Automatic voice pathology detection and classification using vocal tract area irregularity

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), Saarbrücken 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.

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.

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

A novel voice pathology detection technique through deep neural networks utilizing speech and electroglottographic signals

The article presents a set of experiments on pathological voice detection over the Saarbrucken Voice Database (SVD). The SVD is freely available online containing a collection of voice recordings of different pathologies, both functional and organic. It includes recordings for more than 2000 speakers in which sustained vowels /a/, /i/, and /u/ are pronounced with normal, low, high, and low-high-low intonations. This variety of sounds makes possible to set different experiments, and in this paper a comparison between the performance of a system where all the vowels and intonations are pooled together to train a single model per class, and a system where a different model per class is trained for each vowel and intonation, and the scores of each subsystem are fused at the end, is conducted. The first approach is what we call audio level fusion, and the second is what we call score level fusion. For classification, a generative Gaussian mixture model trained with mel-frequency cepstral coefficients, harmonics-to-noise ratio, normalized noise energy and glottal-to-noise excitation ratio, is used. It is shown that the score level fusion is far more effective than the audio level fusion.

Noninvasive Detection of Potentially Precancerous Lesions of Vocal Fold Based on Glottal Wave Signal and SVM Approaches

Voice pathology analysis has been one of the useful tools in the diagnosis of the pathological voice. This method is non-invasive, inexpensive and reduces time required for analysis. This paper investigates the feature extraction based on the Dual-Tree Complex Wavelet Packet Transform (DT-CWPT) with entropies and energy measures tested with two classifiers, k-Nearest Neighbors (k-NN) and Support Vector Machine (SVM). Feature selection using ReliefF algorithm is applied to reduce redundancy features set and obtain the optimum features for classification. Massachusetts Eye and Ear Infirmary (MEEI) voice disorders database and Saarbruecken Voice Database (SVD) are used. This research was done on multiclass and by specific pathology. The experimental results automates the process of voice analysis hence produce promising results of the presence of diseases in vocal folds.

Speech is the underlying strong characteristic and voice is the vibration that the air creates as it's pushed out of the lungs and going into the vocal cords. Vocal cords are two folds of tissue within the larynx, sometimes called a speech box, the sound of these strings is what gives rise to speech.Anything that interferes with vocal cord movement or contact can cause a voice disorder. Speech production may often be compromised as social stressors contribute to chronic aphonia or dysphonia.Machine learning algorithm and non-invasive systems may play a major role in the early detection and in tracking and even development of efficient pathological speech diagnosis, based on a computerized acoustic analysis. A strong voice impairment dataset will help in recognition and classification ofincreasing number of voice disorders in and outside the Arab area. The database protocols for AVPD (Arabic voice pathology database) has been developed in a way to prevent previous data base deficiencies in widely used databases like MEEI (Massachusetts eye and ear infirmary) and SVD (Saarbrücken voice database).

This paper presents a convolutional neural network-based pathological voice detection system using speech and electroglottographic (EGG) signals. Speech signals have been popularly used to detect voice pathology. Recently, the EGG signals have drawn considerable attention from researchers in this field. They argued that the EGG signals could detect the vocal fold vibration more accurately than speech signals and hence can be considered more appropriate for voice pathology detection. This work investigates the effectiveness of the EGG and speech signals in detecting pathological voices using sustained vowel (“/a/”) samples collected from the Saarbrücken Voice Database (SVD). The Mel frequency cepstral coefficients (MFCCs) extracted from the speech and EGG samples are employed as discerning features for this investigation. The results show that the proposed system achieves a higher accuracy (more than 23%) in identifying dysphonic voices from healthy ones with speech signals.

ObjectiveTo investigate changes in the age of occurrence of herpes zoster ophthalmicus (HZO) in patients presenting to the Massachusetts Eye and Ear Infirmary (MEEI) from 2007 through 2013.DesignRetrospective chart review.SettingAcademic...

Nasal resonance is utilized in certain languages to differentiate word meanings. The joint filtering effect by the vocal tract and the nasal tract can be modeled by the auto-regression moving-average (ARMA) approach. However, unlike all-pole (i.e., AR) modeling, it has been difficult to derive the equivalent vocal-tract area function directly from an ARMA model due to the nonlinear nature in the relation between model coefficients and vocal-tract geometry. In this paper, we propose a method to decompose an ARMA model approximately into α/C(z) + β/D(z); in our context, 1/C(z) and 1/D(z) represent the filtering effects of the oral and the nasal tract, respectively. Once the decomposition is performed, equivalent oral-tract and nasal-tract area functions can be obtained by converting C(z) and D(z) to their respective lattice representation. The proposed method was applied to non-nasalized and nasalized vowels produced by three speakers, and it was found that the ratio r = β/α tends to be higher in nasalized vowels than in their non-nasalized counterparts. The vocal-tract area function estimated by the present approach was also fairly stable for sustained vowels.

Automatic detection and assessment of Vocal Folds pathologies using signal processing techniques knows an extensively challenge use in the voice or speech research community. This paper contributes the application of the Recurrence Quantification Analysis (RQA) to a glottal signal waveform in order to evaluate the dynamic process of Vocal Folds (VFs) for diagnosis and classify the voice disorders. The proposed solution starts by extracting the glottal signal waveform from the voice signal through an inverse filtering algorithm. In the next step, the parameters of RQA are determined via the Recurrent Plot (RP) structure of the glottal signal where the normal voice is considered as a reference. Finally, these parameters are used as input features set of a hybrid Particle Swarm Optimization-Support Vector Machines (PSO-SVM) algorithms to segregate between normal and pathological voices. For the test validation, we have adopted the collection of Saarbrucken Voice Database (SVD) where we have selected the long vowel /a:/ of 133 normal samples and 260 pathological samples uttered by four groups of subjects : persons having suffered from vocal folds paralysis, persons having vocal folds polyps, persons having spasmodic dysphonia and normal voices. The obtained results show the effectiveness of RQA applied to the glottal signal as a features extraction technique. Indeed, the PSO-SVM as a classification method presented an effective tool for assessment and diagnosis of pathological voices with an accuracy of 97.41%

The voice pathology detection using automatic classification systems is a useful way to diagnose voice diseases. In this paper, we propose a novel tool to detect voice pathology based on an incremental possibilistic SVM-HMM method which can be applied to serval practical applications using non-stationary or a very large-scale data in purpose to reduce the memory issues faced during the storage of the kernel matrix. The proposed system includes the steps of using SVM to incrementally compute possibilitic probabilities and then they will be used by HMM in order to detect voice pathologies. We evaluated the proposed method on the task of the detection of voice pathologies using voices samples from the Massachusetts Eye and Ear Infirmary Voice and Speech Laboratory (MEEI) database. According to the detection rates obtained by our system, the performance sounds robust, efficient and speed applied to a task of voices pathology detection.

In this paper, a mode decomposition analysis-based adaptive approach is proposed to provide high diagnostic performance for automated voice pathology detection systems. The aim of the study is to develop a reliable and effective system using adaptive cepstral domain features derived from the empirical mode decomposition (EMD), ensemble empirical mode decomposition (EEMD), and complete empirical mode decomposition with adaptive noise (CEEMDAN) methods. The descriptive feature sets are obtained by applying mel-frequency cepstral coefficients (MFCCs) and their derivatives, linear predictive coefficients (LPCs) and linear predictive cepstral coefficients (LPCCs) techniques to each decomposition level. The class-balanced data are generated on the VOice ICar fEDerico II database samples using the synthetic minority oversampling technique (SMOTE). The ReliefF algorithm is used to select the most effective and distinctive features. A combination of selected features and a support vector machine (SVM) classifier is used to identify pathological voices. In the pathology detection approach, the results show that the cepstral features based on EMD and SVM-cubic achieves the highest performance with 99.85\% accuracy, 99.85\% F1-score and 0.997 Matthews correlation coefficient (MCC). In pathology-type classification, the cepstral features based on EEMD and SVM-quadratic approach provided the highest performance with 96.49\% accuracy, 96.46\% F1 and 0.949 MCC values. The comprehensive results of this study reveal that mode decomposition-based approaches are more successful and effective than traditional methods for detection and classification of pathological voices.

An incremental method combining density clustering and support vector machines for voice pathology detection