Juan Ignacio Godino-Llorente

Dimensionality Reduction of a Pathological Voice Quality Assessment System Based on Gaussian Mixture Models and Short-Term Cepstral Parameters

Voice diseases have been increasing dramatically in recent times due mainly to unhealthy social habits and voice abuse. These diseases must be diagnosed and treated at an early stage, especially in the case of larynx cancer. It is widely recognized that vocal and voice diseases do not necessarily cause changes in voice quality as perceived by a listener. Acoustic analysis could be a useful tool to diagnose this type of disease. Preliminary research has shown that the detection of voice alterations can be carried out by means of Gaussian mixture models and short-term mel cepstral parameters complemented by frame energy together with first and second derivatives. This paper, using the F-Ratio and Fishers discriminant ratio, will demonstrate that the detection of voice impairments can be performed using both mel cepstral vectors and their first derivative, ignoring the second derivative

Automatic detection of voice impairments by means of short-term cepstral parameters and neural network based detectors

It is well known that vocal and voice diseases do not necessarily cause perceptible changes in the acoustic voice signal. Acoustic analysis is a useful tool to diagnose voice diseases being a complementary technique to other methods based on direct observation of the vocal folds by laryngoscopy. Through the present paper two neural-network based classification approaches applied to the automatic detection of voice disorders will be studied. Structures studied are multilayer perceptron and learning vector quantization fed using short-term vectors calculated accordingly to the well-known Mel Frequency Coefficient cepstral parameterization. The paper shows that these architectures allow the detection of voice disorders-including glottic cancer-under highly reliable conditions. Within this context, the Learning Vector quantization methodology demonstrated to be more reliable than the multilayer perceptron architecture yielding 96% frame accuracy under similar working conditions.

Methodological issues in the development of automatic systems for voice pathology detection

This paper describes some methodological concerns to be considered when designing systems for automatic detection of voice pathology, in order to enable comparisons to be made with previous or future experiments. The proposed methodology is built around the Massachusetts Eye & Ear Infirmary (MEEI) Voice Disorders Database, which to the present date is the only commercially available one. Discussion about key points on this database is included. Any experiment should have a cross-validation strategy, and results should supply, along with the final confusion matrix, confidence intervals for all measures. Detector performance curves such as detector error trade off (DET) and receiver operating characteristic (ROC) plots are also considered. An example of the methodology is provided, with an experiment based on short-term parameters and multi-layer perceptrons.

Characterization of Healthy and Pathological Voice Through Measures Based on Nonlinear Dynamics

In this paper, we propose to quantify the quality of the recorded voice through objective nonlinear measures. Quantification of speech signal quality has been traditionally carried out with linear techniques since the classical model of voice production is a linear approximation. Nevertheless, nonlinear behaviors in the voice production process have been shown. This paper studies the usefulness of six nonlinear chaotic measures based on nonlinear dynamics theory in the discrimination between two levels of voice quality: healthy and pathological. The studied measures are first- and second-order Renyi entropies, the correlation entropy and the correlation dimension. These measures were obtained from the speech signal in the phase-space domain. The values of the first minimum of mutual information function and Shannon entropy were also studied. Two databases were used to assess the usefulness of the measures: a multiquality database composed of four levels of voice quality (healthy voice and three levels of pathological voice); and a commercial database (MEEI Voice Disorders) composed of two levels of voice quality (healthy and pathological voices). A classifier based on standard neural networks was implemented in order to evaluate the measures proposed. Global success rates of 82.47% (multiquality database) and 99.69% (commercial database) were obtained.

An improved watershed algorithm based on efficient computation of shortest paths

The present paper describes a new algorithm to calculate the watershed transform through rain simulation of greyscale digital images by means of pixel arrowing. The efficiency of this method is based on limiting the necessary neighbouring operations to compute the transform to the outmost, and in the total number of scannings performed over the whole image. The experiments demonstrate that the proposed algorithm is able to significantly reduce the running time of the fastest known algorithm without involving any loss of efficiency.

Automatic Detection of Pathological Voices Using Complexity Measures, Noise Parameters, and Mel-Cepstral Coefficients

This paper proposes a new approach to improve the amount of information extracted from the speech aiming to increase the accuracy of a system developed for the automatic detection of pathological voices. The paper addresses the discrimination capabilities of 11 features extracted using nonlinear analysis of time series. Two of these features are based on conventional nonlinear statistics (largest Lyapunov exponent and correlation dimension), two are based on recurrence and fractal-scaling analysis, and the remaining are based on different estimations of the entropy. Moreover, this paper uses a strategy based on combining classifiers for fusing the nonlinear analysis with the information provided by classic parameterization approaches found in the literature (noise parameters and mel-frequency cepstral coefficients). The classification was carried out in two steps using, first, a generative and, later, a discriminative approach. Combining both classifiers, the best accuracy obtained is 98.23% ± 0.001.

Glottal Source biometrical signature for voice pathology detection

The Glottal Source is an important component of voice as it can be considered as the excitation signal to the voice apparatus. The use of the Glottal Source for pathology detection or the biometric characterization of the speaker are important objectives in the acoustic study of the voice nowadays. Through the present work a biometric signature based on the speakers power spectral density of the Glottal Source is presented. It may be shown that this spectral density is related to the vocal fold cover biomechanics, and from literature it is well-known that certain speakers features as gender, age or pathologic condition leave changes in it. The paper describes the methodology to estimate the biometric signature from the power spectral density of the mucosal wave correlate, which after normalization can be used in pathology detection experiments. Linear Discriminant Analysis is used to confront the detection capability of the parameters defined on this glottal signature among themselves and compared to classical perturbation parameters. A database of 100 normal and 100 pathologic subjects equally balanced in gender and age is used to derive the best parameter cocktails for pathology detection and quantification purposes to validate this methodology in voice evaluation tests. In a study case presented to illustrate the detection capability of the methodology exposed a control subset of 24+24 subjects is used to determine a subjects voice condition in a pre- and post-surgical evaluation. Possible applications of the study can be found in pathology detection and grading and in rehabilitation assessment after treatment.

Digital Auscultation Analysis for Heart Murmur Detection

This work presents a comparison of different approaches for the detection of murmurs from phonocardiographic signals. Taking into account the variability of the phonocardiographic signals induced by valve disorders, three families of features were analyzed: (a) time-varying & time–frequency features; (b) perceptual; and (c) fractal features. With the aim of improving the performance of the system, the accuracy of the system was tested using several combinations of the aforementioned families of parameters. In the second stage, the main components extracted from each family were combined together with the goal of improving the accuracy of the system. The contribution of each family of features extracted was evaluated by means of a simple k-nearest neighbors classifier, showing that fractal features provide the best accuracy (97.17%), followed by time-varying & time–frequency (95.28%), and perceptual features (88.7%). However, an accuracy around 94% can be reached just by using the two main features of the fractal family; therefore, considering the difficulties related to the automatic intrabeat segmentation needed for spectral and perceptual features, this scheme becomes an interesting alternative. The conclusion is that fractal type features were the most robust family of parameters (in the sense of accuracy vs. computational load) for the automatic detection of murmurs. This work was carried out using a database that contains 164 phonocardiographic recordings (81 normal and 83 records with murmurs). The database was segmented to extract 360 representative individual beats (180 per class).

Acoustic analysis of voice using WPCVox: a comparative study with Multi Dimensional Voice Program

In this study, two different tools developed for the parametric extraction and acoustic analysis of voice samples are compared. The main goal of the paper is to contrast the results obtained using the classical Multi Dimensional Voice Program (MDVP), with the results obtained with the novel WPCVox. The aim of this comparison was to find differences and similarities in the parameters extracted with both systems in order to make comparison of measurements and data transfer among both equipments. The study was carried out in two stages: in the first, a wide sample of healthy voices belonging to Spanish-speaking adults from both genders were used to carry out a direct comparison between the results given by MDVP and those obtained with WPCVox. In the second stage, a sample of 200 speakers (53 normal and 173 pathological) taken from a commercially available database of voice disorders were used to demonstrate the usefulness of WPCVox for the acoustic analysis and the characterization of normal and pathological voices. The results conclude that WPCVox provides very reliable measurements which are very similar to those obtained using MDVP, and very similar capabilities to discriminate among normal and pathological voices.

An improved method for voice pathology detection by means of a HMM-based feature space transformation

This paper presents new a feature transformation technique applied to improve the screening accuracy for the automatic detection of pathological voices. The statistical transformation is based on Hidden Markov Models, obtaining a transformation and classification stage simultaneously and adjusting the parameters of the model with a criterion that minimizes the classification error. The original feature vectors are built up using classic short-term noise parameters and mel-frequency cepstral coefficients. With respect to conventional approaches found in the literature of automatic detection of pathological voices, the proposed feature space transformation technique demonstrates a significant improvement of the performance with no addition of new features to the original input space. In view of the results, it is expected that this technique could provide good results in other areas such as speaker verification and/or identification.