Pathological Speech Research Articles

S transform feature for pathological speech

S transform feature for pathological speech

An insight to the automatic categorization of speakers according to sex and its application to the detection of voice pathologies: A comparative study

La hipotesis que se establece en este estudio es que una categorizacion automatica de hablantes de acuerdo con su sexo mejora el rendimiento de un detector automatico de patologias de voz. Esto se basa en hallazgos que demuestran diferencias perceptuales, acusticas y anatomicas en voces masculinas y femeninas. En particular, este trabajo persigue dos objetivos: 1) disenar un sistema que discrimine automaticamente el sexo de hablantes utilizando habla normal y patologica, 2) estudiar la influencia que este detector de sexo tiene sobre el acierto de un posterior detector de patologias de voz. La parametrizacion del detector automatico de sexo esta basada en MFCC aplicados sobre senales de voz; y MFCC aplicados a formas de onda glotal, junto a parametros que modelan el tracto vocal. Las formas de onda glotal se extraen de la voz a traves de un filtrado inverso iterativo en celosia. En cuanto al detector de patologias de voz, una parametrizacion MFCC se aplica sobre senales de voz. La clasificacion, tanto en los detectores de sexo como de patologia, se lleva a cabo con tecnicas del estado del arte basadas en modelos de base universal. Los experimentos se realizan sobre la base de datos Saarbrucken, empleando la fonacion sostenida de la vocal /a/. Los resultados indican que el sexo del hablante puede ser discriminado automaticamente utilizando habla normal y patologica, obteniendo una precision de hasta un 95%. Por otra parte, al incluir informacion a-priori sobre el sexo del hablante se produce una mejora en el rendimiento absoluto de alrededor de 2% en EER, en tareas de deteccion de patologia.

Speech Databases of Typical Children and Children with SLI

The extent of research on children’s speech in general and on disordered speech specifically is very limited. In this article, we describe the process of creating databases of children’s speech and the possibilities for using such databases, which have been created by the LANNA research group in the Faculty of Electrical Engineering at Czech Technical University in Prague. These databases have been principally compiled for medical research but also for use in other areas, such as linguistics. Two databases were recorded: one for healthy children’s speech (recorded in kindergarten and in the first level of elementary school) and the other for pathological speech of children with a Specific Language Impairment (recorded at a surgery of speech and language therapists and at the hospital). Both databases were sub-divided according to specific demands of medical research. Their utilization can be exoteric, specifically for linguistic research and pedagogical use as well as for studies of speech-signal processing.

Empirically Estimable Classification Bounds Based on a Nonparametric Divergence Measure.

Information divergence functions play a critical role in statistics and information theory. In this paper we show that a non-parametric f-divergence measure can be used to provide improved bounds on the minimum binary classification probability of error for the case when the training and test data are drawn from the same distribution and for the case where there exists some mismatch between training and test distributions. We confirm the theoretical results by designing feature selection algorithms using the criteria from these bounds and by evaluating the algorithms on a series of pathological speech classification tasks.

The Effect of Narrow-Band Transmission on Recognition of Paralinguistic Information From Human Vocalizations

Practically, no knowledge exists on the effects of speech coding and recognition for narrow-band transmission of speech signals within certain frequency ranges especially in relation to the recognition of paralinguistic cues in speech. We thus investigated the impact of narrow-band standard speech coders on the machine-based classification of affective vocalizations and clinical vocal recordings. In addition, we analyzed the effect of speech low-pass filtering by a set of different cut-off frequencies, either chosen as static values in the 0.5–5-kHz range or given dynamically by different upper limits from the first five speech formants (F1–F5). Speech coding and recognition were tested, first, according to short-term speaker states by using affective vocalizations as given by the Geneva Multimodal Emotion Portrayals. Second, in relation to long-term speaker traits, we tested vocal recording from clinical populations involving speech impairments as found in the Child Pathological Speech Database. We employ a large acoustic feature space derived from the Interspeech Computational Paralinguistics Challenge. Besides analysis of the sheer corruption outcome, we analyzed the potential of matched and multicondition training as opposed to miss-matched condition. In the results, first, multicondition and matched-condition training significantly increase performances as opposed to mismatched condition. Second, downgrades in classification accuracy occur, however, only at comparably severe levels of low-pass filtering. The downgrades especially appear for multi-categorical rather than for binary decisions. These can be dealt with reasonably by the alluded strategies.

Algorithm for Jitter and Shimmer Measurement in Pathologic Voices

An algorithm to measure the jitter (jitta, jitter, rap and ppq5) and shimmer (ShdB, Shim, apq3 and apq5) parameters was developed. These parameters can be used in an intelligent system to diagnose voice pathologies. The algorithm is sensitive to the fundamental frequency and determines the parameters based on maximum and minimum functions applied to each glottal period of the signal. The algorithm was previously tested with synthesized speech signals with very high accuracy, but several improvements had to be included for the analysis of pathologic voices. A comparison using real, control and pathologic voices was made between the developed algorithm and other software program to evaluate the consistency of measures between different algorithms. Based on this comparison it can be said that the algorithm improved the accuracy with synthetic speech signal and showed consistent measures for pathologic speech signal.

Robust and complex approach of pathological speech signal analysis

This paper presents a study of the approaches in the state-of-the-art in the field of pathological speech signal analysis with a special focus on parametrization techniques. It provides a description of 92 speech features where some of them are already widely used in this field of science and some of them have not been tried yet (they come from different areas of speech signal processing like speech recognition or coding). As an original contribution, this work introduces 36 completely new pathological voice measures based on modulation spectra, inferior colliculus coefficients, bicepstrum, sample and approximate entropy and empirical mode decomposition. The significance of these features was tested on 3 (English, Spanish and Czech) pathological voice databases with respect to classification accuracy, sensitivity and specificity. To our best knowledge the introduced approach based on complex feature extraction and robust testing outperformed all works that have been published already in this field. The results (accuracy, sensitivity and specificity equal to 100.0±0.0%) are discussable in the case of Massachusetts Eye and Ear Infirmary (MEEI) database because of its limitation related to a length of sustained vowels, however in the case of Príncipe de Asturias (PdA) Hospital in Alcalá de Henares of Madrid database we made improvements in classification accuracy (82.1±3.3%) and specificity (83.8±5.1%) when considering a single-classifier approach. Hopefully, large improvements may be achieved in the case of Czech Parkinsonian Speech Database (PARCZ), which are discussed in this work as well. All the features introduced in this work were identified by Mann–Whitney U test as significant (p<0.05) when processing at least one of the mentioned databases. The largest discriminative power from these proposed features has a cepstral peak prominence extracted from the first intrinsic mode function (p=6.9443×10−32) which means, that among all newly designed features those that quantify especially hoarseness or breathiness are good candidates for pathological speech identification. The paper also mentions some ideas for the future work in the field of pathological speech signal analysis that can be valuable especially under the clinical point of view.

The Separation of Multi-Class Pathological Speech Signals Related to Vocal Cords Disorders Using Adaptation Wavelet Transform Based on Lifting Scheme

Abstract. Achievement to a non-invasive method to properly diagnose the diseases is a significant subject in domain of speech processing. The aim of this paper is to apply non-invasive methods to do diagnosis, provide preventive strategies and plan for treatment aids and treatment. Regarding the speech disorders based on wavelet features of common wavelet although have relatively proper performance, it is expected that design optimizations based on the features of speech signal and classifier performance lead to improvement of results. To design the adaptive wavelet transform, the parameters of lifting scheme generating bi-orthogonal wavelet are initially applied and then they are optimized through genetic algorithm and classification performance of Support Vector Machine. The result separation of normal and pathological signals provides an accuracy of 100 percent. Also, the result of two-class and three-class separation of six disorders using adaptation wavelet based on lifting scheme which indicative the advantage of suggested method with other mother wavelet.

Functional imaging of physiological and pathological speech production

Numerous neurological patients suffer from speech and language disorders but the underlying pathomechanisms are not well understood. Imaging studies on speech production disorders lag behind aphasiological research on speech perception, probably due to worries concerning movement artifacts. Meanwhile, modern neuroimaging techniques allow investigation of these processes. This article summarizes the insights from neuroimaging on physiological speech production and also on the pathomechanisms underlying Parkinson's disease and developmental stuttering.

A Pathological Voices Assessment Using Classification

The diagnosing of pathological voice may be a tedious topic and it receives abundant attention. There are several diseases that adversely have an effect on our human speech (voice). The doctor will use only the equipments for detection of pathological voice. However, it is invasive and needs a skilled analysis of diverse human speech signal parameters. Automatic voice analysis for pathological speech has its own blessings, like 1)its quantitative and non-invasive nature. 2) permitting the identification and observance of vocal system diseases . Within the pathological voice classification techniques gathered by the voice of a patient, the goal is to discriminate whether the given voice is normal or pathological. From the speech Mel- Frequency Cepstral Coefficients (MFCC) has been extracted from the voice information and classified into two categories. However, the accuracy of the earlier classification methodology may need additional improvement. In my project work, Support Vector Machine (SVM) classifier is used for pathological voice classification with non-invasive nature to diagnose and analyze the voice of the patient.

A Pathological Voices Assessment Using Classification

The diagnosing of pathological voice may be a tedious topic and it receives abundant attention. There are several diseases that adversely have an effect on our human speech (voice). The doctor will use only the equipments for detection of pathological voice. However, it is invasive and needs an skilled analysis of diverse human speech signal parameters. Automatic voice analysis for pathological speech has its own blessings, like 1) its quantitative and non-invasive nature. 2) permitting the identification and observance of vocal system diseases. Within the pathological voice classification techniques gathered by the voice of a patient, the goal is to discriminate whether the given voice is normal or pathological. From the speech Mel-Frequency Cepstral Coefficients (MFCC) has been extracted from the voice information and classified into two categories. However, the accuracy of the earlier classification methodology may need additional improvement. In my project work, Support Vector Machine (SVM) classifier is used for pathological voice classification with non-invasive nature to diagnose and analyze the voice of the patient.

Modeling Pathological Speech Perception From Data With Similarity Labels.

The current state of the art in judging pathological speech intelligibility is subjective assessment performed by trained speech pathologists (SLP). These tests, however, are inconsistent, costly and, oftentimes suffer from poor intra- and inter-judge reliability. As such, consistent, reliable, and perceptually-relevant objective evaluations of pathological speech are critical. Here, we propose a data-driven approach to this problem. We propose new cost functions for examining data from a series of experiments, whereby we ask certified SLPs to rate pathological speech along the perceptual dimensions that contribute to decreased intelligibility. We consider qualitative feedback from SLPs in the form of comparisons similar to statements "Is Speaker A's rhythm more similar to Speaker B or Speaker C?" Data of this form is common in behavioral research, but is different from the traditional data structures expected in supervised (data matrix + class labels) or unsupervised (data matrix) machine learning. The proposed method identifies relevant acoustic features that correlate with the ordinal data collected during the experiment. Using these features, we show that we are able to develop objective measures of the speech signal degradation that correlate well with SLP responses.

Automatic system to detect the type of voice pathology

Acoustic analysis is a noninvasive technique based on the digital processing of the speech signal. Acoustic analysis based techniques are an effective tool to support vocal and voice disease screening and especially in their early detection and diagnosis. Modern lifestyle has increased the risk of pathological voice problems. This work focuses on a robust, rapid and accurate system for automatic detection of normal and pathological speech and also to detect the type of pathology. This system employs non-invasive, inexpensive and fully automated measures of vocal tract characteristics and excitation information. Mel-frequency cepstral coefficients and linear prediction cepstral coefficients are used as acoustic features. The system uses Gaussian mixture model and hidden Markov model classifiers. Cerebral palsy, dysarthria, hearing impairments, laryngectomy, mental retardation, left side paralysis, quadriparesis, stammering, stroke, tumour in vocal tract are the types of pathologies considered in our experiments. From the experimental results, it is observed that to classify normal and pathological voice hidden Markov model with mel frequency cepstral coefficients with delta and acceleration coefficients is giving 94.44% efficiency. Likewise to identify the type of pathology Gaussian mixture model with mel frequency cepstral coefficients with delta and acceleration coefficients is giving 95.74% efficiency.

Automatic intelligibility classification of sentence-level pathological speech

Pathological speech usually refers to the condition of speech distortion resulting from atypicalities in voice and/or in the articulatory mechanisms owing to disease, illness or other physical or biological insult to the production system. Although automatic evaluation of speech intelligibility and quality could come in handy in these scenarios to assist experts in diagnosis and treatment design, the many sources and types of variability often make it a very challenging computational processing problem. In this work we propose novel sentence-level features to capture abnormal variation in the prosodic, voice quality and pronunciation aspects in pathological speech. In addition, we propose a post-classification posterior smoothing scheme which refines the posterior of a test sample based on the posteriors of other test samples. Finally, we perform feature-level fusions and subsystem decision fusion for arriving at a final intelligibility decision. The performances are tested on two pathological speech datasets, the NKI CCRT Speech Corpus (advanced head and neck cancer) and the TORGO database (cerebral palsy or amyotrophic lateral sclerosis), by evaluating classification accuracy without overlapping subjects’ data among training and test partitions. Results show that the feature sets of each of the voice quality subsystem, prosodic subsystem, and pronunciation subsystem, offer significant discriminating power for binary intelligibility classification. We observe that the proposed posterior smoothing in the acoustic space can further reduce classification errors. The smoothed posterior score fusion of subsystems shows the best classification performance (73.5% for unweighted, and 72.8% for weighted, average recalls of the binary classes).

Feature divergence of pathological speech

Many state of the art speaker verification systems are implemented by modeling the probability distribution of a feature set using Gaussian mixture models. In these systems, a decision is made by comparing a likelihood of an observation using both a Gaussian mixture model corresponding to an individual, and a Gaussian mixture model universal back ground model. In this study we propose to use a similar framework to instead characterize the divergence of the feature set distribution between healthy and pathological speech. We accomplish this by determining the difference between a universal background model trained on healthy speech and model of an individual's pathological speech. There are several known methods to evaluate the difference between two probability distributions, one example being the Kullback-Leibler divergence. By building a universal background model using healthy speech, we hope to capture the expected distribution of our feature space. Then by computing a difference between a dysathric individual's feature distribution, and the universal background model, we can determine the features that are most likely to capture the effects of a specific motor speech disorder.

Signal Processing and Analysis of Pathological Speech Using Artificial Intelligence and Learning Systems Methods

In this paper, selected results are presented of research which is carried on for over a decade and covers valuation of chosen signal processing methods suitable to analyze and valuate pathological speech. This valuation is necessary during solving many medical diagnostics problems and when planning therapy and rehabilitation of certain types of diseases. All presented examples are used in clinical practice in the area of dentistry, dental surgery, otolaryngology and most of all, in phoniatrics and speech correction.

Towards A Clinical Tool For Automatic Intelligibility Assessment.

An important, yet under-explored, problem in speech processing is the automatic assessment of intelligibility for pathological speech. In practice, intelligibility assessment is often done through subjective tests administered by speech pathologists; however research has shown that these tests are inconsistent, costly, and exhibit poor reliability. Although some automatic methods for intelligibility assessment for telecommunications exist, research specific to pathological speech has been limited. Here, we propose an algorithm that captures important multi-scale perceptual cues shown to correlate well with intelligibility. Nonlinear classifiers are trained at each time scale and a final intelligibility decision is made using ensemble learning methods from machine learning. Preliminary results indicate a marked improvement in intelligibility assessment over published baseline results.

Nonlinearities in block-type reduced-order vocal fold models with asymmetric tissue properties

Modeling the vocal fold structure as a reduced-order system is an attractive approach for exploring the dynamics of both normal and pathological phonation. This approach has been used ubiquitously in scientific speech investigations due to its relatively high order of accuracy and low computational cost. In addition, good agreement can also be found between model and clinical data. In the case of pathological speech complex vocal fold dynamics may exist, exhibiting phenomenon such as bifurcation and chaos. The ability to capture these features in reduced-order vocal fold models is a much celebrated feature. However, the question has arisen whether these nonlinearities arise due to the physics, or if they are merely an artifact of the model and its sensitivity to initial and boundary conditions. We explore the sensitivity of commonly-employed reduced-order vocal fold models to both contact mechanics, and the geometric prescription of the vocal fold model. Nonlinearities arising from asymmetric vocal fold tensioning are investigated. Nonlinearity in the vocal fold dynamics is identified by determining the predictive capability of linear and nonlinear Volterra-Weiner-Korenberg series. Nonlinearities in the vocal fold oscillations are shown to be highly dependent upon model formulation and implementation, as opposed to physical features of speech.

Pathological speech signal analysis and classification using empirical mode decomposition

Automated classification of normal and pathological speech signals can provide an objective and accurate mechanism for pathological speech diagnosis, and is an active area of research. A large part of this research is based on analysis of acoustic measures extracted from sustained vowels. However, sustained vowels do not reflect real-world attributes of voice as effectively as continuous speech, which can take into account important attributes of speech such as rapid voice onset and termination, changes in voice frequency and amplitude, and sudden discontinuities in speech. This paper presents a methodology based on empirical mode decomposition (EMD) for classification of continuous normal and pathological speech signals obtained from a well-known database. EMD is used to decompose randomly chosen portions of speech signals into intrinsic mode functions, which are then analyzed to extract meaningful temporal and spectral features, including true instantaneous features which can capture discriminative information in signals hidden at local time-scales. A total of six features are extracted, and a linear classifier is used with the feature vector to classify continuous speech portions obtained from a database consisting of 51 normal and 161 pathological speakers. A classification accuracy of 95.7% is obtained, thus demonstrating the effectiveness of the methodology.

An Investigation of Vocal Tract Characteristics for Acoustic Discrimination of Pathological Voices

This paper investigates the effectiveness of measures related to vocal tract characteristics in classifying normal and pathological speech. Unlike conventional approaches that mainly focus on features related to the vocal source, vocal tract characteristics are examined to determine if interaction effects between vocal folds and the vocal tract can be used to detect pathological speech. Especially, this paper examines features related to formant frequencies to see if vocal tract characteristics are affected by the nature of the vocal fold-related pathology. To test this hypothesis, stationary fragments of vowel /aa/ produced by 223 normal subjects, 472 vocal fold polyp subjects, and 195 unilateral vocal cord paralysis subjects are analyzed. Based on the acoustic-articulatory relationships, phonation for pathological subjects is found to be associated with measures correlated with a raised tongue body or an advanced tongue root. Vocal tract-related features are also found to be statistically significant from the Kruskal-Wallis test in distinguishing normal and pathological speech. Classification results demonstrate that combining the formant measurements with vocal fold-related features results in improved performance in differentiating vocal pathologies including vocal polyps and unilateral vocal cord paralysis, which suggests that measures related to vocal tract characteristics may provide additional information in diagnosing vocal disorders.