Speech Of Stutterers Research Articles

TranStutter: A Convolution-Free Transformer-Based Deep Learning Method to Classify Stuttered Speech Using 2D Mel-Spectrogram Visualization and Attention-Based Feature Representation.

Stuttering, a prevalent neurodevelopmental disorder, profoundly affects fluent speech, causing involuntary interruptions and recurrent sound patterns. This study addresses the critical need for the accurate classification of stuttering types. The researchers introduce "TranStutter", a pioneering Convolution-free Transformer-based DL model, designed to excel in speech disfluency classification. Unlike conventional methods, TranStutter leverages Multi-Head Self-Attention and Positional Encoding to capture intricate temporal patterns, yielding superior accuracy. In this study, the researchers employed two benchmark datasets: the Stuttering Events in Podcasts Dataset (SEP-28k) and the FluencyBank Interview Subset. SEP-28k comprises 28,177 audio clips from podcasts, meticulously annotated into distinct dysfluent and non-dysfluent labels, including Block (BL), Prolongation (PR), Sound Repetition (SR), Word Repetition (WR), and Interjection (IJ). The FluencyBank subset encompasses 4144 audio clips from 32 People Who Stutter (PWS), providing a diverse set of speech samples. TranStutter's performance was assessed rigorously. On SEP-28k, the model achieved an impressive accuracy of 88.1%. Furthermore, on the FluencyBank dataset, TranStutter demonstrated its efficacy with an accuracy of 80.6%. These results highlight TranStutter's significant potential in revolutionizing the diagnosis and treatment of stuttering, thereby contributing to the evolving landscape of speech pathology and neurodevelopmental research. The innovative integration of Multi-Head Self-Attention and Positional Encoding distinguishes TranStutter, enabling it to discern nuanced disfluencies with unparalleled precision. This novel approach represents a substantial leap forward in the field of speech pathology, promising more accurate diagnostics and targeted interventions for individuals with stuttering disorders.

Comparative analysis of various feature extraction techniques for classification of speech disfluencies

Speech plays a vital role in communication, from expressing oneself, to utilizing speech-based platforms, speech is a necessity. Any disruption in speech is referred to as disfluency, and can impact one's quality of life. This paper presents an experimental study on various techniques for the detection and classification of speech disfluencies. Six different types of disfluencies are examined in this paper, namely Interjection, Sound Repetition, Word Repetition, Phrase Repetition, Revision and Prolongation (6 classes). However, this paper also goes a step further by including the clean speech signals as an added class alongside the six disfluencies, thereby making this work more robust with 7 classes. Various machine learning approaches have been investigated on the University College London Archive of Stuttered Speech (UCLASS) dataset; a standard disfluency dataset generated by University College London (UCL). Five different feature extraction techniques viz. Mel Frequency Cepstral Coefficients (MFCC), Linear Predictive Cepstral Coefficients (LPCC), Gammatone Frequency Cepstral Coefficients (GFCC), Mel-filterbank energy features, and Spectrograms have been used. Comparative analysis of various classifiers shows that MFCC, GFCC, and Spectrograms achieved greater than 90% accuracy on both 6 and 7 classes with the kNN classifier. As a future scope to this study, the authors aim to focus on tackling the challenges of detecting multiple disfluencies present simultaneously in a speech sample.

Acoustic Analysis of Formant Frequency Variation in Tamil Stuttered Speech

Acoustic Analysis of Formant Frequency Variation in Tamil Stuttered Speech

Automatic Speech Recognition with Stuttering Speech Removal using Long Short-Term Memory (LSTM)

Stuttering or Stammering is a speech defect within which sounds, syllables, or words are rehashed or delayed, disrupting the traditional flow of speech. Stuttering can make it hard to speak with other individuals, which regularly have an effect on an individual's quality of life. Automatic Speech Recognition (ASR) system is a technology that converts audio speech signal into corresponding text. Presently ASR systems play a major role in controlling or providing inputs to the various applications. Such an ASR system and Machine Translation Application suffers a lot due to stuttering (speech dysfluency). Dysfluencies will affect the phrase consciousness accuracy of an ASR, with the aid of increasing word addition, substitution and dismissal rates. In this work we focused on detecting and removing the prolongation, silent pauses and repetition to generate proper text sequence for the given stuttered speech signal. The stuttered speech recognition consists of two stages namely classification using LSTM and testing in ASR. The major phases of classification system are Re-sampling, Segmentation, Pre-Emphasis, Epoch Extraction and Classification. The current work is carried out in UCLASS Stuttering dataset using MATLAB with 4% to 6% increase in accuracy when compare with ANN and SVM.

Vocal Tone Analysis for Identification of Stuttering Levels based on Tamil Syllable

Speech is the most unique feature of humans and it is the basic mode of verbal communication. Among all, a few people face hurdles in producing normal speech because of various types of speech disorders. Stuttering is one of the disorder types mainly characterized by repetition of syllables or words and involuntary interruption during the speech. One of the unsolved problems in the realm of fluency disorder is the level identification, based upon the patient’s utterance before and after the speech therapy. The main objective of the paper is to perform analysis of vocal tone to identify the major differences between a normal, moderate and severely stuttered speech, particularly for the Tamil spoken language. The stutter speech vocal tone analysis involves envelope detection based on Hilbert transform has been computed from the input of normal and stuttered speech waves in which by applying normalization to the spectrum and cepstrum of the obtained signal considering only Tamil syllable as input. The experimental outcomes are given as subjective evaluation in three categories of speech signals which results people affected by severe stuttering having low vocal tone than moderate and normal stuttering speech.

Pausas e hesitações na fala de adultos com e sem gagueira

Introdução: Gagueira é um distúrbio do neurodesenvolvimento e sua principal manifestação é o excesso de disfluências gagas. Disfluências como as pausas ocorrerem na fala de pessoas com e sem gagueira. Objetivo: Analisar e comparar as pausas e as pausas hesitativas na fala de adultos com gagueira e de adultos fluentes. Método: Participaram 30 adultos, divididos em: Grupo Pesquisa (GP), composto por 15 adultos com diagnóstico de gagueira e Grupo Controle (GC), composto por 15 adultos fluentes. Os procedimentos foram: avaliação da fluência, análise da amostra de fala espontânea e caracterização das tipologias das disfluências, análise das pausas e das pausas hesitativas, a qual englobou: frequência, duração e posição nas frases e aplicação do Instrumento de Gravidade da Gagueira. Resultados: Os adultos com gagueira apresentaram maior duração e frequência das pausas do que os adultos fluentes. Os grupos foram similares quanto à duração e frequência das pausas hesitativas. Na comparação entre os grupos em relação às posições das pausas nas frases, houve diferença significante para a posição inicial e medial. Não foram observadas pausas em posição final para ambos os grupos. Entretanto, os adultos fluentes apresentaram maior frequência das pausas hesitativas em posição final quando comparados aos adultos com gagueira. Conclusão: A análise quantitativa das pausas mostrou que existem diferenças relevantes entre os adultos com e sem gagueira, que propiciarão o diagnóstico e terapia mais adequada.

Analysis of Fundamental Frequency, Jitter and Shimmer in Stuttered and Non-Stuttered Speech of Marathi Language

Stuttering is one of the complex speech disorder which lead speech unintelligible to other and ASR system. In this paper Fundamental frequency (f0), vocal jitter and shimmer were measures the numerical words of 17 Stuttering (PWS) (i.e. 13 Male and 4 female) and 25 Non-Stutterers (NS) (i.e. 15 male 10 female) belongs to the Marathi Language. Jitter and shimmer are measurements of the cycle - to - cycle variations of F0 frequency and amplitude, respectively, which were largely used to describe pathological voice quality. The experiment performed with Pasrelmouth Praat Scripts in Python. This is the first attempt for the Marathi Language. Shimmer were shows the negligible difference between PWS and NS speech samples.

RECEIVER OPERATING CHARACTERISTICS MEASURE FOR THE RECOGNITION OF STUTTERING DYSFLUENCIES USING LINE SPECTRAL FREQUENCIES

Stuttering is a motor-speech disorder, having common features with other motor control disorders such as dystonia, Parkinson’s disease and Tourette’s syndrome. Stuttering results from complex interactions between factors such as motor, language, emotional and genetic. This study used Line Spectral Frequency (LSF) for the feature extraction, while using three classifiers for the identification purpose, Multilayer Perceptron (MLP), Recurrent Neural Network (RNN) and Radial Basis Function (RBF). The UCLASS (University College London Archive of Stuttered Speech) release 1 was used as database in this research. These recordings were from people of ages 12y11m to 19y5m, who were referred to clinics in London for assessment of their stuttering. The performance metrics used for interpreting the results are sensitivity, accuracy, precision and misclassification rate. Only M1 and M2 had below 100% sensitivity for RBF. The sensitivity of M1 was found to be between 40 & 60%, therefore categorized as moderate, while that of M2 falls between 60 & 80%, classed as substantial. Overall, RBF outperforms the two other classifiers, MLP and RNN for all the performance metrics considered.

LPC AND ITS DERIVATIVES FOR STUTTERED SPEECH RECOGNITION

Stuttering or stammering is disruptions in the normal flow of speech by dysfluencies, which can be repetitions or prolongations of phoneme or syllable. Stuttering cannot be permanently cured, though it may go into remission or stutterers can learn to shape their speech into fluent speech with an appropriate speech pathology treatment. Linear Prediction Coefficient (LPC), Linear Prediction Cepstral Coefficient (LPCC) and Line Spectral Frequency (LSF) were used for the feature extraction, while Multilayer Perceptron (MLP) was used as the classifier. The samples used were obtained from UCLASS (University College London Archive of Stuttered Speech) release 1. The LPCC-MLP system had the highest overall sensitivity, precision and the lowest overall misclassification rate. LPCC-MLP system had challenges with F3, the sensitivity of the system to F3 was negligible, similarly, the precision was moderate and the misclassification rate was negligible, but above 10%.

Gaussian Mixture Model Based Classification of Stuttering Dysfluencies

AbstractThe classification of dysfluencies is one of the important steps in objective measurement of stuttering disorder. In this work, the focus is on investigating the applicability of automatic speaker recognition (ASR) method for stuttering dysfluency recognition. The system designed for this particular task relies on the Gaussian mixture model (GMM), which is the most widely used probabilistic modeling technique in ASR. The GMM parameters are estimated from Mel frequency cepstral coefficients (MFCCs). This statistical speaker-modeling technique represents the fundamental characteristic sounds of speech signal. Using this model, we build a dysfluency recognizer that is capable of recognizing dysfluencies irrespective of a person as well as what is being said. The performance of the system is evaluated for different types of dysfluencies such as syllable repetition, word repetition, prolongation, and interjection using speech samples from the University College London Archive of Stuttered Speech (UCLASS).

Second formant transition duration in fluent speech of person who stutter

Abstract Introduction: results of researches on acoustic and motor aspects of speech of persons who stutter have shown that the perceptually fluent speech of stutterers differs from the speech of nonstutterers. One of these encoding and processing aspects of speech that measured in different studies is vowel formant transition features. Because variations in formant structure along the temporal and frequency domains reflect articulatory dynamics especially of the tongue, in study of motor speech ability of persons who stutter, this feature can be used. The purpose of this study is to compare the formant transition duration in fluent speech of those who stutter and those who do not. Materials and methods: In this descriptive-analytic study, 20 PWS and 20 normal counterparts, were asked to read 9 speech samples that insert in a carrier phrase. The responses were recorded and the duration were measured in milisecond by Praat software. Results: The results of the study showed that the average of formant transiotion duration in PWS was lower than that of normal subjects however this difference did not reach statistical significance. Conclusion: according to the result of this study motor speech processing in PWS is different with normal subject and the speed of articulator movement in PWS is faster than PWNS. Key words: stuttering, second formant transition, Praat software

Laryngeal movements in stutterers

Background: The etiology of stuttering is a puzzle. Abnormal laryngeal movements have been assumed to be a cause of stuttering by many researchers. We aimed at comparing the laryngeal functions of stutterers using electroglottogram (EGG) and vocal tract functioning using formant frequency analysis. Materials and Methods: We compared the acoustic and electroglottographic parameters in the phonation of stutterers between the age range of 15-25 years and normal subjects matched for age and sex. Results and Discussion: All the electroglottographic parameters of stutterers differed from that of normal speaking subjects which is indicative of difficulty in adjustment of the laryngeal gestures for speech in stutterers. There was no significant difference between the stutterers and non-stutterers in terms of formant frequencies. Similar formant frequencies in stutterers and normal speakers and abnormal electroglottographic parameters are suggestive of abnormal laryngeal movements and normal vocal tract functioning in stutterers.

Comparison of speech parameterization techniques for the classification of speech disfluencies

Stuttering assessment through the manual classification of speech disfluencies is subjective, inconsistent, time-consuming, and prone to error. The aim of this paper is to compare the effectiveness of the 3 speech feature extraction methods, mel-frequency cepstral coefficients, linear predictive coding (LPC)-based cepstral parameters, and perceptual linear predictive (PLP) analysis, for classifying 2 types of speech disfluencies, repetition and prolongation, from recorded disfluent speech samples. Three different classifiers, the k-nearest neighbor classifier, linear discriminant analysis-based classifier, and support vector machine, are employed for the classification of speech disfluencies. Speech samples are taken from the University College London Archive of Stuttered Speech and stuttered events are identified through manual segmentation. A 10-fold cross-validation method is used for testing the reliability of the classifier results. The effect of the 2 parameters (LPC order and frame length) in the LPC- and PLP-based methods on the classification results is also investigated. The experimental results reveal that the proposed method can be used to help speech language pathologists in classifying speech disfluencies.

Classification of Speech Dysfluencies Using LPC Based Parameterization Techniques

The goal of this paper is to discuss and compare three feature extraction methods: Linear Predictive Coefficients (LPC), Linear Prediction Cepstral Coefficients (LPCC) and Weighted Linear Prediction Cepstral Coefficients (WLPCC) for recognizing the stuttered events. Speech samples from the University College London Archive of Stuttered Speech (UCLASS) were used for our analysis. The stuttered events were identified through manual segmentation and were used for feature extraction. Two simple classifiers namely, k-nearest neighbour (kNN) and Linear Discriminant Analysis (LDA) were employed for speech dysfluencies classification. Conventional validation method was used for testing the reliability of the classifier results. The study on the effect of different frame length, percentage of overlapping, value of ã in a first order pre-emphasizer and different order p were discussed. The speech dysfluencies classification accuracy was found to be improved by applying statistical normalization before feature extraction. The experimental investigation elucidated LPC, LPCC and WLPCC features can be used for identifying the stuttered events and WLPCC features slightly outperforms LPCC features and LPC features.

SOONER SPEAKING THAN SILENT, SOONER SILENT THAN MUTE: SOVIET DEAF THEATRE AND PANTOMIME AFTER STALIN

A television documentary on speech therapy is visible on the screen. A logopedist (speech-defect expert) coaches a young man to overcome his stutter through hypnosis. “You will speak loudly and clearly, freely and easily, unafraid of your voice and your speech,” she instructs. The boy hesitates but finally musters the words: “I can speak.” Thus Andrei Tarkovsky beginsZerkalo[Mirror], his poetic film about personal memory and cultural trauma (conceived in 1964 and completed in 1974).3The symbolism of this scene was impossible for Tarkovsky's Soviet intelligentsia audience to miss. The stutterer coming to speech allegorized the artist coming to free expression in Russia after Stalin, struggling to adapt to alternating intervals of liberating “thaw” and oppressive “freeze,” fluency and silence, in the period of de-Stalinization that Nikita Khrushchev's secret speech at the 20th Party Congress of 1956 set into motion. The crisis of the solo stutterer's speech in the film stood in for the larger emerging crisis of how to represent socialist reality, a world that once had been captured solely by socialist realism—that is, until Khrushchev deprived Stalinism of its status as real socialism and thus invalidated the basis of socialist realism.

The University College London Archive of Stuttered Speech (UCLASS)

The University College London Archive of Stuttered Speech (UCLASS)

The University College London Archive of Stuttered Speech (UCLASS)

PurposeThis research note gives details of 2 releases of audio recordings available from speakers who stutter that can be accessed on the Web.MethodMost of the recordings are from school-age children. These are available on the University College London Archive of Stuttered Speech (UCLASS) Web site, and information is provided about how to access the site. A description of the recordings and background information about the speakers who contributed recordings to UCLASS Releases One and Two are given. The sample types available in Release One are monologs. Release Two has monologs, readings, and conversations. Three optional software formats that can be used with the archive are described (although processing the archive is not restricted to these formats). Some perceptual assessment of the quality of each recording is given. An assessment of the strengths and limitations of the recording archive is presented. Finally, some past applications and future research possibilities using the recordings are discussed.

Identification of Children’s Stuttered and Nonstuttered Speech by Highly Experienced Judges: Binary Judgments and Comparisons With Disfluency-Types Definitions

The purposes of this study were (a) to determine whether highly experienced clinicians and researchers agreed with each other in judging the presence or absence of stuttering in the speech of children who stutter and (b) to determine how those binary stuttered/nonstuttered judgments related to categorizations of the same speech based on disfluency-types descriptions of stuttering. Eleven highly experienced judges made binary judgments of the presence or absence of stuttering for 600 audiovisually recorded 5-s speech samples from twenty 2- to 8-year-old children who stuttered. These judgments were compared with each other and with disfluency-types judgments in multiple interval-by-interval assessments and by using multiple definitions of agreement. Interjudge agreement for the highly experienced judges in the binary stuttered/nonstuttered task varied from 39.0% to 89.1%, depending on methods and definitions used. Congruence between binary judgments and categorizations based on disfluency types also varied depending on methods and definitions, from 21.6% to 100%. Agreement among highly experienced judges, and congruence between their binary judgments of stuttering and categorizations based on disfluency types, were relatively high using some definitions and very low using others. These results suggest the use of measurement methods other than those based on disfluency types for quantifying or describing children's stuttering. They also suggest both the need for, and potential methods for, training to increase judges' accuracy and agreement in identifying children's stuttering.

Neurocognitive mechanisms of disturbances of readiness for speech in stutterers

Neurocognitive mechanisms of disturbances of readiness for speech in stutterers

Event-Related Potentials Distinguish Fluent and Stuttered Speech

ABSTRACT Background. This study aimed to find the best possible approach to neurotherapy for stuttering. Method. Five right-handed Dysfluent Speakers and five right-handed Fluent Speakers were compared before dysfluent and fluent speech onset with electrical event related potentials. EEG electrodes were at inferior frontal, precentral, and temporoparietal locations on each hemiscalp. Participants processed two words displayed consecutively at center screen, the first or second of which was to be uttered aloud according to the subsequent command digit being 1 or 2. Results. The Fluent Speakers manifested significant left hemisphere contingent negative variations (CNVs) prior to the words and the contingency stimulus. The Dysfluent Speakers presented overall smaller CNVs that were more marked over the right hemisphere than left. This pattern was observed before both their stuttered and fluent words, with the former differing significantly from the fluent speakers hemispheric CNV pattern. Conclusion. These r...