic abilities and reading measures in three groups of first graders: monolingual Hebrew speakers, bilingual Russian-Hebrew speakers, and Arabic-speaking children. We found that language experience affects phonological awareness, as both Russian-Hebrew bilinguals and the Arabic speakers achieved higher scores on metalinguistic tests than Hebrew speakers. Orthography affected reading measures and their correlation with phonological abilitites. Children reading Hebrew showed better text reading ability and significant correlations between phonological awareness and reading scores. Children reading Arabic showed a slight advantage in single word and nonword reading over the two Hebrew reading groups, and very weak relationships between phonological abilities and reading performance. We conclude that native Arabic speakers have more difficulty in processing Arabic orthography than Hebrew monolinguals and bilinguals have in processing Hebrew orthography, and suggest that this is due to the additional visual complexity of Arabic orthography.

Cross-cultural emotional prosody recognition: evidence from Chinese and British listeners.

PubMed

Paulmann, Silke; Uskul, Ayse K

2014-01-01

This cross-cultural study of emotional tone of voice recognition tests the in-group advantage hypothesis (Elfenbein & Ambady, 2002) employing a quasi-balanced design. Individuals of Chinese and British background were asked to recognise pseudosentences produced by Chinese and British native speakers, displaying one of seven emotions (anger, disgust, fear, happy, neutral tone of voice, sad, and surprise). Findings reveal that emotional displays were recognised at rates higher than predicted by chance; however, members of each cultural group were more accurate in recognising the displays communicated by a member of their own cultural group than a member of the other cultural group. Moreover, the evaluation of error matrices indicates that both culture groups relied on similar mechanism when recognising emotional displays from the voice. Overall, the study reveals evidence for both universal and culture-specific principles in vocal emotion recognition.

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.

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.

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

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.

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.

Classifying Human Voices by Using Hybrid SFX Time-Series Preprocessing and Ensemble Feature Selection

PubMed Central

Wong, Raymond

2013-01-01

Voice biometrics is one kind of physiological characteristics whose voice is different for each individual person. Due to this uniqueness, voice classification has found useful applications in classifying speakers' gender, mother tongue or ethnicity (accent), emotion states, identity verification, verbal command control, and so forth. In this paper, we adopt a new preprocessing method named Statistical Feature Extraction (SFX) for extracting important features in training a classification model, based on piecewise transformation treating an audio waveform as a time-series. Using SFX we can faithfully remodel statistical characteristics of the time-series; together with spectral analysis, a substantial amount of features are extracted in combination. An ensemble is utilized in selecting only the influential features to be used in classification model induction. We focus on the comparison of effects of various popular data mining algorithms on multiple datasets. Our experiment consists of classification tests over four typical categories of human voice data, namely, Female and Male, Emotional Speech, Speaker Identification, and Language Recognition. The experiments yield encouraging results supporting the fact that heuristically choosing significant features from both time and frequency domains indeed produces better performance in voice classification than traditional signal processing techniques alone, like wavelets and LPC-to-CC. PMID:24288684

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.

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.

Boost OCR accuracy using iVector based system combination approach

NASA Astrophysics Data System (ADS)

Peng, Xujun; Cao, Huaigu; Natarajan, Prem

2015-01-01

Optical character recognition (OCR) is a challenging task because most existing preprocessing approaches are sensitive to writing style, writing material, noises and image resolution. Thus, a single recognition system cannot address all factors of real document images. In this paper, we describe an approach to combine diverse recognition systems by using iVector based features, which is a newly developed method in the field of speaker verification. Prior to system combination, document images are preprocessed and text line images are extracted with different approaches for each system, where iVector is transformed from a high-dimensional supervector of each text line and is used to predict the accuracy of OCR. We merge hypotheses from multiple recognition systems according to the overlap ratio and the predicted OCR score of text line images. We present evaluation results on an Arabic document database where the proposed method is compared against the single best OCR system using word error rate (WER) metric.

Recognition and Comprehension of "Narrow Focus" by Young Adults With Prelingual Hearing Loss Using Hearing Aids or Cochlear Implants.

PubMed

Segal, Osnat; Kishon-Rabin, Liat

2017-12-20

The stressed word in a sentence (narrow focus [NF]) conveys information about the intent of the speaker and is therefore important for processing spoken language and in social interactions. The ability of participants with severe-to-profound prelingual hearing loss to comprehend NF has rarely been investigated. The purpose of this study was to assess the recognition and comprehension of NF by young adults with prelingual hearing loss compared with those of participants with normal hearing (NH). The participants included young adults with hearing aids (HA; n = 10), cochlear implants (CI; n = 12), and NH (n = 18). The test material included the Hebrew Narrow Focus Test (Segal, Kaplan, Patael, & Kishon-Rabin, in press), with 3 subtests, which was used to assess the recognition and comprehension of NF in different contexts. The following results were obtained: (a) CI and HA users successfully recognized the stressed word, with the worst performance for CI; (b) HA and CI comprehended NF less well than NH; and (c) the comprehension of NF was associated with verbal working memory and expressive vocabulary in CI users. Most CI and HA users were able to recognize the stressed word in a sentence but had considerable difficulty understanding it. Different factors may contribute to this difficulty, including the memory load during the task itself and linguistic and pragmatic abilities. https://doi.org/10.23641/asha.5572792.

The effect of voice quality and competing speakers in a passage comprehension task: perceived effort in relation to cognitive functioning and performance in children with normal hearing.

PubMed

von Lochow, Heike; Lyberg-Åhlander, Viveka; Sahlén, Birgitta; Kastberg, Tobias; Brännström, K Jonas

2018-04-01

The study investigates the effect of voice quality and competing speakers on perceived effort in a passage comprehension task in relation to cognitive functioning. In addition, it explores if perceived effort was related to performance. A total of 49 children (aged 7:03 to 12:02 years) with normal hearing participated. The children performed an auditory passage comprehension task presented with six different listening conditions consisting of a typical voice or a dysphonic voice presented in quiet, with one competing speaker, and with four competing speakers. After completing the task, they rated their perceived effort on a five-grade scale. The children also performed tasks measuring working memory capacity (WMC) and executive functioning. The results show that voice quality had no direct effect on perceived effort but the children's ratings of perceived effort were related to their executive functioning. A significant effect was seen for background listening condition indicating higher perceived effort for background listening conditions with competing speakers. The effects of background listening condition were mainly related to the children's WMC but also their executive functioning. It can be concluded that the individual susceptibility to the effect of the dysphonic voice is related to the child's executive functioning. The individual susceptibility to the presence of competing speakers is related to the child's WMC and executive functioning.

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

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

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.…

The Death of the Non-Native Speaker? English as a Lingua Franca in Business Communication: A Research Agenda

ERIC Educational Resources Information Center

Nickerson, Catherine

2015-01-01

The impact of globalisation in the last 20 years has led to an overwhelming increase in the use of English as the medium through which many business people get their work done. As a result, the linguistic landscape within which we now operate as researchers and teachers has changed both rapidly and beyond all recognition. In the discussion below,…

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

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…

Gisting Technique Development.

DTIC Science & Technology

1981-12-01

furnished tapes (" Stonehenge " database) which were used for previous contracts. Recognition results for English male and female speakers are presented in...independent " Stonehenge " test data. A variety of options in generating word arrays were tried; the results below describe the most successful of these. The...time to carry out any quantitative tests, ............. Page 22 even the obvious one of retraining the " Stonehenge " English vocabulary on-line, we

Crossmodal plasticity in the fusiform gyrus of late blind individuals during voice recognition.

PubMed

Hölig, Cordula; Föcker, Julia; Best, Anna; Röder, Brigitte; Büchel, Christian

2014-12-01

Blind individuals are trained in identifying other people through voices. In congenitally blind adults the anterior fusiform gyrus has been shown to be active during voice recognition. Such crossmodal changes have been associated with a superiority of blind adults in voice perception. The key question of the present functional magnetic resonance imaging (fMRI) study was whether visual deprivation that occurs in adulthood is followed by similar adaptive changes of the voice identification system. Late blind individuals and matched sighted participants were tested in a priming paradigm, in which two voice stimuli were subsequently presented. The prime (S1) and the target (S2) were either from the same speaker (person-congruent voices) or from two different speakers (person-incongruent voices). Participants had to classify the S2 as either coming from an old or a young person. Only in late blind but not in matched sighted controls, the activation in the anterior fusiform gyrus was modulated by voice identity: late blind volunteers showed an increase of the BOLD signal in response to person-incongruent compared with person-congruent trials. These results suggest that the fusiform gyrus adapts to input of a new modality even in the mature brain and thus demonstrate an adult type of crossmodal plasticity. Copyright © 2014 Elsevier Inc. All rights reserved.

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.

Recognition memory and awareness: occurrence of perceptual effects in remembering or in knowing depends on conscious resources at encoding, but not at retrieval.

PubMed

Gardiner, John M; Gregg, Vernon H; Karayianni, Irene

2006-03-01

We report four experiments in which a remember-know paradigm was combined with a response deadline procedure in order to assess memory awareness in fast, as compared with slow,recognition judgments. In the experiments, we also investigated the perceptual effects of study-test congruence, either for picture size or for speaker's voice, following either full or divided attention at study. These perceptual effects occurred in remembering with full attention and in knowing with divided attention, but they were uninfluenced by recognition speed, indicating that their occurrence in remembering or knowing depends more on conscious resources at encoding than on those at retrieval. The results have implications for theoretical accounts of remembering and knowing that assume that remembering is more consciously controlled and effortful, whereas knowing is more automatic and faster.

Sensitivity-Enhanced Wearable Active Voiceprint Sensor Based on Cellular Polypropylene Piezoelectret.

PubMed

Li, Wenbo; Zhao, Sheng; Wu, Nan; Zhong, Junwen; Wang, Bo; Lin, Shizhe; Chen, Shuwen; Yuan, Fang; Jiang, Hulin; Xiao, Yongjun; Hu, Bin; Zhou, Jun

2017-07-19

Wearable active sensors have extensive applications in mobile biosensing and human-machine interaction but require good flexibility, high sensitivity, excellent stability, and self-powered feature. In this work, cellular polypropylene (PP) piezoelectret was chosen as the core material of a sensitivity-enhanced wearable active voiceprint sensor (SWAVS) to realize voiceprint recognition. By virtue of the dipole orientation control method, the air layers in the piezoelectret were efficiently utilized, and the current sensitivity was enhanced (from 1.98 pA/Hz to 5.81 pA/Hz at 115 dB). The SWAVS exhibited the superiorities of high sensitivity, accurate frequency response, and excellent stability. The voiceprint recognition system could make correct reactions to human voices by judging both the password and speaker. This study presented a voiceprint sensor with potential applications in noncontact biometric recognition and safety guarantee systems, promoting the progress of wearable sensor networks.

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.

Loudspeaker Performance Aid

NASA Technical Reports Server (NTRS)

1980-01-01

Many manufacturers of loudspeakers are now using a magnetic liquid cooling agent known as ferrofluid. Commercialized by Ferrofluids Corporation, ferrofluid is a liquid material in which sub-microscopic particles of iron oxide are permanently suspended. Injected into the voice coil segment of speaker system, magnetic liquid serves as superior heat transfer medium for cooling the voice coil, thus substantially increasing the system's ability to handle higher power levels and decreasing chance of speaker failure. Ferrofluid offers several additional advantages which add up to improved speaker performance, lower manufacturing costs and fewer rejects.

The Status of Native Speaker Intuitions in a Polylectal Grammar.

ERIC Educational Resources Information Center

Debose, Charles E.

A study of one speaker's intuitions about and performance in Black English is presented with relation to Saussure's "langue-parole" dichotomy. Native speakers of a language have intuitions about the static synchronic entities although the data of their speaking is variable and panchronic. These entities are in a diglossic relationship to each…

TESOL Teachers' Engagement with the Native Speaker Model: How Does Teacher Education Impact on Their Beliefs?

ERIC Educational Resources Information Center

Nguyen, Mai Xuan Nhat Chi

2017-01-01

This research investigates non-native English teachers' engagement with the native speaker model, i.e. whether they agree/disagree with measuring English teaching and learning performance against native speaker standards. More importantly, it aims to unearth the impact of teacher education on teachers' attitudes and beliefs about…

Effects of tonal language background on tests of temporal sequencing in children.

PubMed

Mukari, Siti Zamratol-Mai S; Yu, Xuan; Ishak, Wan Syafira; Mazlan, Rafidah

2015-01-01

The aims of the present study were to determine the effects of language background on the performance of the pitch pattern sequence test (PPST) and duration pattern sequence test (DPST). As temporal order sequencing may be affected by age and working memory, these factors were also studied. Performance of tonal and non-tonal language speakers on PPST and DPST were compared. Twenty-eight native Mandarin (tonal language) speakers and twenty-nine native Malay (non-tonal language) speakers between seven to nine years old participated in this study. The results revealed that relative to native Malay speakers, native Mandarin speakers demonstrated better scores on the PPST in both humming and verbal labeling responses. However, a similar language effect was not apparent in the DPST. An age effect was only significant in the PPST (verbal labeling). Finally, no significant effect of working memory was found on the PPST and the DPST. These findings suggest that the PPST is affected by tonal language background, and highlight the importance of developing different normative values for tonal and non-tonal language speakers.

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.

Development of an auditory situation awareness test battery for advanced hearing protectors and TCAPS: detection subtest of DRILCOM (detection-recognition/identification-localization-communication).

PubMed

Lee, Kichol; Casali, John G

2017-01-01

To design a test battery and conduct a proof-of-concept experiment of a test method that can be used to measure the detection performance afforded by military advanced hearing protection devices (HPDs) and tactical communication and protective systems (TCAPS). The detection test was conducted with each of the four loudspeakers located at front, right, rear and left of the participant. Participants wore 2 in-ear-type TCAPS, 1 earmuff-type TCAPS, a passive Combat Arms Earplug in its "open" or pass-through setting and an EB-15LE™ electronic earplug. Devices with electronic gain systems were tested under two gain settings: "unity" and "max". Testing without any device (open ear) was conducted as a control. Ten participants with audiometric requirements of 25 dBHL or better at 500, 1000, 2000, 4000, 8000 Hz in both ears. Detection task performance varied with different signals and speaker locations. The test identified performance differences among certain TCAPS and protectors, and the open ear. A computer-controlled detection subtest of the Detection-Recognition/Identification-Localisation-Communication (DRILCOM) test battery was designed and implemented. Tested in a proof-of-concept experiment, it showed statistically-significant sensitivity to device differences in detection effects with the small sample of participants (10). This result has important implications for selection and deployment of TCAPS and HPDs on soldiers and workers in dynamic situations.

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

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.

You had me at "Hello": Rapid extraction of dialect information from spoken words.

PubMed

Scharinger, Mathias; Monahan, Philip J; Idsardi, William J

2011-06-15

Research on the neuronal underpinnings of speaker identity recognition has identified voice-selective areas in the human brain with evolutionary homologues in non-human primates who have comparable areas for processing species-specific calls. Most studies have focused on estimating the extent and location of these areas. In contrast, relatively few experiments have investigated the time-course of speaker identity, and in particular, dialect processing and identification by electro- or neuromagnetic means. We show here that dialect extraction occurs speaker-independently, pre-attentively and categorically. We used Standard American English and African-American English exemplars of 'Hello' in a magnetoencephalographic (MEG) Mismatch Negativity (MMN) experiment. The MMN as an automatic change detection response of the brain reflected dialect differences that were not entirely reducible to acoustic differences between the pronunciations of 'Hello'. Source analyses of the M100, an auditory evoked response to the vowels suggested additional processing in voice-selective areas whenever a dialect change was detected. These findings are not only relevant for the cognitive neuroscience of language, but also for the social sciences concerned with dialect and race perception. Copyright © 2011 Elsevier Inc. All rights reserved.

Speaker-Sex Discrimination for Voiced and Whispered Vowels at Short Durations.

PubMed

Smith, David R R

2016-01-01

Whispered vowels, produced with no vocal fold vibration, lack the periodic temporal fine structure which in voiced vowels underlies the perceptual attribute of pitch (a salient auditory cue to speaker sex). Voiced vowels possess no temporal fine structure at very short durations (below two glottal cycles). The prediction was that speaker-sex discrimination performance for whispered and voiced vowels would be similar for very short durations but, as stimulus duration increases, voiced vowel performance would improve relative to whispered vowel performance as pitch information becomes available. This pattern of results was shown for women's but not for men's voices. A whispered vowel needs to have a duration three times longer than a voiced vowel before listeners can reliably tell whether it's spoken by a man or woman (∼30 ms vs. ∼10 ms). Listeners were half as sensitive to information about speaker-sex when it is carried by whispered compared with voiced vowels.

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.

Comparable Common Factors in English Homophone Recognition. Report from the Project on Situational Variables and Efficiency of Concept Learning.

ERIC Educational Resources Information Center

Houston, Thomas Rappe, Jr.

A homophone is a word having the same pronunciation as another English word, but a different spelling. A list of 7,300 English homophones was compiled and used to construct two tests. Scores were obtained in these and on reference tests for J. P. Guilford's factors CMU, CSU, DMU, and DSU for 70 native speakers of midwestern American English from a…

L1 and L2 Word Recognotion in Finnish. Examining L1 Effects on L2 Processing of Morphological Complexity and Morphophonological Transparency

ERIC Educational Resources Information Center

Vainio, Seppo; Anneli, Pajunen; Hyona, Jukka

2014-01-01

This study investigated the effect of the first language (L1) on the visual word recognition of inflected nouns in second language (L2) Finnish by native Russian and Chinese speakers. Case inflection is common in Russian and in Finnish but nonexistent in Chinese. Several models have been posited to describe L2 morphological processing. The unified…

Scalable Learning for Geostatistics and Speaker Recognition

DTIC Science & Technology

2011-01-01

of prior knowledge of the model or due to improved robustness requirements). Both these methods have their own advantages and disadvantages. The use...application. If the data is well-correlated and low-dimensional, any prior knowledge available on the data can be used to build a parametric model. In the...absence of prior knowledge , non-parametric methods can be used. If the data is high-dimensional, PCA based dimensionality reduction is often the first

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…

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.

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.

High Performance Computing at NASA

NASA Technical Reports Server (NTRS)

Bailey, David H.; Cooper, D. M. (Technical Monitor)

1994-01-01

The speaker will give an overview of high performance computing in the U.S. in general and within NASA in particular, including a description of the recently signed NASA-IBM cooperative agreement. The latest performance figures of various parallel systems on the NAS Parallel Benchmarks will be presented. The speaker was one of the authors of the NAS (National Aerospace Standards) Parallel Benchmarks, which are now widely cited in the industry as a measure of sustained performance on realistic high-end scientific applications. It will be shown that significant progress has been made by the highly parallel supercomputer industry during the past year or so, with several new systems, based on high-performance RISC processors, that now deliver superior performance per dollar compared to conventional supercomputers. Various pitfalls in reporting performance will be discussed. The speaker will then conclude by assessing the general state of the high performance computing field.

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.

Experiments on Urdu Text Recognition

NASA Astrophysics Data System (ADS)

Mukhtar, Omar; Setlur, Srirangaraj; Govindaraju, Venu

Urdu is a language spoken in the Indian subcontinent by an estimated 130-270 million speakers. At the spoken level, Urdu and Hindi are considered dialects of a single language because of shared vocabulary and the similarity in grammar. At the written level, however, Urdu is much closer to Arabic because it is written in Nastaliq, the calligraphic style of the Persian-Arabic script. Therefore, a speaker of Hindi can understand spoken Urdu but may not be able to read written Urdu because Hindi is written in Devanagari script, whereas an Arabic writer can read the written words but may not understand the spoken Urdu. In this chapter we present an overview of written Urdu. Prior research in handwritten Urdu OCR is very limited. We present (perhaps) the first system for recognizing handwritten Urdu words. On a data set of about 1300 handwritten words, we achieved an accuracy of 70% for the top choice, and 82% for the top three choices.

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.

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.

Is the superior verbal memory span of Mandarin speakers due to faster rehearsal?

PubMed

Mattys, Sven L; Baddeley, Alan; Trenkic, Danijela

2018-04-01

It is well established that digit span in native Chinese speakers is atypically high. This is commonly attributed to a capacity for more rapid subvocal rehearsal for that group. We explored this hypothesis by testing a group of English-speaking native Mandarin speakers on digit span and word span in both Mandarin and English, together with a measure of speed of articulation for each. When compared to the performance of native English speakers, the Mandarin group proved to be superior on both digit and word spans while predictably having lower spans in English. This suggests that the Mandarin advantage is not limited to digits. Speed of rehearsal correlated with span performance across materials. However, this correlation was more pronounced for English speakers than for any of the Chinese measures. Further analysis suggested that speed of rehearsal did not provide an adequate account of differences between Mandarin and English spans or for the advantage of digits over words. Possible alternative explanations are discussed.

A Study of Non-Native English Speakers' Academic Performance at Santa Ana College.

ERIC Educational Resources Information Center

Slark, Julie; Bateman, Harold

A study was conducted in 1980-81 at Santa Ana College (SAC) to collect data on the English communication skills of non-native English speakers and to determine if a relationship existed between these skills and student's educational success. A sample of 22 classes, with an enrollment of at least 50% non-native English speakers and representing a…

[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.

Bystander capability to activate speaker function for continuous dispatcher assisted CPR in case of suspected cardiac arrest.

PubMed

Steensberg, Alvilda T; Eriksen, Mette M; Andersen, Lars B; Hendriksen, Ole M; Larsen, Heinrich D; Laier, Gunnar H; Thougaard, Thomas

2017-06-01

The European Resuscitation Council Guidelines 2015 recommend bystanders to activate their mobile phone speaker function, if possible, in case of suspected cardiac arrest. This is to facilitate continuous dialogue with the dispatcher including (if required) cardiopulmonary resuscitation instructions. The aim of this study was to measure the bystander capability to activate speaker function in case of suspected cardiac arrest. In 87days, a systematic prospective registration of bystander capability to activate the speaker function, when cardiac arrest was suspected, was performed. For those asked, "can you activate your mobile phone's speaker function", audio recordings were examined and categorized into groups according to the bystanders capability to activate speaker function on their own initiative, without instructions, or with instructions from the emergency medical dispatcher. Time delay was measured, in seconds, for the bystanders without pre-activated speaker function. 42.0% (58) was able to activate the speaker function without instructions, 2.9% (4) with instructions, 18.1% (25) on own initiative and 37.0% (51) were unable to activate the speaker function. The median time to activate speaker function was 19s and 8s, with and without instructions, respectively. Dispatcher assisted cardiopulmonary resuscitation with activated speaker function, in cases of suspected cardiac arrest, allows for continuous dialogue between the emergency medical dispatcher and the bystander. In this study, we found a 63.0% success rate of activating the speaker function in such situations. Copyright © 2017 Elsevier B.V. All rights reserved.

Center for Neural Engineering: applications of pulse-coupled neural networks

NASA Astrophysics Data System (ADS)

Malkani, Mohan; Bodruzzaman, Mohammad; Johnson, John L.; Davis, Joel

1999-03-01

Pulsed-Coupled Neural Network (PCNN) is an oscillatory model neural network where grouping of cells and grouping among the groups that form the output time series (number of cells that fires in each input presentation also called `icon'). This is based on the synchronicity of oscillations. Recent work by Johnson and others demonstrated the functional capabilities of networks containing such elements for invariant feature extraction using intensity maps. PCNN thus presents itself as a more biologically plausible model with solid functional potential. This paper will present the summary of several projects and their results where we successfully applied PCNN. In project one, the PCNN was applied for object recognition and classification through a robotic vision system. The features (icons) generated by the PCNN were then fed into a feedforward neural network for classification. In project two, we developed techniques for sensory data fusion. The PCNN algorithm was implemented and tested on a B14 mobile robot. The PCNN-based features were extracted from the images taken from the robot vision system and used in conjunction with the map generated by data fusion of the sonar and wheel encoder data for the navigation of the mobile robot. In our third project, we applied the PCNN for speaker recognition. The spectrogram image of speech signals are fed into the PCNN to produce invariant feature icons which are then fed into a feedforward neural network for speaker identification.

Speaker-Sex Discrimination for Voiced and Whispered Vowels at Short Durations

PubMed Central

2016-01-01

Whispered vowels, produced with no vocal fold vibration, lack the periodic temporal fine structure which in voiced vowels underlies the perceptual attribute of pitch (a salient auditory cue to speaker sex). Voiced vowels possess no temporal fine structure at very short durations (below two glottal cycles). The prediction was that speaker-sex discrimination performance for whispered and voiced vowels would be similar for very short durations but, as stimulus duration increases, voiced vowel performance would improve relative to whispered vowel performance as pitch information becomes available. This pattern of results was shown for women’s but not for men’s voices. A whispered vowel needs to have a duration three times longer than a voiced vowel before listeners can reliably tell whether it’s spoken by a man or woman (∼30 ms vs. ∼10 ms). Listeners were half as sensitive to information about speaker-sex when it is carried by whispered compared with voiced vowels. PMID:27757218

Parallel photonic information processing at gigabyte per second data rates using transient states

NASA Astrophysics Data System (ADS)

Brunner, Daniel; Soriano, Miguel C.; Mirasso, Claudio R.; Fischer, Ingo

2013-01-01

The increasing demands on information processing require novel computational concepts and true parallelism. Nevertheless, hardware realizations of unconventional computing approaches never exceeded a marginal existence. While the application of optics in super-computing receives reawakened interest, new concepts, partly neuro-inspired, are being considered and developed. Here we experimentally demonstrate the potential of a simple photonic architecture to process information at unprecedented data rates, implementing a learning-based approach. A semiconductor laser subject to delayed self-feedback and optical data injection is employed to solve computationally hard tasks. We demonstrate simultaneous spoken digit and speaker recognition and chaotic time-series prediction at data rates beyond 1Gbyte/s. We identify all digits with very low classification errors and perform chaotic time-series prediction with 10% error. Our approach bridges the areas of photonic information processing, cognitive and information science.

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

Encoding, rehearsal, and recall in signers and speakers: shared network but differential engagement.

PubMed

Bavelier, D; Newman, A J; Mukherjee, M; Hauser, P; Kemeny, S; Braun, A; Boutla, M

2008-10-01

Short-term memory (STM), or the ability to hold verbal information in mind for a few seconds, is known to rely on the integrity of a frontoparietal network of areas. Here, we used functional magnetic resonance imaging to ask whether a similar network is engaged when verbal information is conveyed through a visuospatial language, American Sign Language, rather than speech. Deaf native signers and hearing native English speakers performed a verbal recall task, where they had to first encode a list of letters in memory, maintain it for a few seconds, and finally recall it in the order presented. The frontoparietal network described to mediate STM in speakers was also observed in signers, with its recruitment appearing independent of the modality of the language. This finding supports the view that signed and spoken STM rely on similar mechanisms. However, deaf signers and hearing speakers differentially engaged key structures of the frontoparietal network as the stages of STM unfold. In particular, deaf signers relied to a greater extent than hearing speakers on passive memory storage areas during encoding and maintenance, but on executive process areas during recall. This work opens new avenues for understanding similarities and differences in STM performance in signers and speakers.

Encoding, Rehearsal, and Recall in Signers and Speakers: Shared Network but Differential Engagement

PubMed Central

Newman, A. J.; Mukherjee, M.; Hauser, P.; Kemeny, S.; Braun, A.; Boutla, M.

2008-01-01

Short-term memory (STM), or the ability to hold verbal information in mind for a few seconds, is known to rely on the integrity of a frontoparietal network of areas. Here, we used functional magnetic resonance imaging to ask whether a similar network is engaged when verbal information is conveyed through a visuospatial language, American Sign Language, rather than speech. Deaf native signers and hearing native English speakers performed a verbal recall task, where they had to first encode a list of letters in memory, maintain it for a few seconds, and finally recall it in the order presented. The frontoparietal network described to mediate STM in speakers was also observed in signers, with its recruitment appearing independent of the modality of the language. This finding supports the view that signed and spoken STM rely on similar mechanisms. However, deaf signers and hearing speakers differentially engaged key structures of the frontoparietal network as the stages of STM unfold. In particular, deaf signers relied to a greater extent than hearing speakers on passive memory storage areas during encoding and maintenance, but on executive process areas during recall. This work opens new avenues for understanding similarities and differences in STM performance in signers and speakers. PMID:18245041

Perception of contrastive bi-syllabic lexical stress in unaccented and accented words by younger and older listeners.

PubMed

Gordon-Salant, Sandra; Yeni-Komshian, Grace H; Pickett, Erin J; Fitzgibbons, Peter J

2016-03-01

This study examined the ability of older and younger listeners to perceive contrastive syllable stress in unaccented and Spanish-accented cognate bi-syllabic English words. Younger listeners with normal hearing, older listeners with normal hearing, and older listeners with hearing impairment judged recordings of words that contrasted in stress that conveyed a noun or verb form (e.g., CONduct/conDUCT), using two paradigms differing in the amount of semantic support. The stimuli were spoken by four speakers: one native English speaker and three Spanish-accented speakers (one moderately and two mildly accented). The results indicate that all listeners showed the lowest accuracy scores in responding to the most heavily accented speaker and the highest accuracy in judging the productions of the native English speaker. The two older groups showed lower accuracy in judging contrastive lexical stress than the younger group, especially for verbs produced by the most accented speaker. This general pattern of performance was observed in the two experimental paradigms, although performance was generally lower in the paradigm without semantic support. The findings suggest that age-related difficulty in adjusting to deviations in contrastive bi-syllabic lexical stress produced with a Spanish accent may be an important factor limiting perception of accented English by older people.

Perception of contrastive bi-syllabic lexical stress in unaccented and accented words by younger and older listeners

PubMed Central

Gordon-Salant, Sandra; Yeni-Komshian, Grace H.; Pickett, Erin J.; Fitzgibbons, Peter J.

2016-01-01

This study examined the ability of older and younger listeners to perceive contrastive syllable stress in unaccented and Spanish-accented cognate bi-syllabic English words. Younger listeners with normal hearing, older listeners with normal hearing, and older listeners with hearing impairment judged recordings of words that contrasted in stress that conveyed a noun or verb form (e.g., CONduct/conDUCT), using two paradigms differing in the amount of semantic support. The stimuli were spoken by four speakers: one native English speaker and three Spanish-accented speakers (one moderately and two mildly accented). The results indicate that all listeners showed the lowest accuracy scores in responding to the most heavily accented speaker and the highest accuracy in judging the productions of the native English speaker. The two older groups showed lower accuracy in judging contrastive lexical stress than the younger group, especially for verbs produced by the most accented speaker. This general pattern of performance was observed in the two experimental paradigms, although performance was generally lower in the paradigm without semantic support. The findings suggest that age-related difficulty in adjusting to deviations in contrastive bi-syllabic lexical stress produced with a Spanish accent may be an important factor limiting perception of accented English by older people. PMID:27036250

To award a Congressional Gold Medal to the Freedom Riders, collectively, in recognition of their unique contribution to Civil Rights, which inspired a revolutionary movement for equality in interstate travel.

THOMAS, 113th Congress

Rep. Johnson, Henry C. "Hank," Jr. [D-GA-4

2014-02-11

House - 02/11/2014 Referred to the Committee on Financial Services, and in addition to the Committee on House Administration, for a period to be subsequently determined by the Speaker, in each case for consideration of such provisions as fall within the jurisdiction of the committee... (All Actions) Tracker: This bill has the status IntroducedHere are the steps for Status of Legislation:

Membrane Estrogen Receptor Alpha Targeting and its Association with SHC in Regulating Breast Cancer Cell Proliferation

DTIC Science & Technology

2004-06-01

American Society for Cell Biology, San Francisco , California, Dec. 13-17, 2003. 3. Invited speaker in one of symposiums "Recognition of estrogen receptor in...Oncology, Bahamonde MI, Mann GE, Vergara C, Latorre R 1999 University of Virginia Health Science Center, Charlottesville, Acute activation of Maxi-K...intracellular Bahamonde, G.E. Mann, C. Vergara , R. Latorre, Acute activa- calcium, Proc. Nati. Acad. Sci. USA. 96 (1999) 4686-4691. tion of Maxi-K channels by

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

Common constraints limit Korean and English character recognition in peripheral vision.

PubMed

He, Yingchen; Kwon, MiYoung; Legge, Gordon E

2018-01-01

The visual span refers to the number of adjacent characters that can be recognized in a single glance. It is viewed as a sensory bottleneck in reading for both normal and clinical populations. In peripheral vision, the visual span for English characters can be enlarged after training with a letter-recognition task. Here, we examined the transfer of training from Korean to English characters for a group of bilingual Korean native speakers. In the pre- and posttests, we measured visual spans for Korean characters and English letters. Training (1.5 hours × 4 days) consisted of repetitive visual-span measurements for Korean trigrams (strings of three characters). Our training enlarged the visual spans for Korean single characters and trigrams, and the benefit transferred to untrained English symbols. The improvement was largely due to a reduction of within-character and between-character crowding in Korean recognition, as well as between-letter crowding in English recognition. We also found a negative correlation between the size of the visual span and the average pattern complexity of the symbol set. Together, our results showed that the visual span is limited by common sensory (crowding) and physical (pattern complexity) factors regardless of the language script, providing evidence that the visual span reflects a universal bottleneck for text recognition.

Common constraints limit Korean and English character recognition in peripheral vision

PubMed Central

He, Yingchen; Kwon, MiYoung; Legge, Gordon E.

2018-01-01

The visual span refers to the number of adjacent characters that can be recognized in a single glance. It is viewed as a sensory bottleneck in reading for both normal and clinical populations. In peripheral vision, the visual span for English characters can be enlarged after training with a letter-recognition task. Here, we examined the transfer of training from Korean to English characters for a group of bilingual Korean native speakers. In the pre- and posttests, we measured visual spans for Korean characters and English letters. Training (1.5 hours × 4 days) consisted of repetitive visual-span measurements for Korean trigrams (strings of three characters). Our training enlarged the visual spans for Korean single characters and trigrams, and the benefit transferred to untrained English symbols. The improvement was largely due to a reduction of within-character and between-character crowding in Korean recognition, as well as between-letter crowding in English recognition. We also found a negative correlation between the size of the visual span and the average pattern complexity of the symbol set. Together, our results showed that the visual span is limited by common sensory (crowding) and physical (pattern complexity) factors regardless of the language script, providing evidence that the visual span reflects a universal bottleneck for text recognition. PMID:29327041

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.

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.

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.

Evaluation of speaker de-identification based on voice gender and age conversion

NASA Astrophysics Data System (ADS)

Přibil, Jiří; Přibilová, Anna; Matoušek, Jindřich

2018-03-01

Two basic tasks are covered in this paper. The first one consists in the design and practical testing of a new method for voice de-identification that changes the apparent age and/or gender of a speaker by multi-segmental frequency scale transformation combined with prosody modification. The second task is aimed at verification of applicability of a classifier based on Gaussian mixture models (GMM) to detect the original Czech and Slovak speakers after applied voice deidentification. The performed experiments confirm functionality of the developed gender and age conversion for all selected types of de-identification which can be objectively evaluated by the GMM-based open-set classifier. The original speaker detection accuracy was compared also for sentences uttered by German and English speakers showing language independence of the proposed method.

Selective social learning in infancy: looking for mechanisms.

PubMed

Crivello, Cristina; Phillips, Sara; Poulin-Dubois, Diane

2018-05-01

Although there is mounting evidence that selective social learning begins in infancy, the psychological mechanisms underlying this ability are currently a controversial issue. The purpose of this study is to investigate whether theory of mind abilities and statistical learning skills are related to infants' selective social learning. Seventy-seven 18-month-olds were first exposed to a reliable or an unreliable speaker and then completed a word learning task, two theory of mind tasks, and a statistical learning task. If domain-general abilities are linked to selective social learning, then infants who demonstrate superior performance on the statistical learning task should perform better on the selective learning task, that is, should be less likely to learn words from an unreliable speaker. Alternatively, if domain-specific abilities are involved, then superior performance on theory of mind tasks should be related to selective learning performance. Findings revealed that, as expected, infants were more likely to learn a novel word from a reliable speaker. Importantly, infants who passed a theory of mind task assessing knowledge attribution were significantly less likely to learn a novel word from an unreliable speaker compared to infants who failed this task. No such effect was observed for the other tasks. These results suggest that infants who possess superior social-cognitive abilities are more apt to reject an unreliable speaker as informant. A video abstract of this article can be viewed at: https://youtu.be/zuuCniHYzqo. © 2017 John Wiley & Sons Ltd.

Bayesian Tracking within a Feedback Sensing Environment: Estimating Interacting, Spatially Constrained Complex Dynamical Systems from Multiple Sources of Controllable Devices

DTIC Science & Technology

2014-07-25

composition of simple temporal structures to a speaker diarization task with the goal of segmenting conference audio in the presence of an unknown number of...application domains including neuroimaging, diverse document selection, speaker diarization , stock modeling, and target tracking. We detail each of...recall performance than competing methods in a task of discovering articles preferred by the user • a gold-standard speaker diarization method, as

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.

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

Paying attention to attention in recognition memory: insights from models and electrophysiology.

PubMed

Dubé, Chad; Payne, Lisa; Sekuler, Robert; Rotello, Caren M

2013-12-01

Reliance on remembered facts or events requires memory for their sources, that is, the contexts in which those facts or events were embedded. Understanding of source retrieval has been stymied by the fact that uncontrolled fluctuations of attention during encoding can cloud results of key importance to theoretical development. To address this issue, we combined electrophysiology (high-density electroencephalogram, EEG, recordings) with computational modeling of behavioral results. We manipulated subjects' attention to an auditory attribute, whether the source of individual study words was a male or female speaker. Posterior alpha-band (8-14 Hz) power in subjects' EEG increased after a cue to ignore the voice of the person who was about to speak. Receiver-operating-characteristic analysis validated our interpretation of oscillatory dynamics as a marker of attention to source information. With attention under experimental control, computational modeling showed unequivocally that memory for source (male or female speaker) reflected a continuous signal detection process rather than a threshold recollection process.

Professional Ethics for Astronomers

NASA Astrophysics Data System (ADS)

Marvel, K. B.

2005-05-01

There is a growing recognition that professional ethics is an important topic for all professional scientists, especially physical scientists. Situations at the National Laboratories have dramatically proven this point. Professional ethics is usually only considered important for the health sciences and the legal and medical professions. However, certain aspects of the day to day work of professional astronomers can be impacted by ethical issues. Examples include refereeing scientific papers, serving on grant panels or telescope allocation committees, submitting grant proposals, providing proper references in publications, proposals or talks and even writing recommendation letters for job candidates or serving on search committees. This session will feature several speakers on a variety of topics and provide time for questions and answers from the audience. Confirmed speakers include: Kate Kirby, Director Institute for Theoretical Atomic and Molecular Physics - Professional Ethics in the Physical Sciences: An Overview Rob Kennicutt, Astrophysical Journal Editor - Ethical Issues for Publishing Astronomers Peggy Fischer, Office of the NSF Inspector General - Professional Ethics from the NSF Inspector General's Point of View

The impact of iconic gestures on foreign language word learning and its neural substrate.

PubMed

Macedonia, Manuela; Müller, Karsten; Friederici, Angela D

2011-06-01

Vocabulary acquisition represents a major challenge in foreign language learning. Research has demonstrated that gestures accompanying speech have an impact on memory for verbal information in the speakers' mother tongue and, as recently shown, also in foreign language learning. However, the neural basis of this effect remains unclear. In a within-subjects design, we compared learning of novel words coupled with iconic and meaningless gestures. Iconic gestures helped learners to significantly better retain the verbal material over time. After the training, participants' brain activity was registered by means of fMRI while performing a word recognition task. Brain activations to words learned with iconic and with meaningless gestures were contrasted. We found activity in the premotor cortices for words encoded with iconic gestures. In contrast, words encoded with meaningless gestures elicited a network associated with cognitive control. These findings suggest that memory performance for newly learned words is not driven by the motor component as such, but by the motor image that matches an underlying representation of the word's semantics. Copyright © 2010 Wiley-Liss, Inc.

Using perturbed handwriting to support writer identification in the presence of severe data constraints

NASA Astrophysics Data System (ADS)

Chen, Jin; Cheng, Wen; Lopresti, Daniel

2011-01-01

Since real data is time-consuming and expensive to collect and label, researchers have proposed approaches using synthetic variations for the tasks of signature verification, speaker authentication, handwriting recognition, keyword spotting, etc. However, the limitation of real data is particularly critical in the field of writer identification in that in forensics, adversaries cannot be expected to provide sufficient data to train a classifier. Therefore, it is unrealistic to always assume sufficient real data to train classifiers extensively for writer identification. In addition, this field differs from many others in that we strive to preserve as much inter-writer variations, but model-perturbed handwriting might break such discriminability among writers. Building on work described in another paper where human subjects were involved in calibrating realistic-looking transformation, we then measured the effects of incorporating perturbed handwriting into the training dataset. Experimental results justified our hypothesis that with limited real data, model-perturbed handwriting improved the performance of writer identification. Particularly, if only one single sample for each writer was available, incorporating perturbed data achieved a 36x performance gain.

A neuroimaging study of conflict during word recognition.

PubMed

Riba, Jordi; Heldmann, Marcus; Carreiras, Manuel; Münte, Thomas F

2010-08-04

Using functional magnetic resonance imaging the neural activity associated with error commission and conflict monitoring in a lexical decision task was assessed. In a cohort of 20 native speakers of Spanish conflict was introduced by presenting words with high and low lexical frequency and pseudo-words with high and low syllabic frequency for the first syllable. Erroneous versus correct responses showed activation in the frontomedial and left inferior frontal cortex. A similar pattern was found for correctly classified words of low versus high lexical frequency and for correctly classified pseudo-words of high versus low syllabic frequency. Conflict-related activations for language materials largely overlapped with error-induced activations. The effect of syllabic frequency underscores the role of sublexical processing in visual word recognition and supports the view that the initial syllable mediates between the letter and word level.

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.

Inside-in, alternative paradigms for sound spatialization

NASA Astrophysics Data System (ADS)

Bahn, Curtis; Moore, Stephan

2003-04-01

Arrays of widely spaced mono-directional loudspeakers (P.A.-style stereo configurations or ``outside-in'' surround-sound systems) have long provided the dominant paradigms for electronic sound diffusion. So prevalent are these models that alternatives have largely been ignored and electronic sound, regardless of musical aesthetic, has come to be inseparably associated with single-channel speakers, or headphones. We recognize the value of these familiar paradigms, but believe that electronic sound can and should have many alternative, idiosyncratic voices. Through the design and construction of unique sound diffusion structures, one can reinvent the nature of electronic sound; when allied with new sensor technologies, these structures offer alternative modes of interaction with techniques of sonic computation. This paper describes several recent applications of spherical speakers (multichannel, outward-radiating geodesic speaker arrays) and Sensor-Speaker-Arrays (SenSAs: combinations of various sensor devices with outward-radiating multi-channel speaker arrays). This presentation introduces the development of four generations of spherical speakers-over a hundred individual speakers of various configurations-and their use in many different musical situations including live performance, recording, and sound installation. We describe the design and construction of these systems, and, more generally, the new ``voices'' they give to electronic sound.

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.

Toddlers learn words in a foreign language: The role of native vocabulary knowledge

PubMed Central

Koenig, Melissa A.; Woodward, Amanda L.

2013-01-01

The current study examined monolingual English-speaking toddlers’ (N=50) ability to learn word-referent links from native speakers of Dutch versus English and secondly, whether children generalized or sequestered their extensions when terms were tested by a subsequent speaker of English. Overall, children performed better in the English than in the Dutch condition; however, children with high native vocabularies successfully selected the target object for terms trained in fluent Dutch. Furthermore, children with higher vocabularies did not indicate their comprehension of Dutch terms when subsequently tested by an English speaker whereas children with low vocabulary scores responded at chance levels to both the original Dutch speaker and the second English speaker. These findings demonstrate that monolingual toddlers with proficiency in their native language are capable of learning words outside of their conventional system and may be sensitive to the boundaries that exist between language systems. PMID:22310327

Some factors underlying individual differences in speech recognition on PRESTO: a first report.

PubMed

Tamati, Terrin N; Gilbert, Jaimie L; Pisoni, David B

2013-01-01

Previous studies investigating speech recognition in adverse listening conditions have found extensive variability among individual listeners. However, little is currently known about the core underlying factors that influence speech recognition abilities. To investigate sensory, perceptual, and neurocognitive differences between good and poor listeners on the Perceptually Robust English Sentence Test Open-set (PRESTO), a new high-variability sentence recognition test under adverse listening conditions. Participants who fell in the upper quartile (HiPRESTO listeners) or lower quartile (LoPRESTO listeners) on key word recognition on sentences from PRESTO in multitalker babble completed a battery of behavioral tasks and self-report questionnaires designed to investigate real-world hearing difficulties, indexical processing skills, and neurocognitive abilities. Young, normal-hearing adults (N = 40) from the Indiana University community participated in the current study. Participants' assessment of their own real-world hearing difficulties was measured with a self-report questionnaire on situational hearing and hearing health history. Indexical processing skills were assessed using a talker discrimination task, a gender discrimination task, and a forced-choice regional dialect categorization task. Neurocognitive abilities were measured with the Auditory Digit Span Forward (verbal short-term memory) and Digit Span Backward (verbal working memory) tests, the Stroop Color and Word Test (attention/inhibition), the WordFam word familiarity test (vocabulary size), the Behavioral Rating Inventory of Executive Function-Adult Version (BRIEF-A) self-report questionnaire on executive function, and two performance subtests of the Wechsler Abbreviated Scale of Intelligence (WASI) Performance Intelligence Quotient (IQ; nonverbal intelligence). Scores on self-report questionnaires and behavioral tasks were tallied and analyzed by listener group (HiPRESTO and LoPRESTO). The extreme groups did not differ overall on self-reported hearing difficulties in real-world listening environments. However, an item-by-item analysis of questions revealed that LoPRESTO listeners reported significantly greater difficulty understanding speakers in a public place. HiPRESTO listeners were significantly more accurate than LoPRESTO listeners at gender discrimination and regional dialect categorization, but they did not differ on talker discrimination accuracy or response time, or gender discrimination response time. HiPRESTO listeners also had longer forward and backward digit spans, higher word familiarity ratings on the WordFam test, and lower (better) scores for three individual items on the BRIEF-A questionnaire related to cognitive load. The two groups did not differ on the Stroop Color and Word Test or either of the WASI performance IQ subtests. HiPRESTO listeners and LoPRESTO listeners differed in indexical processing abilities, short-term and working memory capacity, vocabulary size, and some domains of executive functioning. These findings suggest that individual differences in the ability to encode and maintain highly detailed episodic information in speech may underlie the variability observed in speech recognition performance in adverse listening conditions using high-variability PRESTO sentences in multitalker babble. American Academy of Audiology.

Some Factors Underlying Individual Differences in Speech Recognition on PRESTO: A First Report

PubMed Central

Tamati, Terrin N.; Gilbert, Jaimie L.; Pisoni, David B.

2013-01-01

Background Previous studies investigating speech recognition in adverse listening conditions have found extensive variability among individual listeners. However, little is currently known about the core, underlying factors that influence speech recognition abilities. Purpose To investigate sensory, perceptual, and neurocognitive differences between good and poor listeners on PRESTO, a new high-variability sentence recognition test under adverse listening conditions. Research Design Participants who fell in the upper quartile (HiPRESTO listeners) or lower quartile (LoPRESTO listeners) on key word recognition on sentences from PRESTO in multitalker babble completed a battery of behavioral tasks and self-report questionnaires designed to investigate real-world hearing difficulties, indexical processing skills, and neurocognitive abilities. Study Sample Young, normal-hearing adults (N = 40) from the Indiana University community participated in the current study. Data Collection and Analysis Participants’ assessment of their own real-world hearing difficulties was measured with a self-report questionnaire on situational hearing and hearing health history. Indexical processing skills were assessed using a talker discrimination task, a gender discrimination task, and a forced-choice regional dialect categorization task. Neurocognitive abilities were measured with the Auditory Digit Span Forward (verbal short-term memory) and Digit Span Backward (verbal working memory) tests, the Stroop Color and Word Test (attention/inhibition), the WordFam word familiarity test (vocabulary size), the BRIEF-A self-report questionnaire on executive function, and two performance subtests of the WASI Performance IQ (non-verbal intelligence). Scores on self-report questionnaires and behavioral tasks were tallied and analyzed by listener group (HiPRESTO and LoPRESTO). Results The extreme groups did not differ overall on self-reported hearing difficulties in real-world listening environments. However, an item-by-item analysis of questions revealed that LoPRESTO listeners reported significantly greater difficulty understanding speakers in a public place. HiPRESTO listeners were significantly more accurate than LoPRESTO listeners at gender discrimination and regional dialect categorization, but they did not differ on talker discrimination accuracy or response time, or gender discrimination response time. HiPRESTO listeners also had longer forward and backward digit spans, higher word familiarity ratings on the WordFam test, and lower (better) scores for three individual items on the BRIEF-A questionnaire related to cognitive load. The two groups did not differ on the Stroop Color and Word Test or either of the WASI performance IQ subtests. Conclusions HiPRESTO listeners and LoPRESTO listeners differed in indexical processing abilities, short-term and working memory capacity, vocabulary size, and some domains of executive functioning. These findings suggest that individual differences in the ability to encode and maintain highly detailed episodic information in speech may underlie the variability observed in speech recognition performance in adverse listening conditions using high-variability PRESTO sentences in multitalker babble. PMID:24047949

Charting the functional relevance of Broca's area for visual word recognition and picture naming in Dutch using fMRI-guided TMS.

PubMed

Wheat, Katherine L; Cornelissen, Piers L; Sack, Alexander T; Schuhmann, Teresa; Goebel, Rainer; Blomert, Leo

2013-05-01

Magnetoencephalography (MEG) has shown pseudohomophone priming effects at Broca's area (specifically pars opercularis of left inferior frontal gyrus and precentral gyrus; LIFGpo/PCG) within ∼100ms of viewing a word. This is consistent with Broca's area involvement in fast phonological access during visual word recognition. Here we used online transcranial magnetic stimulation (TMS) to investigate whether LIFGpo/PCG is necessary for (not just correlated with) visual word recognition by ∼100ms. Pulses were delivered to individually fMRI-defined LIFGpo/PCG in Dutch speakers 75-500ms after stimulus onset during reading and picture naming. Reading and picture naming reactions times were significantly slower following pulses at 225-300ms. Contrary to predictions, there was no disruption to reading for pulses before 225ms. This does not provide evidence in favour of a functional role for LIFGpo/PCG in reading before 225ms in this case, but does extend previous findings in picture stimuli to written Dutch words. Copyright © 2012 Elsevier Inc. All rights reserved.

Blinded by taboo words in L1 but not L2.

PubMed

Colbeck, Katie L; Bowers, Jeffrey S

2012-04-01

The present study compares the emotionality of English taboo words in native English speakers and native Chinese speakers who learned English as a second language. Neutral and taboo/sexual words were included in a Rapid Serial Visual Presentation (RSVP) task as to-be-ignored distracters in a short- and long-lag condition. Compared with neutral distracters, taboo/sexual distracters impaired the performance in the short-lag condition only. Of critical note, however, is that the performance of Chinese speakers was less impaired by taboo/sexual distracters. This supports the view that a first language is more emotional than a second language, even when words are processed quickly and automatically. (PsycINFO Database Record (c) 2012 APA, all rights reserved).

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…

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

Low-voltage Driven Graphene Foam Thermoacoustic Speaker.

PubMed

Fei, Wenwen; Zhou, Jianxin; Guo, Wanlin

2015-05-20

A low-voltage driven thermoacoustic speaker is fabricated based on three-dimensional graphene foams synthesized by a nickel-template assisted chemical vapor deposition method. The corresponding thermoacoustic performances are found to be related to its microstructure. Graphene foams exhibit low heat-leakage to substrates and feasible tunability in structures and thermoacoustic performances, having great promise for applications in flexible or ultrasonic acoustic devices. © 2014 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

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.

Predicting Receptive-Expressive Vocabulary Discrepancies in Preschool Children With Autism Spectrum Disorder.

PubMed

McDaniel, Jena; Yoder, Paul; Woynaroski, Tiffany; Watson, Linda R

2018-05-15

Correlates of receptive-expressive vocabulary size discrepancies may provide insights into why language development in children with autism spectrum disorder (ASD) deviates from typical language development and ultimately improve intervention outcomes. We indexed receptive-expressive vocabulary size discrepancies of 65 initially preverbal children with ASD (20-48 months) to a comparison sample from the MacArthur-Bates Communicative Development Inventories Wordbank (Frank, Braginsky, Yurovsky, & Marchman, 2017) to quantify typicality. We then tested whether attention toward a speaker and oral motor performance predict typicality of the discrepancy 8 months later. Attention toward a speaker correlated positively with receptive-expressive vocabulary size discrepancy typicality. Imitative and nonimitative oral motor performance were not significant predictors of vocabulary size discrepancy typicality. Secondary analyses indicated that midpoint receptive vocabulary size mediated the association between initial attention toward a speaker and end point receptive-expressive vocabulary size discrepancy typicality. Findings support the hypothesis that variation in attention toward a speaker might partially explain receptive-expressive vocabulary size discrepancy magnitude in children with ASD. Results are consistent with an input-processing deficit explanation of language impairment in this clinical population. Future studies should test whether attention toward a speaker is malleable and causally related to receptive-expressive discrepancies in children with ASD.

Does a Speaking Task Affect Second Language Comprehensibility?

ERIC Educational Resources Information Center

Crowther, Dustin; Trofimovich, Pavel; Isaacs, Talia; Saito, Kazuya

2015-01-01

The current study investigated task effects on listener perception of second language (L2) comprehensibility (ease of understanding). Sixty university-level adult speakers of English from 4 first language (L1) backgrounds (Chinese, Romance, Hindi, Farsi), with 15 speakers per group, were recorded performing 2 tasks (IELTS long-turn speaking task…

A pilot study to assess oral health literacy by comparing a word recognition and comprehension tool.

PubMed

Khan, Khadija; Ruby, Brendan; Goldblatt, Ruth S; Schensul, Jean J; Reisine, Susan

2014-11-18

Oral health literacy is important to oral health outcomes. Very little has been established on comparing word recognition to comprehension in oral health literacy especially in older adults. Our goal was to compare methods to measure oral health literacy in older adults by using the Rapid Estimate of Literacy in Dentistry (REALD-30) tool including word recognition and comprehension and by assessing comprehension of a brochure about dry mouth. 75 males and 75 females were recruited from the University of Connecticut Dental practice. Participants were English speakers and at least 50 years of age. They were asked to read the REALD-30 words out loud (word recognition) and then define them (comprehension). Each correctly-pronounced and defined word was scored 1 for total REALD-30 word recognition and REALD-30 comprehension scores of 0-30. Participants then read the National Institute of Dental and Craniofacial Research brochure "Dry Mouth" and answered three questions defining dry mouth, causes and treatment. Participants also completed a survey on dental behavior. Participants scored higher on REALD-30 word recognition with a mean of 22.98 (SD = 5.1) compared to REALD-30 comprehension with a mean of 16.1 (SD = 4.3). The mean score on the brochure comprehension was 5.1 of a possible total of 7 (SD = 1.6). Pearson correlations demonstrated significant associations among the three measures. Multivariate regression showed that females and those with higher education had significantly higher scores on REALD-30 word-recognition, and dry mouth brochure questions. Being white was significantly related to higher REALD-30 recognition and comprehension scores but not to the scores on the brochure. This pilot study demonstrates the feasibility of using the REALD-30 and a brochure to assess literacy in a University setting among older adults. Participants had higher scores on the word recognition than on comprehension agreeing with other studies that recognition does not imply understanding.

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.

Feature Selection for Speech Emotion Recognition in Spanish and Basque: On the Use of Machine Learning to Improve Human-Computer Interaction

PubMed Central

Arruti, Andoni; Cearreta, Idoia; Álvarez, Aitor; Lazkano, Elena; Sierra, Basilio

2014-01-01

Study of emotions in human–computer interaction is a growing research area. This paper shows an attempt to select the most significant features for emotion recognition in spoken Basque and Spanish Languages using different methods for feature selection. RekEmozio database was used as the experimental data set. Several Machine Learning paradigms were used for the emotion classification task. Experiments were executed in three phases, using different sets of features as classification variables in each phase. Moreover, feature subset selection was applied at each phase in order to seek for the most relevant feature subset. The three phases approach was selected to check the validity of the proposed approach. Achieved results show that an instance-based learning algorithm using feature subset selection techniques based on evolutionary algorithms is the best Machine Learning paradigm in automatic emotion recognition, with all different feature sets, obtaining a mean of 80,05% emotion recognition rate in Basque and a 74,82% in Spanish. In order to check the goodness of the proposed process, a greedy searching approach (FSS-Forward) has been applied and a comparison between them is provided. Based on achieved results, a set of most relevant non-speaker dependent features is proposed for both languages and new perspectives are suggested. PMID:25279686

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.

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.

Phonetic complexity and stuttering in Spanish

PubMed Central

Howell, Peter; Au-Yeung, James

2007-01-01

The current study investigated whether phonetic complexity affected stuttering rate for Spanish speakers. The speakers were assigned to three age groups (6-11, 12-17 and 18 years plus) that were similar to those used in an earlier study on English. The analysis was performed using Jakielski's (1998) Index of Phonetic Complexity (IPC) scheme in which each word is given an IPC score based on the number of complex attributes it includes for each of eight factors. Stuttering on function words for Spanish did not correlate with IPC score for any age group. This mirrors the finding for English that stuttering on these words is not affected by phonetic complexity. The IPC scores of content words correlated positively with stuttering rate for 6-11 year old and adult speakers. Comparison was made between the languages to establish whether or not experience with the factors determines the problem they pose for speakers (revealed by differences in stuttering rate). Evidence was obtained that four factors found to be important determinants of stuttering on content words in English for speakers aged 12 and above, also affected Spanish speakers. This occurred despite large differences in frequency of usage of these factors. It is concluded that phonetic factors affect stuttering rate irrespective of a speaker's experience with that factor. PMID:17364620

Phonetic complexity and stuttering in Spanish.

PubMed

Howell, Peter; Au-Yeung, James

2007-02-01

The current study investigated whether phonetic complexity affected stuttering rate for Spanish speakers. The speakers were assigned to three age groups (6-11, 12-17 and 18-years plus) that were similar to those used in an earlier study on English. The analysis was performed using Jakielski's Index of Phonetic Complexity (IPC) scheme in which each word is given an IPC score based on the number of complex attributes it includes for each of eight factors. Stuttering on function words for Spanish did not correlate with IPC score for any age group. This mirrors the finding for English that stuttering on these words is not affected by phonetic complexity. The IPC scores of content words correlated positively with stuttering rate for 6-11-year-old and adult speakers. Comparison was made between the languages to establish whether or not experience with the factors determines the problem they pose for speakers (revealed by differences in stuttering rate). Evidence was obtained that four factors found to be important determinants of stuttering on content words in English for speakers aged 12 and above, also affected Spanish speakers. This occurred despite large differences in frequency of usage of these factors. It is concluded that phonetic factors affect stuttering rate irrespective of a speaker's experience with that factor.

Lip-reading aids word recognition most in moderate noise: a Bayesian explanation using high-dimensional feature space.

PubMed

Ma, Wei Ji; Zhou, Xiang; Ross, Lars A; Foxe, John J; Parra, Lucas C

2009-01-01

Watching a speaker's facial movements can dramatically enhance our ability to comprehend words, especially in noisy environments. From a general doctrine of combining information from different sensory modalities (the principle of inverse effectiveness), one would expect that the visual signals would be most effective at the highest levels of auditory noise. In contrast, we find, in accord with a recent paper, that visual information improves performance more at intermediate levels of auditory noise than at the highest levels, and we show that a novel visual stimulus containing only temporal information does the same. We present a Bayesian model of optimal cue integration that can explain these conflicts. In this model, words are regarded as points in a multidimensional space and word recognition is a probabilistic inference process. When the dimensionality of the feature space is low, the Bayesian model predicts inverse effectiveness; when the dimensionality is high, the enhancement is maximal at intermediate auditory noise levels. When the auditory and visual stimuli differ slightly in high noise, the model makes a counterintuitive prediction: as sound quality increases, the proportion of reported words corresponding to the visual stimulus should first increase and then decrease. We confirm this prediction in a behavioral experiment. We conclude that auditory-visual speech perception obeys the same notion of optimality previously observed only for simple multisensory stimuli.

What's in a voice? Prosody as a test case for the Theory of Mind account of autism.

PubMed

Chevallier, Coralie; Noveck, Ira; Happé, Francesca; Wilson, Deirdre

2011-02-01

The human voice conveys a variety of information about people's feelings, emotions and mental states. Some of this information relies on sophisticated Theory of Mind (ToM) skills, whilst others are simpler and do not require ToM. This variety provides an interesting test case for the ToM account of autism, which would predict greater impairment as ToM requirements increase. In this paper, we draw on psychological and pragmatic theories to classify vocal cues according to the amount of mindreading required to identify them. Children with a high functioning Autism Spectrum Disorder and matched controls were tested in three experiments where the speakers' state had to be extracted from their vocalizations. Although our results confirm that people with autism have subtle difficulties dealing with vocal cues, they show a pattern of performance that is inconsistent with the view that atypical recognition of vocal cues is caused by impaired ToM. Copyright © 2010 Elsevier Ltd. All rights reserved.

Newly learned word forms are abstract and integrated immediately after acquisition

PubMed Central

Kapnoula, Efthymia C.; McMurray, Bob

2015-01-01

A hotly debated question in word learning concerns the conditions under which newly learned words compete or interfere with familiar words during spoken word recognition. This has recently been described as a key marker of the integration of a new word into the lexicon and was thought to require consolidation Dumay & Gaskell, (Psychological Science, 18, 35–39, 2007; Gaskell & Dumay, Cognition, 89, 105–132, 2003). Recently, however, Kapnoula, Packard, Gupta, and McMurray, (Cognition, 134, 85–99, 2015) showed that interference can be observed immediately after a word is first learned, implying very rapid integration of new words into the lexicon. It is an open question whether these kinds of effects derive from episodic traces of novel words or from more abstract and lexicalized representations. Here we addressed this question by testing inhibition for newly learned words using training and test stimuli presented in different talker voices. During training, participants were exposed to a set of nonwords spoken by a female speaker. Immediately after training, we assessed the ability of the novel word forms to inhibit familiar words, using a variant of the visual world paradigm. Crucially, the test items were produced by a male speaker. An analysis of fixations showed that even with a change in voice, newly learned words interfered with the recognition of similar known words. These findings show that lexical competition effects from newly learned words spread across different talker voices, which suggests that newly learned words can be sufficiently lexicalized, and abstract with respect to talker voice, without consolidation. PMID:26202702

Tone Language Speakers and Musicians Share Enhanced Perceptual and Cognitive Abilities for Musical Pitch: Evidence for Bidirectionality between the Domains of Language and Music

PubMed Central

Bidelman, Gavin M.; Hutka, Stefanie; Moreno, Sylvain

2013-01-01

Psychophysiological evidence suggests that music and language are intimately coupled such that experience/training in one domain can influence processing required in the other domain. While the influence of music on language processing is now well-documented, evidence of language-to-music effects have yet to be firmly established. Here, using a cross-sectional design, we compared the performance of musicians to that of tone-language (Cantonese) speakers on tasks of auditory pitch acuity, music perception, and general cognitive ability (e.g., fluid intelligence, working memory). While musicians demonstrated superior performance on all auditory measures, comparable perceptual enhancements were observed for Cantonese participants, relative to English-speaking nonmusicians. These results provide evidence that tone-language background is associated with higher auditory perceptual performance for music listening. Musicians and Cantonese speakers also showed superior working memory capacity relative to nonmusician controls, suggesting that in addition to basic perceptual enhancements, tone-language background and music training might also be associated with enhanced general cognitive abilities. Our findings support the notion that tone language speakers and musically trained individuals have higher performance than English-speaking listeners for the perceptual-cognitive processing necessary for basic auditory as well as complex music perception. These results illustrate bidirectional influences between the domains of music and language. PMID:23565267

Using Telephone Conversations to Develop Awareness of Pragmatic Skills: An Activity-Theory-Driven Approach

ERIC Educational Resources Information Center

Xia, Saihua

2009-01-01

This paper investigates ESL learners' awareness of pragmatic skills utilizing an activity-theory driven approach to perform an inquiry task into problem-solving service call conversations (PSSCs) between native speakers (NS) and non-native speakers of English (NNSs). Eight high-intermediate ESL learners, from five different language backgrounds,…

Nonoccurrence of Negotiation of Meaning in Task-Based Synchronous Computer-Mediated Communication

ERIC Educational Resources Information Center

Van Der Zwaard, Rose; Bannink, Anne

2016-01-01

This empirical study investigated the occurrence of meaning negotiation in an interactive synchronous computer-mediated second language (L2) environment. Sixteen dyads (N = 32) consisting of nonnative speakers (NNSs) and native speakers (NSs) of English performed 2 different tasks using videoconferencing and written chat. The data were coded and…

Acoustic Cues to Perception of Word Stress by English, Mandarin, and Russian Speakers

ERIC Educational Resources Information Center

Chrabaszcz, Anna; Winn, Matthew; Lin, Candise Y.; Idsardi, William J.

2014-01-01

Purpose: This study investigated how listeners' native language affects their weighting of acoustic cues (such as vowel quality, pitch, duration, and intensity) in the perception of contrastive word stress. Method: Native speakers (N = 45) of typologically diverse languages (English, Russian, and Mandarin) performed a stress identification…

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)

Insight into the Structure of Compound Words among Speakers of Chinese and English

ERIC Educational Resources Information Center

Zhang, Jie; Anderson, Richard C.; Wang, Qiuying; Packard, Jerome; Wu, Xinchun; Tang, Shan; Ke, Xiaoling

2012-01-01

Knowledge of compound word structures in Chinese and English was investigated, comparing 435 Chinese and 258 Americans, including second, fourth, and sixth graders, and college undergraduates. As anticipated, the results revealed that Chinese speakers performed better on a word structure analogy task than their English-speaking counterparts. Also,…

What makes a voice masculine: physiological and acoustical correlates of women's ratings of men's vocal masculinity.

PubMed

Cartei, Valentina; Bond, Rod; Reby, David

2014-09-01

Men's voices contain acoustic cues to body size and hormonal status, which have been found to affect women's ratings of speaker size, masculinity and attractiveness. However, the extent to which these voice parameters mediate the relationship between speakers' fitness-related features and listener's judgments of their masculinity has not yet been investigated. We audio-recorded 37 adult heterosexual males performing a range of speech tasks and asked 20 adult heterosexual female listeners to rate speakers' masculinity on the basis of their voices only. We then used a two-level (speaker within listener) path analysis to examine the relationships between the physiological (testosterone, height), acoustic (fundamental frequency or F0, and resonances or ΔF) and perceptual dimensions (listeners' ratings) of speakers' masculinity. Overall, results revealed that male speakers who were taller and had higher salivary testosterone levels also had lower F0 and ΔF, and were in turn rated as more masculine. The relationship between testosterone and perceived masculinity was essentially mediated by F0, while that of height and perceived masculinity was partially mediated by both F0 and ΔF. These observations confirm that women listeners attend to sexually dimorphic voice cues to assess the masculinity of unseen male speakers. In turn, variation in these voice features correlate with speakers' variation in stature and hormonal status, highlighting the interdependence of these physiological, acoustic and perceptual dimensions. Copyright © 2014. Published by Elsevier Inc.

Use of the BAT with a Cantonese-Putonghua speaker with aphasia.

PubMed

Kong, Anthony Pak-Hin; Weekes, Brendan Stuart

2011-06-01

The aim of this article is to illustrate the use of the Bilingual Aphasia Test (BAT) with a Cantonese-Putonghua speaker. We describe G, who is a relatively young Chinese bilingual speaker with aphasia. G's communication abilities in his L2, Putonghua, were impaired following brain damage. This impairment caused specific difficulties in communication with his wife, a native Putonghua speaker, and was thus a priority for investigation. Given a paucity of standardised tests of aphasia in Putonghua, our goal was to use the BAT to assess G's impairments in his L2. Results showed that G's performance on the BAT subtests measuring word and sentence comprehension and production was impaired. His pattern of performance on the BAT allowed us to generate hypotheses about his higher-level language impairments in Putonghua, which were subsequently found to be impaired. We argue that the BAT is able to capture the primary language impairments in Chinese-speaking patients with aphasia when Putonghua is the second language. We also suggest some modifications to the BAT for testing Chinese-speaking patients with bilingual aphasia.

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.

The effects of ethnicity, musicianship, and tone language experience on pitch perception.

PubMed

Zheng, Yi; Samuel, Arthur G

2018-02-01

Language and music are intertwined: music training can facilitate language abilities, and language experiences can also help with some music tasks. Possible language-music transfer effects are explored in two experiments in this study. In Experiment 1, we tested native Mandarin, Korean, and English speakers on a pitch discrimination task with two types of sounds: speech sounds and fundamental frequency (F0) patterns derived from speech sounds. To control for factors that might influence participants' performance, we included cognitive ability tasks testing memory and intelligence. In addition, two music skill tasks were used to examine general transfer effects from language to music. Prior studies showing that tone language speakers have an advantage on pitch tasks have been taken as support for three alternative hypotheses: specific transfer effects, general transfer effects, and an ethnicity effect. In Experiment 1, musicians outperformed non-musicians on both speech and F0 sounds, suggesting a music-to-language transfer effect. Korean and Mandarin speakers performed similarly, and they both outperformed English speakers, providing some evidence for an ethnicity effect. Alternatively, this could be due to population selection bias. In Experiment 2, we recruited Chinese Americans approximating the native English speakers' language background to further test the ethnicity effect. Chinese Americans, regardless of their tone language experiences, performed similarly to their non-Asian American counterparts in all tasks. Therefore, although this study provides additional evidence of transfer effects across music and language, it casts doubt on the contribution of ethnicity to differences observed in pitch perception and general music abilities.

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.

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.

Evaluation of a speaker identification system with and without fusion using three databases in the presence of noise and handset effects

NASA Astrophysics Data System (ADS)

S. Al-Kaltakchi, Musab T.; Woo, Wai L.; Dlay, Satnam; Chambers, Jonathon A.

2017-12-01

In this study, a speaker identification system is considered consisting of a feature extraction stage which utilizes both power normalized cepstral coefficients (PNCCs) and Mel frequency cepstral coefficients (MFCC). Normalization is applied by employing cepstral mean and variance normalization (CMVN) and feature warping (FW), together with acoustic modeling using a Gaussian mixture model-universal background model (GMM-UBM). The main contributions are comprehensive evaluations of the effect of both additive white Gaussian noise (AWGN) and non-stationary noise (NSN) (with and without a G.712 type handset) upon identification performance. In particular, three NSN types with varying signal to noise ratios (SNRs) were tested corresponding to street traffic, a bus interior, and a crowded talking environment. The performance evaluation also considered the effect of late fusion techniques based on score fusion, namely, mean, maximum, and linear weighted sum fusion. The databases employed were TIMIT, SITW, and NIST 2008; and 120 speakers were selected from each database to yield 3600 speech utterances. As recommendations from the study, mean fusion is found to yield overall best performance in terms of speaker identification accuracy (SIA) with noisy speech, whereas linear weighted sum fusion is overall best for original database recordings.

Word and Pseudoword Superiority Effects: Evidence From a Shallow Orthography Language.

PubMed

Ripamonti, Enrico; Luzzatti, Claudio; Zoccolotti, Pierluigi; Traficante, Daniela

2017-08-03

The Word Superiority Effect (WSE) denotes better recognition of a letter embedded in a word rather than in a pseudoword. Along with WSE, also a Pseudoword Superiority Effect (PSE) has been described: it is easier to recognize a letter in a legal pseudoword than in an unpronounceable nonword. At the current state of the art, both WSE and PSE have been mainly tested with English speakers. The present study uses the Reicher-Wheeler paradigm with native speakers of Italian (a shallow orthography language). Differently from English and French, we found WSE for RTs only, whereas PSE was significant for both accuracy and reaction times (RTs). This finding indicates that, in the Reicher-Wheeler task, readers of a shallow orthography language can effectively rely on both the lexical and the sublexical routes. As to the effect of letter position, a clear advantage for the first letter position emerged, a finding suggesting a fine-grained processing of the letter strings with coding of letter position, and indicating the role of visual acuity and crowding factors.

What is French for déjà vu? Descriptions of déjà vu in native French and English speakers.

PubMed

Fortier, Jonathan; Moulin, Chris J A

2015-11-01

Little is known about how people characterise and classify the experience of déjà vu. The term déjà vu might capture a range of different phenomena and people may use it differently. We examined the description of déjà vu in two languages: French and English, hypothesising that the use of déjà vu would vary between the two languages. In French, the phrase déjà vu can be used to indicate a veridical experience of recognition - as in "I have already seen this face before". However, the same is not true in English. In an online questionnaire, we found equal rates of déjà vu amongst French and English speakers, and key differences in how the experience was described. As expected, the French group described the experience as being more frequent, but there was the unexpected finding that they found it to be more troubling. Copyright © 2015 Elsevier Inc. All rights reserved.

Masked priming effects are modulated by expertise in the script.

PubMed

Perea, Manuel; Abu Mallouh, Reem; Garcı A-Orza, Javier; Carreiras, Manuel

2011-05-01

In a recent study using a masked priming same-different matching task, Garcı´a-Orza, Perea, and Munoz (2010) found a transposition priming effect for letter strings, digit strings, and symbol strings, but not for strings of pseudoletters (i.e., EPRI-ERPI produced similar response times to the control pair EDBI-ERPI). They argued that the mechanism responsible for position coding in masked priming is not operative with those "objects" whose identity cannot be attained rapidly. To assess this hypothesis, Experiment 1 examined masked priming effects in Arabic for native speakers of Arabic, whereas participants in Experiments 2 and 3 were lower intermediate learners of Arabic and readers with no knowledge of Arabic, respectively. Results showed a masked priming effect only for readers who are familiar with the Arabic script. Furthermore, transposed-letter priming in native speakers of Arabic only occurred when the order of the root letters was kept intact. In Experiments 3-7, we examined why masked repetition priming is absent for readers who are unfamiliar with the Arabic script. We discuss the implications of these findings for models of visual-word recognition.

A fundamental residue pitch perception bias for tone language speakers

NASA Astrophysics Data System (ADS)

Petitti, Elizabeth

A complex tone composed of only higher-order harmonics typically elicits a pitch percept equivalent to the tone's missing fundamental frequency (f0). When judging the direction of residue pitch change between two such tones, however, listeners may have completely opposite perceptual experiences depending on whether they are biased to perceive changes based on the overall spectrum or the missing f0 (harmonic spacing). Individual differences in residue pitch change judgments are reliable and have been associated with musical experience and functional neuroanatomy. Tone languages put greater pitch processing demands on their speakers than non-tone languages, and we investigated whether these lifelong differences in linguistic pitch processing affect listeners' bias for residue pitch. We asked native tone language speakers and native English speakers to perform a pitch judgment task for two tones with missing fundamental frequencies. Given tone pairs with ambiguous pitch changes, listeners were asked to judge the direction of pitch change, where the direction of their response indicated whether they attended to the overall spectrum (exhibiting a spectral bias) or the missing f0 (exhibiting a fundamental bias). We found that tone language speakers are significantly more likely to perceive pitch changes based on the missing f0 than English speakers. These results suggest that tone-language speakers' privileged experience with linguistic pitch fundamentally tunes their basic auditory processing.

KSC-04pd0489

NASA Image and Video Library

2004-03-12

KENNEDY SPACE CENTER, FLA. - Florida Gov. Jeb Bush (left) and Center Director Jim Kennedy attend the luncheon at the 2004 Florida Regional FIRST competition held at the University of Central Florida. Both are featured speakers. The event hosted 41 teams from Canada, Brazil, Great Britain and the United States. FIRST is a nonprofit organization, For Inspiration and Recognition of Science and Technology, that sponsors the event pitting gladiator robots against each other in an athletic-style competition. The FIRST robotics competition is designed to provide students with a hands-on, inside look at engineering and other professional careers, pairing high school students with engineer mentors and corporations.

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…

Fixed-Choice Word-Association Tasks as Second-Language Lexical Tests: What Native-Speaker Performance Reveals about Their Potential Weaknesses

ERIC Educational Resources Information Center

Dronjic, Vedran; Helms-Park, Rena

2014-01-01

Qian and Schedl's Depth of Vocabulary Knowledge Test was administered to 31 native-speaker undergraduates under an "unconstrained" condition, in which the number of responses to headwords was unfixed, whereas a corresponding group ("n" = 36) completed the test under the original "constrained" condition. Results…

Toddlers Learn Words in a Foreign Language: The Role of Native Vocabulary Knowledge

ERIC Educational Resources Information Center

Koening, Melissa; Woodward, Amanda

2012-01-01

The current study examined monolingual English-speaking toddlers' (N=50) ability to learn word-referent links from native speakers of Dutch versus English, and second, whether children generalized or sequestered their extensions when terms were tested by a subsequent speaker of English. Overall, children performed better in the English than in the…

How Well Do U.S. High School Students Achieve in Spanish When Compared to Native Spanish Speakers?

ERIC Educational Resources Information Center

Sparks, Richard L.; Luebbers, Julie; Castañeda, Martha E.

2017-01-01

Foreign language educators have developed measures to assess the proficiency of U.S. high school learners. Most have compared language learners to clearly defined criteria for proficiency in the language (criterion-referenced assessment) or to the performance of other monolingual English speakers (norm-referenced assessment). In this study, the…

Early-Stage Chunking of Finger Tapping Sequences by Persons Who Stutter and Fluent Speakers

ERIC Educational Resources Information Center

Smits-Bandstra, Sarah; De Nil, Luc F.

2013-01-01

This research note explored the hypothesis that chunking differences underlie the slow finger-tap sequencing performance reported in the literature for persons who stutter (PWS) relative to fluent speakers (PNS). Early-stage chunking was defined as an immediate and spontaneous tendency to organize a long sequence into pauses, for motor planning,…

Designing, Modeling, Constructing, and Testing a Flat Panel Speaker and Sound Diffuser for a Simulator

NASA Technical Reports Server (NTRS)

Dillon, Christina

2013-01-01

The goal of this project was to design, model, build, and test a flat panel speaker and frame for a spherical dome structure being made into a simulator. The simulator will be a test bed for evaluating an immersive environment for human interfaces. This project focused on the loud speakers and a sound diffuser for the dome. The rest of the team worked on an Ambisonics 3D sound system, video projection system, and multi-direction treadmill to create the most realistic scene possible. The main programs utilized in this project, were Pro-E and COMSOL. Pro-E was used for creating detailed figures for the fabrication of a frame that held a flat panel loud speaker. The loud speaker was made from a thin sheet of Plexiglas and 4 acoustic exciters. COMSOL, a multiphysics finite analysis simulator, was used to model and evaluate all stages of the loud speaker, frame, and sound diffuser. Acoustical testing measurements were utilized to create polar plots from the working prototype which were then compared to the COMSOL simulations to select the optimal design for the dome. The final goal of the project was to install the flat panel loud speaker design in addition to a sound diffuser on to the wall of the dome. After running tests in COMSOL on various speaker configurations, including a warped Plexiglas version, the optimal speaker design included a flat piece of Plexiglas with a rounded frame to match the curvature of the dome. Eight of these loud speakers will be mounted into an inch and a half of high performance acoustic insulation, or Thinsulate, that will cover the inside of the dome. The following technical paper discusses these projects and explains the engineering processes used, knowledge gained, and the projected future goals of this project

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.

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

Oral-diadochokinesis rates across languages: English and Hebrew norms.

PubMed

Icht, Michal; Ben-David, Boaz M

2014-01-01

Oro-facial and speech motor control disorders represent a variety of speech and language pathologies. Early identification of such problems is important and carries clinical implications. A common and simple tool for gauging the presence and severity of speech motor control impairments is oral-diadochokinesis (oral-DDK). Surprisingly, norms for adult performance are missing from the literature. The goals of this study were: (1) to establish a norm for oral-DDK rate for (young to middle-age) adult English speakers, by collecting data from the literature (five studies, N=141); (2) to investigate the possible effect of language (and culture) on oral-DDK performance, by analyzing studies conducted in other languages (five studies, N=140), alongside the English norm; and (3) to find a new norm for adult Hebrew speakers, by testing 115 speakers. We first offer an English norm with a mean of 6.2syllables/s (SD=.8), and a lower boundary of 5.4syllables/s that can be used to indicate possible abnormality. Next, we found significant differences between four tested languages (English, Portuguese, Farsi and Greek) in oral-DDK rates. Results suggest the need to set language and culture sensitive norms for the application of the oral-DDK task world-wide. Finally, we found the oral-DDK performance for adult Hebrew speakers to be 6.4syllables/s (SD=.8), not significantly different than the English norms. This implies possible phonological similarities between English and Hebrew. We further note that no gender effects were found in our study. We recommend using oral-DDK as an important tool in the speech language pathologist's arsenal. Yet, application of this task should be done carefully, comparing individual performance to a set norm within the specific language. Readers will be able to: (1) identify the Speech-Language Pathologist assessment process using the oral-DDK task, by comparing an individual performance to the present English norm, (2) describe the impact of language on oral-DDK performance, and (3) accurately detect Hebrew speakers' patients using this tool. Copyright © 2014 Elsevier Inc. All rights reserved.

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).

The role of lexical variables in the visual recognition of Chinese characters: A megastudy analysis.

PubMed

Sze, Wei Ping; Yap, Melvin J; Rickard Liow, Susan J

2015-01-01

Logographic Chinese orthography partially represents both phonology and semantics. By capturing the online processing of a large pool of Chinese characters, we were able to examine the relative salience of specific lexical variables when this nonalphabetic script is read. Using a sample of native mainland Chinese speakers (N = 35), lexical decision latencies for 1560 single characters were collated into a database, before the effects of a comprehensive range of variables were explored. Hierarchical regression analyses determined the unique item-level variance explained by orthographic (frequency, stroke count), semantic (age of learning, imageability, number of meanings), and phonological (consistency, phonological frequency) factors. Orthographic and semantic variables, respectively, accounted for more collective variance than the phonological variables. Significant main effects were further observed for the individual orthographic and semantic predictors. These results are consistent with the idea that skilled readers tend to rely on orthographic and semantic information when processing visually presented characters. This megastudy approach marks an important extension to existing work on Chinese character recognition, which hitherto has relied on factorial designs. Collectively, the findings reported here represent a useful set of empirical constraints for future computational models of character recognition.

The cognitive neuroscience of person identification.

PubMed

Biederman, Irving; Shilowich, Bryan E; Herald, Sarah B; Margalit, Eshed; Maarek, Rafael; Meschke, Emily X; Hacker, Catrina M

2018-02-14

We compare and contrast five differences between person identification by voice and face. 1. There is little or no cost when a familiar face is to be recognized from an unrestricted set of possible faces, even at Rapid Serial Visual Presentation (RSVP) rates, but the accuracy of familiar voice recognition declines precipitously when the set of possible speakers is increased from one to a mere handful. 2. Whereas deficits in face recognition are typically perceptual in origin, those with normal perception of voices can manifest severe deficits in their identification. 3. Congenital prosopagnosics (CPros) and congenital phonagnosics (CPhon) are generally unable to imagine familiar faces and voices, respectively. Only in CPros, however, is this deficit a manifestation of a general inability to form visual images of any kind. CPhons report no deficit in imaging non-voice sounds. 4. The prevalence of CPhons of 3.2% is somewhat higher than the reported prevalence of approximately 2.0% for CPros in the population. There is evidence that CPhon represents a distinct condition statistically and not just normal variation. 5. Face and voice recognition proficiency are uncorrelated rather than reflecting limitations of a general capacity for person individuation. Copyright © 2018 Elsevier Ltd. All rights reserved.

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.

Characterizing opto-electret based paper speakers by using a real-time projection Moiré metrology system

NASA Astrophysics Data System (ADS)

Chang, Ya-Ling; Hsu, Kuan-Yu; Lee, Chih-Kung

2016-03-01

Advancement of distributed piezo-electret sensors and actuators facilitates various smart systems development, which include paper speakers, opto-piezo/electret bio-chips, etc. The array-based loudspeaker system possess several advantages over conventional coil speakers, such as light-weightness, flexibility, low power consumption, directivity, etc. With the understanding that the performance of the large-area piezo-electret loudspeakers or even the microfluidic biochip transport behavior could be tailored by changing their dynamic behaviors, a full-field real-time high-resolution non-contact metrology system was developed. In this paper, influence of the resonance modes and the transient vibrations of an arraybased loudspeaker system on the acoustic effect were measured by using a real-time projection moiré metrology system and microphones. To make the paper speaker even more versatile, we combine the photosensitive material TiOPc into the original electret loudspeaker. The vibration of this newly developed opto-electret loudspeaker could be manipulated by illuminating different light-intensity patterns. Trying to facilitate the tailoring process of the opto-electret loudspeaker, projection moiré was adopted to measure its vibration. By recording the projected fringes which are modulated by the contours of the testing sample, the phase unwrapping algorithm can give us a continuous phase distribution which is proportional to the object height variations. With the aid of the projection moiré metrology system, the vibrations associated with each distinctive light pattern could be characterized. Therefore, we expect that the overall acoustic performance could be improved by finding the suitable illuminating patterns. In this manuscript, the system performance of the projection moiré and the optoelectret paper speakers were cross-examined and verified by the experimental results obtained.

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.

Young Children Use Shared Experience to Interpret Definite Reference

ERIC Educational Resources Information Center

Schmerse, Daniel; Lieven, Elena; Tomasello, Michael

2015-01-01

We investigated whether children at the ages of two and three years understand that a speaker's use of the definite article specifies a referent that is in common ground between speaker and listener. An experimenter and a child engaged in joint actions in which the experimenter chose one of three similar objects of the same category to perform an…

Item-Level Psychometrics and Predictors of Performance for Spanish/English Bilingual Speakers on "An Object and Action Naming Battery"

ERIC Educational Resources Information Center

Edmonds, Lisa A.; Donovan, Neila J.

2012-01-01

Purpose: There is a pressing need for psychometrically sound naming materials for Spanish/English bilingual adults. To address this need, in this study the authors examined the psychometric properties of An Object and Action Naming Battery (An O&A Battery; Druks & Masterson, 2000) in bilingual speakers. Method: Ninety-one Spanish/English…

The Wor(l)d is a Collage: Multi-Performance by Chinese Heritage Language Speakers

ERIC Educational Resources Information Center

He, Agnes Weiyun

2013-01-01

This study examines the simultaneous use of English and Chinese by speakers of Chinese as a heritage language (CHL). It focuses on spontaneous, dynamic, and high-density mixing of the two languages within the smallest building block of a speaking turn: the turn constructional unit (TCU). Drawing upon data from different age and proficiency groups,…

Does the speaker's voice quality influence children's performance on a language comprehension test?

PubMed

Lyberg-Åhlander, Viveka; Haake, Magnus; Brännström, Jonas; Schötz, Susanne; Sahlén, Birgitta

2015-02-01

A small number of studies have explored children's perception of speakers' voice quality and its possible influence on language comprehension. The aim of this explorative study was to investigate the relationship between the examiner's voice quality, the child's performance on a digital version of a language comprehension test, the Test for Reception of Grammar (TROG-2), and two measures of cognitive functioning. The participants were (n = 86) mainstreamed 8-year old children with typical language development. Two groups of children (n = 41/45) were presented with the TROG-2 through recordings of one female speaker: one group was presented with a typical voice and the other with a simulated dysphonic voice. Significant associations were found between executive functioning and language comprehension. The results also showed that children listening to the dysphonic voice achieved significantly lower scores for more difficult sentences ("the man but not the horse jumps") and used more self-corrections on simpler sentences ("the girl is sitting"). Findings suggest that a dysphonic speaker's voice may force the child to allocate capacity to the processing of the voice signal at the expense of comprehension. The findings have implications for clinical and research settings where standardized language tests are used.

Coupled Electro-Magneto-Mechanical-Acoustic Analysis Method Developed by Using 2D Finite Element Method for Flat Panel Speaker Driven by Magnetostrictive-Material-Based Actuator

NASA Astrophysics Data System (ADS)

Yoo, Byungjin; Hirata, Katsuhiro; Oonishi, Atsurou

In this study, a coupled analysis method for flat panel speakers driven by giant magnetostrictive material (GMM) based actuator was developed. The sound field produced by a flat panel speaker that is driven by a GMM actuator depends on the vibration of the flat panel, this vibration is a result of magnetostriction property of the GMM. In this case, to predict the sound pressure level (SPL) in the audio-frequency range, it is necessary to take into account not only the magnetostriction property of the GMM but also the effect of eddy current and the vibration characteristics of the actuator and the flat panel. In this paper, a coupled electromagnetic-structural-acoustic analysis method is presented; this method was developed by using the finite element method (FEM). This analysis method is used to predict the performance of a flat panel speaker in the audio-frequency range. The validity of the analysis method is verified by comparing with the measurement results of a prototype speaker.

Theory of Mind and Context Processing in Schizophrenia: The Role of Social Knowledge.

PubMed

Champagne-Lavau, Maud; Charest, Anick

2015-01-01

The present study sought to determine whether social knowledge such as speaker occupation stereotypes may impact theory of mind (ToM) ability in patients with schizophrenia (SZ). Thirty individuals with SZ and 30 matched healthy control (HC) participants were tested individually on their ToM ability using a paradigm showing that stereotypes such as speaker occupation influences the extent to which speaker ironic intent is understood. ToM ability was assessed with open questions on the speaker ironic intent, irony rating, and mockery rating. Social perception was also assessed through politeness rating. The main results showed that SZ participants, like HC participants, were sensitive to the social stereotypes. They used these stereotypes adequately to attribute mental states such as speaker ironic intent to a protagonist while they found it difficult to explicitly judge and attribute negative attitude and emotion, as evidenced by mockery rating. No difference was found between the two groups regarding social perception ability. These performances were not associated with clinical symptoms. The integration of contextual information seems to be a good target for cognitive remediation aiming to increase social cognition ability.

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.

Photovoltaic Performance and Reliability Workshop summary

NASA Astrophysics Data System (ADS)

Kroposki, Benjamin

1997-02-01

The objective of the Photovoltaic Performance and Reliability Workshop was to provide a forum where the entire photovoltaic (PV) community (manufacturers, researchers, system designers, and customers) could get together and discuss technical issues relating to PV. The workshop included presentations from twenty-five speakers and had more than one hundred attendees. This workshop also included several open sessions in which the audience and speakers could discuss technical subjects in depth. Several major topics were discussed including: PV characterization and measurements, service lifetimes for PV devices, degradation and failure mechanisms for PV devices, standardization of testing procedures, AC module performance and reliability testing, inverter performance and reliability testing, standardization of utility interconnect requirements, experience from field deployed systems, and system certification.

Investigating Executive Working Memory and Phonological Short-Term Memory in Relation to Fluency and Self-Repair Behavior in L2 Speech.

PubMed

Georgiadou, Effrosyni; Roehr-Brackin, Karen

2017-08-01

This paper reports the findings of a study investigating the relationship of executive working memory (WM) and phonological short-term memory (PSTM) to fluency and self-repair behavior during an unrehearsed oral task performed by second language (L2) speakers of English at two levels of proficiency, elementary and lower intermediate. Correlational analyses revealed a negative relationship between executive WM and number of pauses in the lower intermediate L2 speakers. However, no reliable association was found in our sample between executive WM or PSTM and self-repair behavior in terms of either frequency or type of self-repair. Taken together, our findings suggest that while executive WM may enhance performance at the conceptualization and formulation stages of the speech production process, self-repair behavior in L2 speakers may depend on factors other than working memory.

'All the better for not seeing you': effects of communicative context on the speech of an individual with acquired communication difficulties.

PubMed

Bruce, Carolyn; Braidwood, Ursula; Newton, Caroline

2013-01-01

Evidence shows that speakers adjust their speech depending on the demands of the listener. However, it is unclear whether people with acquired communication disorders can and do make similar adaptations. This study investigated the impact of different conversational settings on the intelligibility of a speaker with acquired communication difficulties. Twenty-eight assessors listened to recordings of the speaker reading aloud 40 words and 32 sentences to a listener who was either face-to-face or unseen. The speaker's ability to convey information was measured by the accuracy of assessors' orthographic transcriptions of the words and sentences. Assessors' scores were significantly higher in the unseen condition for the single word task particularly if they had heard the face-to-face condition first. Scores for the sentence task were significantly higher in the second presentation regardless of the condition. The results from this study suggest that therapy conducted in situations where the client is not able to see their conversation partner may encourage them to perform at a higher level and increase the clarity of their speech. Readers will be able to describe: (1) the range of conversational adjustments made by speakers without communication difficulties; (2) differences between these tasks in offering contextual information to the listener; and (3) the potential for using challenging communicative situations to improve the performance of adults with communication disorders. Copyright © 2013 Elsevier Inc. All rights reserved.

Multimodal Speaker Diarization.

PubMed

Noulas, A; Englebienne, G; Krose, B J A

2012-01-01

We present a novel probabilistic framework that fuses information coming from the audio and video modality to perform speaker diarization. The proposed framework is a Dynamic Bayesian Network (DBN) that is an extension of a factorial Hidden Markov Model (fHMM) and models the people appearing in an audiovisual recording as multimodal entities that generate observations in the audio stream, the video stream, and the joint audiovisual space. The framework is very robust to different contexts, makes no assumptions about the location of the recording equipment, and does not require labeled training data as it acquires the model parameters using the Expectation Maximization (EM) algorithm. We apply the proposed model to two meeting videos and a news broadcast video, all of which come from publicly available data sets. The results acquired in speaker diarization are in favor of the proposed multimodal framework, which outperforms the single modality analysis results and improves over the state-of-the-art audio-based speaker diarization.

The Perception and Representation of Segmental and Prosodic Mandarin Contrasts in Native Speakers of Cantonese

PubMed Central

Zhang, Xujin; Samuel, Arthur G.; Liu, Siyun

2011-01-01

Previous research has found that a speaker’s native phonological system has a great influence on perception of another language. In three experiments, we tested the perception and representation of Mandarin phonological contrasts by Guangzhou Cantonese speakers, and compared their performance to that of native Mandarin speakers. Despite their rich experience using Mandarin Chinese, the Cantonese speakers had problems distinguishing specific Mandarin segmental and tonal contrasts that do not exist in Guangzhou Cantonese. However, we found evidence that the subtle differences between two members of a contrast were nonetheless represented in the lexicon. We also found different processing patterns for non-native segmental versus non-native tonal contrasts. The results provide substantial new information about the representation and processing of segmental and prosodic information by individuals listening to a closely-related, very well-learned, but still non-native language. PMID:22707849

Understanding of emotions and false beliefs among hearing children versus deaf children.

PubMed

Ziv, Margalit; Most, Tova; Cohen, Shirit

2013-04-01

Emotion understanding and theory of mind (ToM) are two major aspects of social cognition in which deaf children demonstrate developmental delays. The current study investigated these social cognition aspects in two subgroups of deaf children-those with cochlear implants who communicate orally (speakers) and those who communicate primarily using sign language (signers)-in comparison to hearing children. Participants were 53 Israeli kindergartners-20 speakers, 10 signers, and 23 hearing children. Tests included four emotion identification and understanding tasks and one false belief task (ToM). Results revealed similarities among all children's emotion labeling and affective perspective taking abilities, similarities between speakers and hearing children in false beliefs and in understanding emotions in typical contexts, and lower performance of signers on the latter three tasks. Adapting educational experiences to the unique characteristics and needs of speakers and signers is recommended.

Recognizing vocal emotions in Mandarin Chinese: a validated database of Chinese vocal emotional stimuli.

PubMed

Liu, Pan; Pell, Marc D

2012-12-01

To establish a valid database of vocal emotional stimuli in Mandarin Chinese, a set of Chinese pseudosentences (i.e., semantically meaningless sentences that resembled real Chinese) were produced by four native Mandarin speakers to express seven emotional meanings: anger, disgust, fear, sadness, happiness, pleasant surprise, and neutrality. These expressions were identified by a group of native Mandarin listeners in a seven-alternative forced choice task, and items reaching a recognition rate of at least three times chance performance in the seven-choice task were selected as a valid database and then subjected to acoustic analysis. The results demonstrated expected variations in both perceptual and acoustic patterns of the seven vocal emotions in Mandarin. For instance, fear, anger, sadness, and neutrality were associated with relatively high recognition, whereas happiness, disgust, and pleasant surprise were recognized less accurately. Acoustically, anger and pleasant surprise exhibited relatively high mean f0 values and large variation in f0 and amplitude; in contrast, sadness, disgust, fear, and neutrality exhibited relatively low mean f0 values and small amplitude variations, and happiness exhibited a moderate mean f0 value and f0 variation. Emotional expressions varied systematically in speech rate and harmonics-to-noise ratio values as well. This validated database is available to the research community and will contribute to future studies of emotional prosody for a number of purposes. To access the database, please contact pan.liu@mail.mcgill.ca.

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.

Do We All Apologize the Same?--An Empirical Study on the Act of Apologizing by Spanish Speakers Learning English.

ERIC Educational Resources Information Center

Mir, Montserrat

1992-01-01

A study examined the production of English apology strategies by Spanish speakers learning English, by analyzing the remedial move in native and non-native social interactions. To restore harmony when an offensive act has been committed, remedial exchanges are performed according to the rules of speaking and the social norms of the speech…

The Functional Unit in Phonological Encoding: Evidence for Moraic Representation in Native Japanese Speakers

ERIC Educational Resources Information Center

Kureta, Yoichi; Fushimi, Takao; Tatsumi, Itaru F.

2006-01-01

Speech production studies have shown that the phonological form of a word is made up of phonemic segments in stress-timed languages (e.g., Dutch) and of syllables in syllable timed languages (e.g., Chinese). To clarify the functional unit of mora-timed languages, the authors asked native Japanese speakers to perform an implicit priming task (A. S.…

The Relationship between Receptive and Expressive Subskills of Academic L2 Proficiency in Nonnative Speakers of English: A Multigroup Approach

ERIC Educational Resources Information Center

Pae, Hye K.; Greenberg, Daphne

2014-01-01

The purpose of this study was to examine the relationship between receptive and expressive language skills characterized by the performance of nonnative speakers (NNSs) of English in the academic context. Test scores of 585 adult NNSs were selected from Form 2 of the Pearson Test of English Academic's field-test database. A correlated…

U.S. History and Modern World History Courses for English Speakers of Other Languages in Montgomery County Public Schools

ERIC Educational Resources Information Center

Zhao, Huafang; Wade, Julie

2014-01-01

The Office of Shared Accountability (OSA) in Montgomery County (Maryland) Public Schools (MCPS) examined academic performance of English for Speakers of Other Languages (ESOL) students in U.S. History and Modern World History courses, as well as the course sequence in ESOL U.S. History and Modern World History. In MCPS, students who are not ESOL…

Understanding and Overcoming Pragmatic Failure in Intercultural Communication: From Focus on Speakers to Focus on Hearers

ERIC Educational Resources Information Center

Padilla Cruz, Manuel

2013-01-01

For learners to communicate efficiently in the L2, they must avoid pragmatic failure. In many cases, teachers' praxis centres on the learner's performance in the L2 or his role as a speaker, which neglects the importance of his role as interpreter of utterances. Assuming that, as hearers, learners also have a responsibility to avoid…

Performance enhancement for audio-visual speaker identification using dynamic facial muscle model.

PubMed

Asadpour, Vahid; Towhidkhah, Farzad; Homayounpour, Mohammad Mehdi

2006-10-01

Science of human identification using physiological characteristics or biometry has been of great concern in security systems. However, robust multimodal identification systems based on audio-visual information has not been thoroughly investigated yet. Therefore, the aim of this work to propose a model-based feature extraction method which employs physiological characteristics of facial muscles producing lip movements. This approach adopts the intrinsic properties of muscles such as viscosity, elasticity, and mass which are extracted from the dynamic lip model. These parameters are exclusively dependent on the neuro-muscular properties of speaker; consequently, imitation of valid speakers could be reduced to a large extent. These parameters are applied to a hidden Markov model (HMM) audio-visual identification system. In this work, a combination of audio and video features has been employed by adopting a multistream pseudo-synchronized HMM training method. Noise robust audio features such as Mel-frequency cepstral coefficients (MFCC), spectral subtraction (SS), and relative spectra perceptual linear prediction (J-RASTA-PLP) have been used to evaluate the performance of the multimodal system once efficient audio feature extraction methods have been utilized. The superior performance of the proposed system is demonstrated on a large multispeaker database of continuously spoken digits, along with a sentence that is phonetically rich. To evaluate the robustness of algorithms, some experiments were performed on genetically identical twins. Furthermore, changes in speaker voice were simulated with drug inhalation tests. In 3 dB signal to noise ratio (SNR), the dynamic muscle model improved the identification rate of the audio-visual system from 91 to 98%. Results on identical twins revealed that there was an apparent improvement on the performance for the dynamic muscle model-based system, in which the identification rate of the audio-visual system was enhanced from 87 to 96%.

Determinants of naming latencies, object comprehension times, and new norms for the Russian standardized set of the colorized version of the Snodgrass and Vanderwart pictures.

PubMed

Bonin, Patrick; Guillemard-Tsaparina, Diana; Méot, Alain

2013-09-01

We report object-naming and object recognition times collected from Russian native speakers for the colorized version of the Snodgrass and Vanderwart (Journal of Experimental Psychology: Human Learning and Memory 6:174-215, 1980) pictures (Rossion & Pourtois, Perception 33:217-236, 2004). New norms for image variability, body-object interaction [BOI], and subjective frequency collected in Russian, as well as new name agreement scores for the colorized pictures in French, are also reported. In both object-naming and object comprehension times, the name agreement, image agreement, and age-of-acquisition variables made significant independent contributions. Objective word frequency was reliable in object-naming latencies only. The variables of image variability, BOI, and subjective frequency were not significant in either object naming or object comprehension. Finally, imageability was reliable in both tasks. The new norms and object-naming and object recognition times are provided as supplemental materials.

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

Representational deficit or processing effect? An electrophysiological study of noun-noun compound processing by very advanced L2 speakers of English

PubMed Central

De Cat, Cecile; Klepousniotou, Ekaterini; Baayen, R. Harald

2015-01-01

The processing of English noun-noun compounds (NNCs) was investigated to identify the extent and nature of differences between the performance of native speakers of English and advanced Spanish and German non-native speakers of English. The study sought to establish whether the word order of the equivalent structure in the non-native speakers' mothertongue (L1) had an influence on their processing of NNCs in their second language (L2), and whether this influence was due to differences in grammatical representation (i.e., incomplete acquisition of the relevant structure) or processing effects. Two mask-primed lexical decision experiments were conducted in which compounds were presented with their constituent nouns in licit vs. reversed order. The first experiment used a speeded lexical decision task with reaction time registration, and the second a delayed lexical decision task with EEG registration. There were no significant group differences in accuracy in the licit word order condition, suggesting that the grammatical representation had been fully acquired by the non-native speakers. However, the Spanish speakers made slightly more errors with the reversed order and had longer response times, suggesting an L1 interference effect (as the reverse order matches the licit word order in Spanish). The EEG data, analyzed with generalized additive mixed models, further supported this hypothesis. The EEG waveform of the non-native speakers was characterized by a slightly later onset N400 in the violation condition (reversed constituent order). Compound frequency predicted the amplitude of the EEG signal for the licit word order for native speakers, but for the reversed constituent order for Spanish speakers—the licit order in their L1—supporting the hypothesis that Spanish speakers are affected by interferences from their L1. The pattern of results for the German speakers in the violation condition suggested a strong conflict arising due to licit constituents being presented in an order that conflicts with the expected order in both their L1 and L2. PMID:25709590

Toward the Early Recognition of Psychosis Among Spanish-Speaking Adults on both Sides of the US-Mexico Border

PubMed Central

Casas, Rachel Nichole; Gonzales, Edlin; Aldana-Aragón, Eréndira; Lara-Muñoz, María del Carmen; Kopelowicz, Alex; Andrews, Laura; López, Steven Regeser

2015-01-01

Lack of knowledge about psychosis, a condition oftentimes associated with serious mental illness, may contribute to disparities in mental health service use. Psychoeducational interventions aimed at improving psychosis literacy have attracted significant attention recently, but few have focused on the growing numbers of ethnic and linguistic minorities in countries with large immigrant populations, such as the United States. This paper reports on two studies designed to evaluate the effectiveness of a DVD version of La CLAve, a psychoeducational program that aims to increase psychosis literacy among Spanish-speaking Latinos. Study 1 is a randomized control study to test directly the efficacy of a DVD version of La CLAve for Spanish-speakers across a range of educational backgrounds. Fifty-seven medical students and 68 community residents from Mexico were randomly assigned to view either La CLAve or a psychoeducational program of similar length regarding caregiving. Study 2 employed a single-subjects design to evaluate the effectiveness of the DVD presentation when administered by a community mental health educator. Ninety-three Spanish-speakers from San Diego, California completed assessments both before and after receiving the DVD training. Results from these two studies indicate that the DVD version of La CLAve is capable of producing a range of psychosis literacy gains for Spanish-speakers in both the United States and Mexico, even when administered by a community worker. Thus, it has potential for widespread dissemination and use among underserved communities of Spanish-speaking Latinos and for minimizing disparities in mental health service use, particularly as it relates to insufficient knowledge of psychosis. PMID:25383998

Impact of Acoustic Standing Waves on Structural Responses: Reverberant Acoustic Testing (RAT) vs. Direct Field Acoustic Testing (DFAT)

NASA Technical Reports Server (NTRS)

Kolaini, Ali R.; Doty, Benjamin; Chang, Zensheu

2012-01-01

Loudspeakers have been used for acoustic qualification of spacecraft, reflectors, solar panels, and other acoustically responsive structures for more than a decade. Limited measurements from some of the recent speaker tests used to qualify flight hardware have indicated significant spatial variation of the acoustic field within the test volume. Also structural responses have been reported to differ when similar tests were performed using reverberant chambers. To address the impact of non-uniform acoustic field on structural responses, a series of acoustic tests were performed using a flat panel and a 3-ft cylinder exposed to the field controlled by speakers and repeated in a reverberant chamber. The speaker testing was performed using multi-input-single-output (MISO) and multi-input-multi-output (MIMO) control schemes with and without the test articles. In this paper the spatial variation of the acoustic field due to acoustic standing waves and their impacts on the structural responses in RAT and DFAT (both using MISO and MIMO controls for DFAT) are discussed in some detail.

Design of a digital voice data compression technique for orbiter voice channels

NASA Technical Reports Server (NTRS)

1975-01-01

Candidate techniques were investigated for digital voice compression to a transmission rate of 8 kbps. Good voice quality, speaker recognition, and robustness in the presence of error bursts were considered. The technique of delayed-decision adaptive predictive coding is described and compared with conventional adaptive predictive coding. Results include a set of experimental simulations recorded on analog tape. The two FM broadcast segments produced show the delayed-decision technique to be virtually undegraded or minimally degraded at .001 and .01 Viterbi decoder bit error rates. Preliminary estimates of the hardware complexity of this technique indicate potential for implementation in space shuttle orbiters.

KSC-04pd0490

NASA Image and Video Library

2004-03-12

KENNEDY SPACE CENTER, FLA. - Florida Gov. Jeb Bush (left) and Center Director Jim Kennedy enjoy a humorous break at the luncheon for the 2004 Florida Regional FIRST competition held at the University of Central Florida. Both are featured speakers. The event hosted 41 teams from Canada, Brazil, Great Britain and the United States. FIRST is a nonprofit organization, For Inspiration and Recognition of Science and Technology, that sponsors the event pitting gladiator robots against each other in an athletic-style competition. The FIRST robotics competition is designed to provide students with a hands-on, inside look at engineering and other professional careers, pairing high school students with engineer mentors and corporations.

Hearing history influences voice gender perceptual performance in cochlear implant users.

PubMed

Kovačić, Damir; Balaban, Evan

2010-12-01

The study was carried out to assess the role that five hearing history variables (chronological age, age at onset of deafness, age of first cochlear implant [CI] activation, duration of CI use, and duration of known deafness) play in the ability of CI users to identify speaker gender. Forty-one juvenile CI users participated in two voice gender identification tasks. In a fixed, single-interval task, subjects listened to a single speech item from one of 20 adult male or 20 adult female speakers and had to identify speaker gender. In an adaptive speech-based voice gender discrimination task with the fundamental frequency difference between the voices as the adaptive parameter, subjects listened to a pair of speech items presented in sequential order, one of which was always spoken by an adult female and the other by an adult male. Subjects had to identify the speech item spoken by the female voice. Correlation and regression analyses between perceptual scores in the two tasks and the hearing history variables were performed. Subjects fell into three performance groups: (1) those who could distinguish voice gender in both tasks, (2) those who could distinguish voice gender in the adaptive but not the fixed task, and (3) those who could not distinguish voice gender in either task. Gender identification performance for single voices in the fixed task was significantly and negatively related to the duration of deafness before cochlear implantation (shorter deafness yielded better performance), whereas performance in the adaptive task was weakly but significantly related to age at first activation of the CI device, with earlier activations yielding better scores. The existence of a group of subjects able to perform adaptive discrimination but unable to identify the gender of singly presented voices demonstrates the potential dissociability of the skills required for these two tasks, suggesting that duration of deafness and age of cochlear implantation could have dissociable effects on the development of different skills required by CI users to identify speaker gender.

The Main Concept Analysis: Validation and sensitivity in differentiating discourse produced by unimpaired English speakers from individuals with aphasia and dementia of Alzheimer type.

PubMed

Kong, Anthony Pak-Hin; Whiteside, Janet; Bargmann, Peggy

2016-10-01

Discourse from speakers with dementia and aphasia is associated with comparable but not identical deficits, necessitating appropriate methods to differentiate them. The current study aims to validate the Main Concept Analysis (MCA) to be used for eliciting and quantifying discourse among native typical English speakers and to establish its norm, and investigate the validity and sensitivity of the MCA to compare discourse produced by individuals with fluent aphasia, non-fluent aphasia, or dementia of Alzheimer's type (DAT), and unimpaired elderly. Discourse elicited through a sequential picture description task was collected from 60 unimpaired participants to determine the MCA scoring criteria; 12 speakers with fluent aphasia, 12 with non-fluent aphasia, 13 with DAT, and 20 elderly participants from the healthy group were compared on the finalized MCA. Results of MANOVA revealed significant univariate omnibus effects of speaker group as an independent variable on each main concept index. MCA profiles differed significantly between all participant groups except dementia versus fluent aphasia. Correlations between the MCA performances and the Western Aphasia Battery and Cognitive Linguistic Quick Test were found to be statistically significant among the clinical groups. The MCA was appropriate to be used among native speakers of English. The results also provided further empirical evidence of discourse deficits in aphasia and dementia. Practitioners can use the MCA to evaluate discourse production systemically and objectively.

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

Lexical access in a bilingual speaker with dementia: Changes over time.

PubMed

Lind, Marianne; Simonsen, Hanne Gram; Ribu, Ingeborg Sophie Bjønness; Svendsen, Bente Ailin; Svennevig, Jan; de Bot, Kees

2018-01-01

In this article, we explore the naming skills of a bilingual English-Norwegian speaker diagnosed with Primary Progressive Aphasia, in each of his languages across three different speech contexts: confrontation naming, semi-spontaneous narrative (picture description), and conversation, and at two points in time: 12 and 30 months post diagnosis, respectively. The results are discussed in light of two main theories of lexical retrieval in healthy, elderly speakers: the Transmission Deficit Hypothesis and the Inhibitory Deficit Theory. Our data show that, consistent with the participant's premorbid use of and proficiency in the two languages, his performance in his L2 is lower than in his L1, but this difference diminishes as the disease progresses. This is the case across the three speech contexts; however, the difference is smaller in the narrative task, where his performance is very low in both languages already at the first measurement point. Despite his word finding problems, he is able to take active part in conversation, particularly in his L1 and more so at the first measurement point. In addition to the task effect, we find effects of word class, frequency, and cognateness on his naming skills. His performance seems to support the Transmission Deficit Hypothesis. By combining different tools and methods of analysis, we get a more comprehensive picture of the impact of the dementia on the speaker's languages from an intra-individual as well as an inter-individual perspective, which may be useful in research as well as in clinical practice.

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.

Selective Audiovisual Semantic Integration Enabled by Feature-Selective Attention.

PubMed

Li, Yuanqing; Long, Jinyi; Huang, Biao; Yu, Tianyou; Wu, Wei; Li, Peijun; Fang, Fang; Sun, Pei

2016-01-13

An audiovisual object may contain multiple semantic features, such as the gender and emotional features of the speaker. Feature-selective attention and audiovisual semantic integration are two brain functions involved in the recognition of audiovisual objects. Humans often selectively attend to one or several features while ignoring the other features of an audiovisual object. Meanwhile, the human brain integrates semantic information from the visual and auditory modalities. However, how these two brain functions correlate with each other remains to be elucidated. In this functional magnetic resonance imaging (fMRI) study, we explored the neural mechanism by which feature-selective attention modulates audiovisual semantic integration. During the fMRI experiment, the subjects were presented with visual-only, auditory-only, or audiovisual dynamical facial stimuli and performed several feature-selective attention tasks. Our results revealed that a distribution of areas, including heteromodal areas and brain areas encoding attended features, may be involved in audiovisual semantic integration. Through feature-selective attention, the human brain may selectively integrate audiovisual semantic information from attended features by enhancing functional connectivity and thus regulating information flows from heteromodal areas to brain areas encoding the attended features.

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.

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

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.

Structural Metadata Research in the Ears Program

DTIC Science & Technology

2005-01-01

detecting structural information in the word stream (the so-called “structural MDE” portion of the EARS program); other MDE efforts on speaker ... diarization are overviewed in [13]. The rest of this paper is organized as follows. We describe the structural MDE tasks, performance measurement, and corpora...tems have only recently been introduced, with NIST reporting re- sults with the Wilcoxon signed rank test for speaker -level average score differences

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…

Advanced Course Enrollment and Performance in Washington State: Comparing Spanish-Speaking Students with Other Language Minority Students and English-Only Speakers. REL 2017-220

ERIC Educational Resources Information Center

Hanson, Havala; Bisht, Biraj; Motamedi, Jason Greenberg

2017-01-01

Students who take advanced courses in high school are more likely to enroll and persist in college. This report describes patterns in advanced coursetaking among three groups of students in Washington state: Spanish-speaking students, other language minority students whose primary or home language is not Spanish, and English-only speakers. This…

Language complexity modulates 8- and 10-year-olds' success at using their theory of mind abilities in a communication task.

PubMed

Wang, J Jessica; Ali, Muna; Frisson, Steven; Apperly, Ian A

2016-09-01

Basic competence in theory of mind is acquired during early childhood. Nonetheless, evidence suggests that the ability to take others' perspectives in communication improves continuously from middle childhood to the late teenage years. This indicates that theory of mind performance undergoes protracted developmental changes after the acquisition of basic competence. Currently, little is known about the factors that constrain children's performance or that contribute to age-related improvement. A sample of 39 8-year-olds and 56 10-year-olds were tested on a communication task in which a speaker's limited perspective needed to be taken into account and the complexity of the speaker's utterance varied. Our findings showed that 10-year-olds were generally less egocentric than 8-year-olds. Children of both ages committed more egocentric errors when a speaker uttered complex sentences compared with simple sentences. Both 8- and 10-year-olds were affected by the demand to integrate complex sentences with the speaker's limited perspective and to a similar degree. These results suggest that long after children's development of simple visual perspective-taking, their use of this ability to assist communication is substantially constrained by the complexity of the language involved. Copyright © 2015 Elsevier Inc. All rights reserved.

Age of acquisition and naming performance in Frisian-Dutch bilingual speakers with dementia.

PubMed

Veenstra, Wencke S; Huisman, Mark; Miller, Nick

2014-01-01

Age of acquisition (AoA) of words is a recognised variable affecting language processing in speakers with and without language disorders. For bi- and multilingual speakers their languages can be differentially affected in neurological illness. Study of language loss in bilingual speakers with dementia has been relatively neglected. We investigated whether AoA of words was associated with level of naming impairment in bilingual speakers with probable Alzheimer's dementia within and across their languages. Twenty-six Frisian-Dutch bilinguals with mild to moderate dementia named 90 pictures in each language, employing items with rated AoA and other word variable measures matched across languages. Quantitative (totals correct) and qualitative (error types and (in)appropriate switching) aspects were measured. Impaired retrieval occurred in Frisian (Language 1) and Dutch (Language 2), with a significant effect of AoA on naming in both languages. Earlier acquired words were better preserved and retrieved. Performance was identical across languages, but better in Dutch when controlling for covariates. However, participants demonstrated more inappropriate code switching within the Frisian test setting. On qualitative analysis, no differences in overall error distribution were found between languages for early or late acquired words. There existed a significantly higher percentage of semantically than visually-related errors. These findings have implications for understanding problems in lexical retrieval among bilingual individuals with dementia and its relation to decline in other cognitive functions which may play a role in inappropriate code switching. We discuss the findings in the light of the close relationship between Frisian and Dutch and the pattern of usage across the life-span.

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

A Functional Imaging Study of Self-Regulatory Capacities in Persons Who Stutter

PubMed Central

Liu, Jie; Wang, Zhishun; Huo, Yuankai; Davidson, Stephanie M.; Klahr, Kristin; Herder, Carl L.; Sikora, Chamonix O.; Peterson, Bradley S.

2014-01-01

Developmental stuttering is a disorder of speech fluency with an unknown pathogenesis. The similarity of its phenotype and natural history with other childhood neuropsychiatric disorders of frontostriatal pathology suggests that stuttering may have a closely related pathogenesis. We investigated in this study the potential involvement of frontostriatal circuits in developmental stuttering. We collected functional magnetic resonance imaging data from 46 persons with stuttering and 52 fluent controls during performance of the Simon Spatial Incompatibility Task. We examined differences between the two groups of blood-oxygen-level-dependent activation associated with two neural processes, the resolution of cognitive conflict and the context-dependent adaptation to changes in conflict. Stuttering speakers and controls did not differ on behavioral performance on the task. In the presence of conflict-laden stimuli, however, stuttering speakers activated more strongly the cingulate cortex, left anterior prefrontal cortex, right medial frontal cortex, left supplementary motor area, right caudate nucleus, and left parietal cortex. The magnitude of activation in the anterior cingulate cortex correlated inversely in stuttering speakers with symptom severity. Stuttering speakers also showed blunted activation during context-dependent adaptation in the left dorsolateral prefrontal cortex, a brain region that mediates cross-temporal contingencies. Frontostriatal hyper-responsivity to conflict resembles prior findings in other disorders of frontostriatal pathology, and therefore likely represents a general mechanism supporting functional compensation for an underlying inefficiency of neural processing in these circuits. The reduced activation of dorsolateral prefrontal cortex likely represents the inadequate readiness of stuttering speakers to execute a sequence of motor responses. PMID:24587104

Validity of Single-Item Screening for Limited Health Literacy in English and Spanish Speakers.

PubMed

Bishop, Wendy Pechero; Craddock Lee, Simon J; Skinner, Celette Sugg; Jones, Tiffany M; McCallister, Katharine; Tiro, Jasmin A

2016-05-01

To evaluate 3 single-item screening measures for limited health literacy in a community-based population of English and Spanish speakers. We recruited 324 English and 314 Spanish speakers from a community research registry in Dallas, Texas, enrolled between 2009 and 2012. We used 3 screening measures: (1) How would you rate your ability to read?; (2) How confident are you filling out medical forms by yourself?; and (3) How often do you have someone help you read hospital materials? In analyses stratified by language, we used area under the receiver operating characteristic (AUROC) curves to compare each item with the validated 40-item Short Test of Functional Health Literacy in Adults. For English speakers, no difference was seen among the items. For Spanish speakers, "ability to read" identified inadequate literacy better than "help reading hospital materials" (AUROC curve = 0.76 vs 0.65; P = .019). The "ability to read" item performed the best, supporting use as a screening tool in safety-net systems caring for diverse populations. Future studies should investigate how to implement brief measures in safety-net settings and whether highlighting health literacy level influences providers' communication practices and patient outcomes.

Evaluating acoustic speaker normalization algorithms: evidence from longitudinal child data.

PubMed

Kohn, Mary Elizabeth; Farrington, Charlie

2012-03-01

Speaker vowel formant normalization, a technique that controls for variation introduced by physical differences between speakers, is necessary in variationist studies to compare speakers of different ages, genders, and physiological makeup in order to understand non-physiological variation patterns within populations. Many algorithms have been established to reduce variation introduced into vocalic data from physiological sources. The lack of real-time studies tracking the effectiveness of these normalization algorithms from childhood through adolescence inhibits exploration of child participation in vowel shifts. This analysis compares normalization techniques applied to data collected from ten African American children across five time points. Linear regressions compare the reduction in variation attributable to age and gender for each speaker for the vowels BEET, BAT, BOT, BUT, and BOAR. A normalization technique is successful if it maintains variation attributable to a reference sociolinguistic variable, while reducing variation attributable to age. Results indicate that normalization techniques which rely on both a measure of central tendency and range of the vowel space perform best at reducing variation attributable to age, although some variation attributable to age persists after normalization for some sections of the vowel space. © 2012 Acoustical Society of America

On the optimization of a mixed speaker array in an enclosed space using the virtual-speaker weighting method

NASA Astrophysics Data System (ADS)

Peng, Bo; Zheng, Sifa; Liao, Xiangning; Lian, Xiaomin

2018-03-01

In order to achieve sound field reproduction in a wide frequency band, multiple-type speakers are used. The reproduction accuracy is not only affected by the signals sent to the speakers, but also depends on the position and the number of each type of speaker. The method of optimizing a mixed speaker array is investigated in this paper. A virtual-speaker weighting method is proposed to optimize both the position and the number of each type of speaker. In this method, a virtual-speaker model is proposed to quantify the increment of controllability of the speaker array when the speaker number increases. While optimizing a mixed speaker array, the gain of the virtual-speaker transfer function is used to determine the priority orders of the candidate speaker positions, which optimizes the position of each type of speaker. Then the relative gain of the virtual-speaker transfer function is used to determine whether the speakers are redundant, which optimizes the number of each type of speaker. Finally the virtual-speaker weighting method is verified by reproduction experiments of the interior sound field in a passenger car. The results validate that the optimum mixed speaker array can be obtained using the proposed method.

Encoding lexical tones in jTRACE: a simulation of monosyllabic spoken word recognition in Mandarin Chinese.

PubMed

Shuai, Lan; Malins, Jeffrey G

2017-02-01

Despite its prevalence as one of the most highly influential models of spoken word recognition, the TRACE model has yet to be extended to consider tonal languages such as Mandarin Chinese. A key reason for this is that the model in its current state does not encode lexical tone. In this report, we present a modified version of the jTRACE model in which we borrowed on its existing architecture to code for Mandarin phonemes and tones. Units are coded in a way that is meant to capture the similarity in timing of access to vowel and tone information that has been observed in previous studies of Mandarin spoken word recognition. We validated the model by first simulating a recent experiment that had used the visual world paradigm to investigate how native Mandarin speakers process monosyllabic Mandarin words (Malins & Joanisse, 2010). We then subsequently simulated two psycholinguistic phenomena: (1) differences in the timing of resolution of tonal contrast pairs, and (2) the interaction between syllable frequency and tonal probability. In all cases, the model gave rise to results comparable to those of published data with human subjects, suggesting that it is a viable working model of spoken word recognition in Mandarin. It is our hope that this tool will be of use to practitioners studying the psycholinguistics of Mandarin Chinese and will help inspire similar models for other tonal languages, such as Cantonese and Thai.

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.

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

[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.

Tone Attrition in Mandarin Speakers of Varying English Proficiency

PubMed Central

Creel, Sarah C.

2017-01-01

Purpose The purpose of this study was to determine whether the degree of dominance of Mandarin–English bilinguals' languages affects phonetic processing of tone content in their native language, Mandarin. Method We tested 72 Mandarin–English bilingual college students with a range of language-dominance profiles in the 2 languages and ages of acquisition of English. Participants viewed 2 photographs at a time while hearing a familiar Mandarin word referring to 1 photograph. The names of the 2 photographs diverged in tone, vowels, or both. Word recognition was evaluated using clicking accuracy, reaction times, and an online recognition measure (gaze) and was compared in the 3 conditions. Results Relative proficiency in English was correlated with reduced word recognition success in tone-disambiguated trials, but not in vowel-disambiguated trials, across all 3 dependent measures. This selective attrition for tone content emerged even though all bilinguals had learned Mandarin from birth. Lengthy experience with English thus weakened tone use. Conclusions This finding has implications for the question of the extent to which bilinguals' 2 phonetic systems interact. It suggests that bilinguals may not process pitch information language-specifically and that processing strategies from the dominant language may affect phonetic processing in the nondominant language—even when the latter was learned natively. PMID:28124064

EEG-based auditory attention decoding using unprocessed binaural signals in reverberant and noisy conditions?

PubMed

Aroudi, Ali; Doclo, Simon

2017-07-01

To decode auditory attention from single-trial EEG recordings in an acoustic scenario with two competing speakers, a least-squares method has been recently proposed. This method however requires the clean speech signals of both the attended and the unattended speaker to be available as reference signals. Since in practice only the binaural signals consisting of a reverberant mixture of both speakers and background noise are available, in this paper we explore the potential of using these (unprocessed) signals as reference signals for decoding auditory attention in different acoustic conditions (anechoic, reverberant, noisy, and reverberant-noisy). In addition, we investigate whether it is possible to use these signals instead of the clean attended speech signal for filter training. The experimental results show that using the unprocessed binaural signals for filter training and for decoding auditory attention is feasible with a relatively large decoding performance, although for most acoustic conditions the decoding performance is significantly lower than when using the clean speech signals.

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

The Exposure Advantage: Early Exposure to a Multilingual Environment Promotes Effective Communication.

PubMed

Fan, Samantha P; Liberman, Zoe; Keysar, Boaz; Kinzler, Katherine D

2015-07-01

Early language exposure is essential to developing a formal language system, but may not be sufficient for communicating effectively. To understand a speaker's intention, one must take the speaker's perspective. Multilingual exposure may promote effective communication by enhancing perspective taking. We tested children on a task that required perspective taking to interpret a speaker's intended meaning. Monolingual children failed to interpret the speaker's meaning dramatically more often than both bilingual children and children who were exposed to a multilingual environment but were not bilingual themselves. Children who were merely exposed to a second language performed as well as bilingual children, despite having lower executive-function scores. Thus, the communicative advantages demonstrated by the bilinguals may be social in origin, and not due to enhanced executive control. For millennia, multilingual exposure has been the norm. Our study shows that such an environment may facilitate the development of perspective-taking tools that are critical for effective communication. © The Author(s) 2015.

More than Use it or Lose it: The Number of Speakers Effect on Heritage Language Proficiency

PubMed Central

Gollan, Tamar H.; Starr, Jennie; Ferreira, Victor S.

2014-01-01

Acquiring a Heritage Language (HL), a minority language spoken primarily at home, is often a major step toward achieving bilingualism. Two studies examined factors that promote HL proficiency. Chinese-English and Spanish-English undergraduates and Hebrew-English children named pictures in both their languages, and they or their parents completed language history questionnaires. HL picture-naming ability correlated positively with the number of different HL speakers participants spoke to as children, independent of each language’s frequency of use, and without negatively affecting English picture naming ability. HL performance increased also when primary caregivers had lower English proficiency, with later English age-of-acquisition, and (in children) with increased age. These results suggest a prescription for increasing bilingual proficiency is regular interaction with multiple HL speakers. Responsible cognitive mechanisms could include greater variety of words used by different speakers, representational robustness from exposure to variations in form, or multiple retrieval cues, perhaps analogous to contextual diversity effects. PMID:24942146

Suppression and Working Memory in Auditory Comprehension of L2 Narratives: Evidence from Cross-Modal Priming.

PubMed

Wu, Shiyu; Ma, Zheng

2016-10-01

Using a cross-modal priming task, the present study explores whether Chinese-English bilinguals process goal related information during auditory comprehension of English narratives like native speakers. Results indicate that English native speakers adopted both mechanisms of suppression and enhancement to modulate the activation of goals and keep track of the "causal path" in narrative events and that L1 speakers with higher working memory (WM) capacity are more skilled at attenuating interference. L2 speakers, however, experienced the phenomenon of "facilitation-without-inhibition." Their difficulty in suppressing irrelevant information was related to their performance in the test of working memory capacity. For the L2 group with greater working memory capacity, the effects of both enhancement and suppression were found. These findings are discussed in light of a landscape model of L2 text comprehension which highlights the need for WM to be incorporated into comprehensive models of L2 processing as well as theories of SLA.

Orthography affects second language speech: Double letters and geminate production in English.

PubMed

Bassetti, Bene

2017-11-01

Second languages (L2s) are often learned through spoken and written input, and L2 orthographic forms (spellings) can lead to non-native-like pronunciation. The present study investigated whether orthography can lead experienced learners of English L2 to make a phonological contrast in their speech production that does not exist in English. Double consonants represent geminate (long) consonants in Italian but not in English. In Experiment 1, native English speakers and English L2 speakers (Italians) were asked to read aloud English words spelled with a single or double target consonant letter, and consonant duration was compared. The English L2 speakers produced the same consonant as shorter when it was spelled with a single letter, and longer when spelled with a double letter. Spelling did not affect consonant duration in native English speakers. In Experiment 2, effects of orthographic input were investigated by comparing 2 groups of English L2 speakers (Italians) performing a delayed word repetition task with or without orthographic input; the same orthographic effects were found in both groups. These results provide arguably the first evidence that L2 orthographic forms can lead experienced L2 speakers to make a contrast in their L2 production that does not exist in the language. The effect arises because L2 speakers are affected by the interaction between the L2 orthographic form (number of letters), and their native orthography-phonology mappings, whereby double consonant letters represent geminate consonants. These results have important implications for future studies investigating the effects of orthography on native phonology and for L2 phonological development models. (PsycINFO Database Record (c) 2017 APA, all rights reserved).

Functional activity and white matter microstructure reveal the independent effects of age of acquisition and proficiency on second-language learning.

PubMed

Nichols, Emily S; Joanisse, Marc F

2016-12-01

Two key factors govern how bilingual speakers neurally maintain two languages: the speakers' second language age of acquisition (AoA) and their subsequent proficiency. However, the relative roles of these two factors have been difficult to disentangle given that the two can be closely correlated, and most prior studies have examined the two factors in isolation. Here, we combine functional magnetic resonance imaging with diffusion tensor imaging to identify specific brain areas that are independently modulated by AoA and proficiency in second language speakers. First-language Mandarin Chinese speakers who are second language speakers of English were scanned as they performed a picture-word matching task in either language. In the same session we also acquired diffusion-weighted scans to assess white matter microstructure, along with behavioural measures of language proficiency prior to entering the scanner. Results reveal gray- and white-matter networks involving both the left and right hemisphere that independently vary as a function of a second-language speaker's AoA and proficiency, focused on the superior temporal gyrus, middle and inferior frontal gyrus, parahippocampal gyrus, and the basal ganglia. These results indicate that proficiency and AoA explain separate functional and structural networks in the bilingual brain, which we interpret as suggesting distinct types of plasticity for age-dependent effects (i.e., AoA) versus experience and/or predisposition (i.e., proficiency). Copyright © 2016 The Authors. Published by Elsevier Inc. All rights reserved.

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.

Evaluating language environment analysis system performance for Chinese: a pilot study in Shanghai.

PubMed

Gilkerson, Jill; Zhang, Yiwen; Xu, Dongxin; Richards, Jeffrey A; Xu, Xiaojuan; Jiang, Fan; Harnsberger, James; Topping, Keith

2015-04-01

The purpose of this study was to evaluate performance of the Language Environment Analysis (LENA) automated language-analysis system for the Chinese Shanghai dialect and Mandarin (SDM) languages. Volunteer parents of 22 children aged 3-23 months were recruited in Shanghai. Families provided daylong in-home audio recordings using LENA. A native speaker listened to 15 min of randomly selected audio samples per family to label speaker regions and provide Chinese character and SDM word counts for adult speakers. LENA segment labeling and counts were compared with rater-based values. LENA demonstrated good sensitivity in identifying adult and child; this sensitivity was comparable to that of American English validation samples. Precision was strong for adults but less so for children. LENA adult word count correlated strongly with both Chinese characters and SDM word counts. LENA conversational turn counts correlated similarly with rater-based counts after the exclusion of three unusual samples. Performance related to some degree to child age. LENA adult word count and conversational turn provided reasonably accurate estimates for SDM over the age range tested. Theoretical and practical considerations regarding LENA performance in non-English languages are discussed. Despite the pilot nature and other limitations of the study, results are promising for broader cross-linguistic applications.

Oral-diadochokinetic rates for Hebrew-speaking healthy ageing population: non-word versus real-word repetition.

PubMed

Ben-David, Boaz M; Icht, Michal

2017-05-01

Oral-diadochokinesis (oral-DDK) tasks are extensively used in the evaluation of motor speech abilities. Currently, validated normative data for older adults (aged 65 years and older) are missing in Hebrew. The effect of task stimuli (non-word versus real-word repetition) is also non-clear in the population of older adult Hebrew speakers. (1) To establish a norm for oral-DDK rate for older adult (aged 65 years and older) Hebrew speakers, and to investigate the possible effect of age and gender on performance rate; and (2) to examine the effects of stimuli (non-word versus real word) on oral-DDK rates. In experiment 1, 88 healthy older Hebrew speakers (60-95 years, 48 females and 40 males) were audio-recorded while performing an oral-DDK task (repetition of /pataka/), and repetition rates (syllables/s) were coded. In experiment 2, the effect of real-word repetition was evaluated. Sixty-eight older Hebrew speakers (aged 66-95 years, 43 females and 25 males) were asked to repeat 'pataka' (non-word) and 'bodeket' (Hebrew real word). Experiment 1: Oral-DDK performance for older adult Hebrew speakers was 5.07 syllables/s (SD = 1.16 syllables/s), across age groups and gender. Comparison of this data with Hebrew norms for younger adults (and equivalent data in English) shows the following gradient of oral-DDK rates: ages 15-45 > 65-74 > 75-86 years. Gender was not a significant factor in our data. Experiment 2: Repetition of real words was faster than that of non-words, by 13.5%. The paper provides normative values for oral-DDK rates for older Hebrew speakers. The data show the large impact of ageing on oro-motor functions. The analysis further indicates that speech and language pathologists should consider separate norms for clients of 65-74 years and those of 75-86 years. Hebrew rates were found to be different from English norms for the oldest group, shedding light on the impact of language on these norms. Finally, the data support using a dual-protocol (real- and non-word repetition) with older adults to improve differential diagnosis of normal and pathological ageing in this task. © 2016 Royal College of Speech and Language Therapists.

Is having similar eye movement patterns during face learning and recognition beneficial for recognition performance? Evidence from hidden Markov modeling.

PubMed

Chuk, Tim; Chan, Antoni B; Hsiao, Janet H

2017-12-01

The hidden Markov model (HMM)-based approach for eye movement analysis is able to reflect individual differences in both spatial and temporal aspects of eye movements. Here we used this approach to understand the relationship between eye movements during face learning and recognition, and its association with recognition performance. We discovered holistic (i.e., mainly looking at the face center) and analytic (i.e., specifically looking at the two eyes in addition to the face center) patterns during both learning and recognition. Although for both learning and recognition, participants who adopted analytic patterns had better recognition performance than those with holistic patterns, a significant positive correlation between the likelihood of participants' patterns being classified as analytic and their recognition performance was only observed during recognition. Significantly more participants adopted holistic patterns during learning than recognition. Interestingly, about 40% of the participants used different patterns between learning and recognition, and among them 90% switched their patterns from holistic at learning to analytic at recognition. In contrast to the scan path theory, which posits that eye movements during learning have to be recapitulated during recognition for the recognition to be successful, participants who used the same or different patterns during learning and recognition did not differ in recognition performance. The similarity between their learning and recognition eye movement patterns also did not correlate with their recognition performance. These findings suggested that perceptuomotor memory elicited by eye movement patterns during learning does not play an important role in recognition. In contrast, the retrieval of diagnostic information for recognition, such as the eyes for face recognition, is a better predictor for recognition performance. Copyright © 2017 Elsevier Ltd. All rights reserved.

Age of acquisition and naming performance in Frisian-Dutch bilingual speakers with dementia

PubMed Central

Veenstra, Wencke S.; Huisman, Mark; Miller, Nick

2014-01-01

Age of acquisition (AoA) of words is a recognised variable affecting language processing in speakers with and without language disorders. For bi- and multilingual speakers their languages can be differentially affected in neurological illness. Study of language loss in bilingual speakers with dementia has been relatively neglected. Objective We investigated whether AoA of words was associated with level of naming impairment in bilingual speakers with probable Alzheimer's dementia within and across their languages. Methods Twenty-six Frisian-Dutch bilinguals with mild to moderate dementia named 90 pictures in each language, employing items with rated AoA and other word variable measures matched across languages. Quantitative (totals correct) and qualitative (error types and (in)appropriate switching) aspects were measured. Results Impaired retrieval occurred in Frisian (Language 1) and Dutch (Language 2), with a significant effect of AoA on naming in both languages. Earlier acquired words were better preserved and retrieved. Performance was identical across languages, but better in Dutch when controlling for covariates. However, participants demonstrated more inappropriate code switching within the Frisian test setting. On qualitative analysis, no differences in overall error distribution were found between languages for early or late acquired words. There existed a significantly higher percentage of semantically than visually-related errors. Conclusion These findings have implications for understanding problems in lexical retrieval among bilingual individuals with dementia and its relation to decline in other cognitive functions which may play a role in inappropriate code switching. We discuss the findings in the light of the close relationship between Frisian and Dutch and the pattern of usage across the life-span. PMID:29213911

The neural correlates of agrammatism: Evidence from aphasic and healthy speakers performing an overt picture description task

PubMed Central

Schönberger, Eva; Heim, Stefan; Meffert, Elisabeth; Pieperhoff, Peter; da Costa Avelar, Patricia; Huber, Walter; Binkofski, Ferdinand; Grande, Marion

2014-01-01

Functional brain imaging studies have improved our knowledge of the neural localization of language functions and the functional reorganization after a lesion. However, the neural correlates of agrammatic symptoms in aphasia remain largely unknown. The present fMRI study examined the neural correlates of morpho-syntactic encoding and agrammatic errors in continuous language production by combining three approaches. First, the neural mechanisms underlying natural morpho-syntactic processing in a picture description task were analyzed in 15 healthy speakers. Second, agrammatic-like speech behavior was induced in the same group of healthy speakers to study the underlying functional processes by limiting the utterance length. In a third approach, five agrammatic participants performed the picture description task to gain insights in the neural correlates of agrammatism and the functional reorganization of language processing after stroke. In all approaches, utterances were analyzed for syntactic completeness, complexity, and morphology. Event-related data analysis was conducted by defining every clause-like unit (CLU) as an event with its onset-time and duration. Agrammatic and correct CLUs were contrasted. Due to the small sample size as well as heterogeneous lesion sizes and sites with lesion foci in the insula lobe, inferior frontal, superior temporal and inferior parietal areas the activation patterns in the agrammatic speakers were analyzed on a single subject level. In the group of healthy speakers, posterior temporal and inferior parietal areas were associated with greater morpho-syntactic demands in complete and complex CLUs. The intentional manipulation of morpho-syntactic structures and the omission of function words were associated with additional inferior frontal activation. Overall, the results revealed that the investigation of the neural correlates of agrammatic language production can be reasonably conducted with an overt language production paradigm. PMID:24711802

The relationship between vocabulary and short-term memory measures in monolingual and bilingual speakers

PubMed Central

Kaushanskaya, Margarita; Blumenfeld, Henrike K.; Marian, Viorica

2012-01-01

Previous studies have indicated that bilingualism may influence the efficiency of lexical access in adults. The goals of this research were (1) to compare bilingual and monolingual adults on their native-language vocabulary performance, and (2) to examine the relationship between short-term memory skills and vocabulary performance in monolinguals and bilinguals. In Experiment 1, English-speaking monolingual adults and simultaneous English–Spanish bilingual adults were administered measures of receptive English vocabulary and of phonological short-term memory. In Experiment 2, monolingual adults were compared to sequential English–Spanish bilinguals, and were administered the same measures as in Experiment 1, as well as a measure of expressive English vocabulary. Analyses revealed comparable levels of performance on the vocabulary and the short-term memory measures in the monolingual and the bilingual groups across both experiments. There was a stronger effect of digit-span in the bilingual group than in the monolingual group, with high-span bilinguals outperforming low-span bilinguals on vocabulary measures. Findings indicate that bilingual speakers may rely on short-term memory resources to support word retrieval in their native language more than monolingual speakers. PMID:22518091

Bilingualism, executive control, and age at diagnosis among people with early-stage Alzheimer's disease in Wales.

PubMed

Clare, Linda; Whitaker, Christopher J; Craik, Fergus I M; Bialystok, Ellen; Martyr, Anthony; Martin-Forbes, Pamela A; Bastable, Alexandra J M; Pye, Kirstie L; Quinn, Catherine; Thomas, Enlli M; Gathercole, Virginia C Mueller; Hindle, John V

2016-09-01

The observation of a bilingual advantage in executive control tasks involving inhibition and management of response conflict suggests that being bilingual might contribute to increased cognitive reserve. In support of this, recent evidence indicates that bilinguals develop Alzheimer's disease (AD) later than monolinguals, and may retain an advantage in performance on executive control tasks. We compared age at the time of receiving an AD diagnosis in bilingual Welsh/English speakers (n = 37) and monolingual English speakers (n = 49), and assessed the performance of bilinguals (n = 24) and monolinguals (n = 49) on a range of executive control tasks. There was a non-significant difference in age at the time of diagnosis, with bilinguals being on average 3 years older than monolinguals, but bilinguals were also significantly more cognitively impaired at the time of diagnosis. There were no significant differences between monolinguals and bilinguals in performance on executive function tests, but bilinguals appeared to show relative strengths in the domain of inhibition and response conflict. Bilingual Welsh/English speakers with AD do not show a clear advantage in executive function over monolingual English speakers, but may retain some benefits in inhibition and management of response conflict. There may be a delay in onset of AD in Welsh/English bilinguals, but if so, it is smaller than that found in some other clinical populations. In this Welsh sample, bilinguals with AD came to the attention of services later than monolinguals, and reasons for this pattern could be explored further. © 2014 The British Psychological Society.

Individual aptitude in Mandarin lexical tone perception predicts effectiveness of high-variability training

PubMed Central

Sadakata, Makiko; McQueen, James M.

2014-01-01

Although the high-variability training method can enhance learning of non-native speech categories, this can depend on individuals’ aptitude. The current study asked how general the effects of perceptual aptitude are by testing whether they occur with training materials spoken by native speakers and whether they depend on the nature of the to-be-learned material. Forty-five native Dutch listeners took part in a 5-day training procedure in which they identified bisyllabic Mandarin pseudowords (e.g., asa) pronounced with different lexical tone combinations. The training materials were presented to different groups of listeners at three levels of variability: low (many repetitions of a limited set of words recorded by a single speaker), medium (fewer repetitions of a more variable set of words recorded by three speakers), and high (similar to medium but with five speakers). Overall, variability did not influence learning performance, but this was due to an interaction with individuals’ perceptual aptitude: increasing variability hindered improvements in performance for low-aptitude perceivers while it helped improvements in performance for high-aptitude perceivers. These results show that the previously observed interaction between individuals’ aptitude and effects of degree of variability extends to natural tokens of Mandarin speech. This interaction was not found, however, in a closely matched study in which native Dutch listeners were trained on the Japanese geminate/singleton consonant contrast. This may indicate that the effectiveness of high-variability training depends not only on individuals’ aptitude in speech perception but also on the nature of the categories being acquired. PMID:25505434

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.

24-month-olds’ sensitivity to the prior inaccuracy of the source: Possible mechanisms

PubMed Central

Koenig, Melissa A.; Woodward, Amanda L.

2013-01-01

Three studies examined 24-month-olds’ sensitivity to the prior accuracy of the source and the way in which young children modify their word learning from inaccurate sources. In Experiments 1A, 2 and 3, toddlers interacted with an accurate or inaccurate speaker who trained and tested children's comprehension of a new word-object link. In Experiment 1, children performed less systematically in response to an inaccurate than to the accurate source. In Experiments 2 and 3, after toddlers’ comprehension of the new word-object links was tested by the original source, a second speaker requested the target objects. In Experiment 2, children responded randomly in response to the second speaker's requests when novel words were previously presented by an inaccurate source. In Experiment 3, toddlers responded randomly in response to both speakers in the inaccurate condition when their memory for words was taxed by a brief delay period. Taken together, these findings suggest that toddlers attend to accuracy information, treat inaccuracy as a feature of a particular individual and that the word-object representations formed as a result may be fragile and short-lived. Findings are discussed in terms of possible mechanisms by which children adjust their word-learning from problematic speakers. PMID:20604604

The Use of Epistemic Markers as a Means of Hedging and Boosting in the Discourse of L1 and L2 Speakers of Modern Greek: A Corpus-Based Study in Informal Letter-Writing

ERIC Educational Resources Information Center

Efstathiadi, Lia

2010-01-01

The paper investigates the semantic area of Epistemic Modality in Modern Greek, by means of a corpus-based research. A comparative, quantitative study was performed between written corpora (informal letter-writing) of non-native informants with various language backgrounds and Greek native speakers. A number of epistemic markers were selected for…