Automatic Voice Pathology Detection Research Articles

A comparison of data augmentation methods in voice pathology detection

To distinguish pathological voices from healthy voices, automatic voice pathology detection systems can be built using machine learning (ML) and deep learning (DL) techniques. To fully exploit such systems, large quantities of training data are typically required. The amount of training data is, however, small in the area of pathological voice, and therefore data augmentation (DA) becomes a potential technology to artificially increase the quantity of training data. This study presents a systematic comparison between various DA methods in the detection of pathological voice, including three time domain methods (noise addition, pitch shifting and time stretching), one time–frequency domain method (SpecAugment), and two vocoder-based methods (harmonic-to-noise ratio (HNR) modification and glottal pulse length modification). Detection systems were built using four popular spectral feature representations (static mel-frequency cepstral coefficients (MFCCs), dynamic MFCCs, spectrogram and mel-spectrogram). As classifiers, two widely used ML models (support vector machine (SVM) and random forest (RF)) and two DL models (long short-term memory (LSTM) network and convolutional neural network (CNN) with 1-dimensional (1-D) and 2-dimensional (2-D) architectures) were used. These systems were trained using a small number of training samples from two popular databases of pathological voice (HUPA and SVD) to find the best feature/classifier combination for each database. As a result, one ML-based detection system (mel-spectrogram/SVM for HUPA and SVD) and two DL-based detection systems (dynamic MFCCs/2-D CNN for HUPA and mel-spectrogram/2-D CNN for SVD) were selected for the comparison of the DA methods. The results show that by using DA in the system training, detection accuracy increased compared to the baseline systems that were trained without using DA. This improvement in accuracy was, however, clearly larger for the 2D-CNN system than for the SVM system. Furthermore, all six DA methods improved accuracy of the 2-D CNN system compared to the baseline system for both databases. The highest improvements were achieved using the time–frequency domain SpecAugment DA method, which improved accuracy by 1.5% and 3.8% (absolute) for the HUPA and SVD database, respectively.

MMHFNet: Multi-modal and multi-layer hybrid fusion network for voice pathology detection

Automatic voice pathology detection using non-invasive techniques that utilize patients’ speech and electroglottograph (EGG) signals play a vital role in diagnosis and early medical intervention. In this paper, a novel deep Multi-Modal and Multi-Layer Hybrid Fusion Network (MMHFNet) is proposed to improve the performance of non-invasive voice pathology detection systems. MMHFNet simultaneously incorporates complementary information of different modalities (speech and EGG signals). It also vertically combines the low-level features, extracted from shallow layers, and high-level features, extracted from deep layers, to take the full advantage of spatio-spectral information of different layers for multi-layer fusion. The features extracted by MMHFNet are then fed into an LSTM classification network to diagnose the voice pathology. Comprehensive experiments are conducted on the publicly available Saarbruecken Voice Database (SVD) to evaluate the performance of the proposed MMHFNet. This dataset is used in two manners; one using its all samples and the other with selected samples to form the largest balanced SVD dataset. Experimental results demonstrated that the proposed MMHFNet achieves accuracy rates of 91% and 96.05% for datasets with all and balanced samples, respectively.

Voice Pathology Detection Using a Two-Level Classifier Based on Combined CNN–RNN Architecture

The construction of an automatic voice pathology detection system employing machine learning algorithms to study voice abnormalities is crucial for the early detection of voice pathologies and identifying the specific type of pathology from which patients suffer. This paper’s primary objective is to construct a deep learning model for accurate speech pathology identification. Manual audio feature extraction was employed as a foundation for the categorization process. Incorporating an additional piece of information, i.e., voice gender, via a two-level classifier model was the most critical aspect of this work. The first level determines whether the audio input is a male or female voice, and the second level determines whether the agent is pathological or healthy. Similar to the bulk of earlier efforts, the current study analyzed the audio signal by focusing solely on a single vowel, such as /a/, and ignoring phrases and other vowels. The analysis was performed on the Saarbruecken Voice Database,. The two-level cascaded model attained an accuracy and F1 score of 88.84% and 87.39%, respectively, which was superior to earlier attempts on the same dataset and provides a steppingstone towards a more precise early diagnosis of voice complications.

Combined Use of Nonlinear Measures for Analyzing Pathological Voices

Automatic voice pathology detection enables an objective assessment of pathologies that influence the voice production strategy. By utilizing the conventional pipeline model as well as the modern deep learning-centric end-to-end methodology, numerous pathological voice analyzing techniques have been developed. The conventional methodology is still a valid choice owing to the lack of enormous amounts of training data in the study region of pathological voice. In the meantime, obtaining higher precision, higher accuracy, and stability is still a complicated task. Therefore, by amalgamating the nonlinear measure, the pathological voices are analyzed to abate such risks. The viability of six nonlinear discriminating measures derived from the phase space realm, involving healthy and pathological voice signals, is studied in this work. The analyzed parameters are Singularity spectrum coefficients ([Formula: see text], [Formula: see text] and [Formula: see text]). Correlation entropy at optimum embedding dimension ([Formula: see text]) and correlation dimension at optimum embedding dimension ([Formula: see text]). Analyzing the pathological voices with better accuracy rates is the major objective of the proposed methodology. Here, the Support Vector Machine (SVM) was utilized as the classifier. Experimentations were performed on VOiceICarfEDerico (VOICED) databases subsuming 208 healthy, as well as pathological voices, amongst these 50 samples, were utilized. Here, the model obtained 97% of accuracy with 99% as of the classifier with Gaussian kernel function. Therefore, to differentiate normal as well as pathological subjects, the six proposed characteristics are highly beneficial; in addition, they will be supportive in pathology diagnosis.

The Effect of the MFCC Frame Length in Automatic Voice Pathology Detection

Automatic voice pathology detection is a research topic, which has gained increasing interest recently. Although methods based on deep learning are becoming popular, the classical pipeline systems based on a two-stage architecture consisting of a feature extraction stage and a classifier stage are still widely used. In these classical detection systems, frame-wise computation of mel-frequency cepstral coefficients (MFCCs) is the most popular feature extraction method. However, no systematic study has been conducted to investigate the effect of the MFCC frame length on automatic voice pathology detection. In this work, we studied the effect of the MFCC frame length in voice pathology detection using three disorders (hyperkinetic dysphonia, hypokinetic dysphonia and reflux laryngitis) from the Saarbrücken Voice Disorders (SVD) database. The detection performance was compared between speaker-dependent and speaker-independent scenarios as well as between speaking task -dependent and speaking task -independent scenarios. The Support Vector Machine, which is the most widely used classifier in the study area, was used as the classifier. The results show that the detection accuracy depended on the MFFC frame length in all the scenarios studied. The best detection accuracy was obtained by using a MFFC frame length of 500 ms with a shift of 5 ms.

Multi-modal voice pathology detection architecture based on deep and handcrafted feature fusion

Automatic voice pathology detection systems can effectively help clinicians by enabling objective assessment and diagnosis in early stage of voice pathologies. This paper suggests a novel multi-modal architecture utilizing speech and electroglottography (EGG) signals and investigates their effectiveness in automatic detection of voice pathology. The proposed multi-modal framework combines two parallel Convolutional Neural Networks (CNNs), one for voice signals and the other for EGG signals, to obtain deep features. Classical handcrafted features are also obtained in the same manner. These features are then concatenated to obtain a more prominent feature set. In addition, a feature selection method is applied to remove redundant features. Finally, a SVM classifier is utilized to detect the voice pathology. In order to measure the performance of the proposed pathology detection system, various experiments are conducted on Saarbruecken Voice Database (SVD) without excluding any available pathology or sample. The experimental results show that the proposed voice pathology detection method achieves accuracy up to 90.10% using all speech and EGG samples. Also, sensitivity, specificity and F1-score results of 92.9%, 84.6% and 92.57% are obtained, respectively. The proposed method provides better performance than those given in the literature using all SVD samples through cross-validation testing. Hence, it is promising for automatic detection applications of voice pathology.

Voice pathology detection and classification from speech signals and EGG signals based on a multimodal fusion method.

Automatic voice pathology detection and classification plays an important role in the diagnosis and prevention of voice disorders. To accurately describe the pronunciation characteristics of patients with dysarthria and improve the effect of pathological voice detection, this study proposes a pathological voice detection method based on a multi-modal network structure. First, speech signals and electroglottography (EGG) signals are mapped from the time domain to the frequency domain spectrogram via a short-time Fourier transform (STFT). The Mel filter bank acts on the spectrogram to enhance the signal's harmonics and denoise. Second, a pre-trained convolutional neural network (CNN) is used as the backbone network to extract sound state features and vocal cord vibration features from the two signals. To obtain a better classification effect, the fused features are input into the long short-term memory (LSTM) network for voice feature selection and enhancement. The proposed system achieves 95.73% for accuracy with 96.10% F1-score and 96.73% recall using the Saarbrucken Voice Database (SVD); thus, enabling a new method for pathological speech detection.

A Comparison of Cepstral Features in the Detection of Pathological Voices by Varying the Input and Filterbank of the Cepstrum Computation

Automatic voice pathology detection enables objective assessment of pathologies that affect the voice production mechanism. Detection systems have been developed using the traditional pipeline approach (consisting of the feature extraction part and the detection part) and using the modern deep learning -based end-to-end approach. Due to the lack of vast amounts of training data in the study area of pathological voice, the former approach is still a valid choice. In the existing detection systems based on the traditional pipeline approach, the mel-frequency cepstral coefficient (MFCC) features can be regarded as the defacto standard feature set. In this study, automatic voice pathology detection is investigated by comparing the performance of various MFCC variants derived by considering two factors: the input and the filterbank in the cepstrum computation. For the first factor, three inputs (the voice signal, the glottal source and the vocal tract) are compared. The glottal source and the vocal tract are estimated using the quasi-closed phase glottal inverse filtering method. For the second factor, the mel-frequency and linear-frequency filterbanks are compared. Experiments were conducted separately using six databases consisting of voices produced by speakers suffering from one of four disorders (dysphonia, Parkinson’s disease, laryngitis, or heart failure) and by healthy speakers. Support vector machine (SVM) was used as the classifier. The results show that by combining mel- and linear-frequency cepstral coefficients derived from the glottal source and vocal tract, better overall detection accuracy was obtained compared to the defacto MFCC features derived from the voice signal. Furthermore, this combination provided comparable or better performance than four existing cepstral feature extraction techniques in clean and high signal-to-noise ratio (SNR) conditions.

Investigation and Evaluation of Glottal Flow Waveform for Voice Pathology Detection

Automatic voice pathology detection can provide objective estimation and prevention in the early stages of voice diseases. Glottal flow waveform directly reflects the state of glottal excitation. Extracting acoustic features from glottal source signals may contribute to the detection of pathological voice. To improve the performance of voice pathology detection, this article investigates the contribution of the glottal flow waveform for pathological voice detection by evaluating the classification result using features extracted from raw speech utterances and corresponding glottal flow waveforms. The individual feature sets used are extracted from raw or glottal voice utterances with identical parameter settings, which are openSMILE acoustic features, audio features computed by Moving Picture Experts Group-7 standard and classical glottal source features. In addition, a feature selection method in terms of the wrapper approach is used to combine the single features ranked by using the Fisher discrimination ratio. Voice pathology detection experiments were carried out using Random Forest. The best accuracies of 88.52% for the Saarbrucken Voice database and 100.00% for the Massachusetts Eye and Ear Infirmary database are achieved using the combined feature set extracted from the glottal source signal, with improvement of 0.44-3.13% in the accuracies obtained by using raw speech utterances. Compared to state-of-the-art methods, the proposed method achieves the highest accuracy for the Massachusetts Eye and Ear Infirmary database and an increase of 2.75-17.16% in detection accuracy compared to other conventional pipeline systems for the Saarbrucken Voice databse. The experimental results demonstrate that using glottal flow waveform as source signal can improve the performance of pathological voice detection.

Voice Pathologies Classification and Detection Using EMD-DWT Analysis Based on Higher Order Statistic Features

BackgroundThe voice is a prominent tool allowing people to communicate and to change information in their daily activities. However, any slight alteration in the voice production system may affect the voice quality. Over the last years, researchers in biomedical engineering field worked to develop a robust automatic system that may help clinicians to perform a preventive diagnosis in order to detect the voice pathologies in an early stage. MethodIn this context, pathological voice detection and classification method based on EMD-DWT analysis and Higher Order Statistics (HOS) features, is proposed. Also DWT coefficients features are extracted and tested. To carry out our experiments a wide subset of voice signal from normal subjects and subjects which suffer from the five most frequent pathologies in the Saarbrücken Voice Database (SVD), is selected. In The first step, we applied the Empirical Mode Decomposition (EMD) to the voice signal. Afterwards, among the obtained candidates of Intrinsic Mode Functions (IMFs), we choose the robust one based on temporal energy criterion. In the second step, the selected IMF was decomposed via the Discrete Wavelet Transform (DWT). As a result, two features vector includes six HOSs parameters, and a features vector includes six DWT features were formed from both approximation and detail coefficients. In order to classify the obtained data a support vector machine (SVM) is employed. After having trained the proposed system using the SVD database, the system was evaluated using voice signals of volunteer's subjects from the Neurological department of RABTA Hospital of Tunis. ResultsThe proposed method gives promising results in pathological voices detection. The accuracies reached 99.26% using HOS features and 93.1% using DWT features for SVD database. In the classification, an accuracy of 100% was reached for “Funktionelle Dysphonia vs. Rekrrensparese” based on HOS features. Nevertheless, using DWT features the accuracy achieved was 90.32% for “Hyperfunktionelle Dysphonia vs. Rekurrensparse”. Furthermore, in the validation the accuracies reached were 94.82%, 91.37% for HOS and DWT features, respectively. In the classification the highest accuracies reached were for classifying “Parkinson versus Paralysis” 94.44% and 88.87% based on HOS and DWT features, respectively. ConclusionHOS features show promising results in the automatic voice pathology detection and classification compared to DWT features. Thus, it can reliably be used as noninvasive tool to assist clinical evaluation for pathological voices identification.

Kullback–Leibler divergence and sample skewness for pathological voice quality assessment

This paper proposes new features aiming to improve the performance of an automatic voice pathology detection system. The features are designed precisely in terms of voice pathologies effects upon the speech signal. The system is intended to deliver high accuracy with a low number of parameters. Kullback–Leibler divergence (KLD) applied to consecutive frames of the speech signal provides a measure of voice instability. In this work, the KLD is applied to frame’s histogram and a modified form of its spectrum named higher amplitude suppression spectrum (HASS). The H-KLD (histogram KLD) and the HASS-KLD are two of the three features presently approached. An additional feature that provides the level of damping of the voice pitch period waveform is proposed, the short-term sample skewness of the signal. The H-KLD, the HASS-KLD, and the sample skewness are features employed along with mel-frequency cepstral coefficients (MFCC) in a voice pathology detection system. The system is composed of a Gaussian mixture models (GMM) classifier and two generalized extreme value (GEV) distribution classifiers. They are fused by means of a Gaussian naïve Bayes classifier. A standard subset of the Massachusetts Eye and Ear Infirmary (MEEI) voice disorders database is adopted for evaluating the system. The obtained global success rate of 99.55% shows that the proposed features are suitable for pathological voice quality assessment.

Classification of Psychogenic and Laryngeal Voice Diseases Based on Teager Energy Operator

Among several ways of communication, the voice remains the fastest natural tool for human-to-human and human-to-machine communication. That is why the research in automatic voice pathology detection and classification area has gained much interest in the recent years. Indeed, these automatic systems may be considered as assistive tools for the physicians during the assessment stage. This latter may help them to make decision, whether the voice signal belongs to a healthy or unhealthy subject and identifies the nature of pathology. In this context, this paper provides a voice pathology detection and classification system based on wavelet analysis and Teager Energy Operator (TEO). First, we used the input voice signal that we taken from Saarbrücken Voice Database (SVD) [1], to extract a set of features. These feature vectors are fed into a Gaussian Mixture Model (GMM) [2] for the sake of classification. The obtained results are 96.66% for the detection task and 92.5 % using TEO. These results show that our proposal outperforms some state-of-art methods used in voice pathology identification.

Detection & Classification of Voice Pathology using Electrical Circuit Parameters

The classification of pathological voice is a hot topic that has been expected significant consideration. Voice pathology is related with a vocal folds difficulty, and for this reason, the vocal tract area which is joined to vocal folds demonstrate random patterns in case of a pathological voice. This random pattern is considered to distinguish healthy and pathological voices. It is possible to utilize transmission line theory in discovering automatic voice pathology detection by taking into consideration the vocal tract as acoustic lines. The work concentrates on developing a feature extraction for detecting and classifying vocal fold polyp by investigating different vocal tract parameters. In this paper, the vocal tract length and area are utilized for computing electrical parameters of the vocal tract. Furthermore, these electrical parameters are used for the classification of pathological voice. Finally, using electrical parameters 97.3% accuracy is obtained with SVM classifier when compared with 88.2% with the acoustic parameters, 85.3% accuracy considering physical parameters and other methods used in the past. The outcomes demonstrate that electrical parameters of the vocal tract can be utilized all the more successfully with better precision in voice pathology identification.

Voice Pathology Detection and Classification Using Auto-Correlation and Entropy Features in Different Frequency Regions

Automatic voice pathology detection and classification systems effectively contribute to the assessment of voice disorders, enabling the early detection of voice pathologies and the diagnosis of the type of pathology from which patients suffer. This paper concentrates on developing an accurate and robust feature extraction for detecting and classifying voice pathologies by investigating different frequency bands using autocorrelation and entropy. We extracted maximum peak values and their corresponding lag values from each frame of a voiced signal by using autocorrelation as features to detect and classify pathological samples. We also extracted the entropy for each frame of the voice signal after we normalized its values to be used as the features. These features were investigated in distinct frequency bands to assess the contribution of each band to the detection and classification processes. Various samples of the sustained vowel /a/ for both normal and pathological voices were extracted from three different databases in English, German, and Arabic. A support vector machine was used as a classifier. We also performed u-tests to investigate if there is a significant difference between the means of the normal and pathological samples. The best achieved accuracies in both detection and classification varied depending on the used band, method, and database. The most contributive bands in both detection and classification were between 1000 and 8000 Hz. The highest obtained accuracies in the case of detection were 99.69%, 92.79%, and 99.79% for Massachusetts eye and ear infirmary (MEEI), Saarbrucken voice database (SVD), and Arabic voice pathology database (AVPD), respectively. However, the highest achieved accuracies for classification were 99.54%, 99.53%, and 96.02% for MEEI, SVD, and AVPD, correspondingly, using the combined feature.

An Investigation of Multidimensional Voice Program Parameters in Three Different Databases for Voice Pathology Detection and Classification

Automatic voice-pathology detection and classification systems may help clinicians to detect the existence of any voice pathologies and the type of pathology from which patients suffer in the early stages. The main aim of this paper is to investigate Multidimensional Voice Program (MDVP) parameters to automatically detect and classify the voice pathologies in multiple databases, and then to find out which parameters performed well in these two processes. Samples of the sustained vowel /a/ of normal and pathological voices were extracted from three different databases, which have three voice pathologies in common. The selected databases in this study represent three distinct languages: (1) the Arabic voice pathology database; (2) the Massachusetts Eye and Ear Infirmary database (English database); and (3) the Saarbruecken Voice Database (German database). A computerized speech lab program was used to extract MDVP parameters as features, and an acoustical analysis was performed. The Fisher discrimination ratio was applied to rank the parameters. A t test was performed to highlight any significant differences in the means of the normal and pathological samples. The experimental results demonstrate a clear difference in the performance of the MDVP parameters using these databases. The highly ranked parameters also differed from one database to another. The best accuracies were obtained by using the three highest ranked MDVP parameters arranged according to the Fisher discrimination ratio: these accuracies were 99.68%, 88.21%, and 72.53% for the Saarbruecken Voice Database, the Massachusetts Eye and Ear Infirmary database, and the Arabic voice pathology database, respectively.

Investigation of Voice Pathology Detection and Classification on Different Frequency Regions Using Correlation Functions

Automatic voice pathology detection and classification systems effectively contribute to the assessment of voice disorders, which helps clinicians to detect the existence of any voice pathologies and the type of pathology from which patients suffer in the early stages. This work concentrates on developing an accurate and robust feature extraction for detecting and classifying voice pathologies by investigating different frequency bands using correlation functions. In this paper, we extracted maximum peak values and their corresponding lag values from each frame of a voiced signal by using correlation functions as features to detect and classify pathological samples. These features are investigated in different frequency bands to see the contribution of each band on the detection and classification processes. Various samples of sustained vowel /a/ of normal and pathological voices were extracted from three different databases: English, German, and Arabic. A support vector machine was used as a classifier. We also performed a t test to investigate the significant differences in mean of normal and pathological samples. The best achieved accuracies in both detection and classification were varied depending on the band, the correlation function, and the database. The most contributive bands in both detection and classification were between 1000 and 8000 Hz. In detection, the highest acquired accuracies when using cross-correlation were 99.809%, 90.979%, and 91.168% in the Massachusetts Eye and Ear Infirmary, Saarbruecken Voice Database, and Arabic Voice Pathology Database databases, respectively. However, in classification, the highest acquired accuracies when using cross-correlation were 99.255%, 98.941%, and 95.188% in the three databases, respectively.

Automatic voice pathology detection and classification using vocal tract area irregularity

In this paper, an automatic voice pathology detection (VPD) system based on voice production theory is developed. More specifically, features are extracted from vocal tract area, which is connected to the glottis. Voice pathology is related to a vocal fold problem, and hence the vocal tract area which is connected to vocal folds or glottis should exhibit irregular patterns over frames in case of a sustained vowel for a pathological voice. This irregular pattern is quantified in the form of different moments across the frames to distinguish between normal and pathological voices. The proposed VPD system is evaluated on the Massachusetts Eye and Ear Infirmary (MEEI) database and Saarbrucken Voice Database (SVD) with sustained vowel samples. Vocal tract irregularity features and support vector machine classifier are used in the proposed system. The proposed system achieves 99.22%±0.01 accuracy on the MEEI database and 94.7%±0.21 accuracy on the SVD. The results indicate that vocal tract irregularity measures can be used effectively in automatic voice pathology detection.

Automatic Voice Pathology Detection With Running Speech by Using Estimation of Auditory Spectrum and Cepstral Coefficients Based on the All-Pole Model

Automatic voice pathology detection using sustained vowels has been widely explored. Because of the stationary nature of the speech waveform, pathology detection with a sustained vowel is a comparatively easier task than that using a running speech. Some disorder detection systems with running speech have also been developed, although most of them are based on a voice activity detection (VAD), that is, itself a challenging task. Pathology detection with running speech needs more investigation, and systems with good accuracy (ACC) are required. Furthermore, pathology classification systems with running speech have not received any attention from the research community. In this article, automatic pathology detection and classification systems are developed using text-dependent running speech without adding a VAD module. A set of three psychophysics conditions of hearing (critical band spectral estimation, equal loudness hearing curve, and the intensity loudness power law of hearing) is used to estimate the auditory spectrum. The auditory spectrum and all-pole models of the auditory spectrums are computed and analyzed and used in a Gaussian mixture model for an automatic decision. In the experiments using the Massachusetts Eye & Ear Infirmary database, an ACC of 99.56% is obtained for pathology detection, and an ACC of 93.33% is obtained for the pathology classification system. The results of the proposed systems outperform the existing running-speech-based systems. The developed system can effectively be used in voice pathology detection and classification systems, and the proposed features can visually differentiate between normal and pathological samples.

Employing linear prediction residual signal of wavelet sub-bands in automatic detection of laryngeal pathology

An automatic voice pathology detection scheme based on the processing of speech signal is introduced that is highly reliable in detecting various vocal folds impairments. Using linear prediction (LP) analysis to accurately keep track the variations of glottal signal from speech signal is the key element of our proposed method. The linear prediction-based residual signal estimation is employed to monitor the irregularity of glottal signal with the aim of providing information about vocal folds status. The procedure is done by decomposing a voiced signal (/a/) selected from Kay Elemetrics databases using 1-D discrete wavelet decomposition in four levels, and then applying linear prediction (LP) analysis on achieved coefficients of wavelet sub-band to capture a time-frequency representation of vocal folds vibrations. Support vector machine is finally used to make a decision about the existence of any abnormality in the vocal folds of the analyzed sample. Experimental results indicate that the extracted residual signals from wavelet sub-bands provide highly reliable features especially where there are a variety of abnormal voices that are applicable for assessing voice quality and the effectiveness of the prescribed rehabilitation medicine.

Pathological voice detection and binary classification using MPEG-7 audio features

ObjectivesA pathological voice detection and classification method based on MPEG-7 audio low-level features is proposed in this paper. MPEG-7 features are originally used for multimedia indexing, which includes both video and audio. Indexing is related to event detection, and as pathological voice is a separate event than normal voice, we show that MPEG-7 part-4 audio low-level features can do very well in detecting pathological voices, as well as binary classifying the pathologies. Patients and methodsThe experiments are done on a subset of sustained vowel (“AH”) recordings from healthy and voice pathological subjects, from the Massachusetts Eye and Ear Infirmary (MEEI) database. For classification, support vector machine (SVM) is applied. An optional feature selection method, namely, Fisher discrimination ratio is applied. ResultsThe proposed method with MPEG-7 audio features and SVM classification is evaluated on voice pathology detection, as well as binary pathologies classification. The proposed method is able to achieve an accuracy of 99.994% with a standard deviation of 0.0105% for detecting pathological voices and an accuracy up to 100% for binary pathologies classification. ConclusionMPEG-7 descriptors can reliably be used for automatic voice pathology detection and classification.