Everthon Silva Fonseca

Trying different wavelets on the search for voice disorders sorting

This work describes the use of different DWTs - discrete wavelet transforms, like Haar, Daubechies, Coiflets, Symmlets and Spikelet in order to distinguish between normal and pathological human voices. All the transforms are used to evaluate some properties of the digitalized voice signals under analysis, as the power density spectrum and also a fractal dimension parameter is calculated. According to an ordinary threshold it is possible to estimate the voice as belonging to a normal or pathological patient, in respect to his or her larynx working. The results are compared and presented and the conclusions show it is possible to have a promising result based on a deterministic approach with low computational order of complexity, furthermore, it is possible to have a DSP real-time implementation.

A neural-wavelet architecture for voice conversion

In this letter we propose a new architecture for voice conversion that is based on a joint neural-wavelet approach. We also examine the characteristics of many wavelet families and determine the one that best matches the requirements of the proposed system. The conclusions presented in theory are confirmed in practice with utterances extracted from TIMIT speech corpus.

Discrete wavelet transform and support vector machine applied to pathological voice signals identification

An algorithm able to classify pathological and normal voice signals based on Daubechies discrete wavelet transform (DWT-db) and support vector machines (SVM) classifier is presented. DWT-db is used for time-frequency analysis giving quantitative evaluation of signal characteristics to identify pathologies in voice signals, particularly nodules in vocal folds, of subjects with different ages for both male and female. After using a linear prediction coefficients (LPC) filter, the signals mean square values of a particular scale from wavelet analysis are entries to a nonlinear least square support vector machine (LS-SVM) classifier, which leads to an adequate larynx pathology classifier which over 95% of classification accuracy.

Normal versus pathological voice signals

In this work, a method to analyze the time-frequency characteristics to distinguish pathological voices from patients with Reinkes edema and nodules in vocal folds was developed. Daubechies discrete wavelet transform (DWT) components of approximation and detail in convenient scales of frequency for different voice signals were used to analyze the time-frequency signal characteristics. In this work, 71 voice signals were used from subjects of different ages, both male and female: 30 with no pathology in vocal folds, 25 from patients with nodules in vocal folds, and 16 from patients with Reinkes edema. Least squares support-vector machines (LS- SVM) classifier leads to more than 90% of classification accuracy between normal voices and voices from patients with nodules in vocal folds, more than 85% between normal voices and voices from patients with Reinkes edema, and more than 80% between the two different pathological voice signals.

Autoregressive decomposition and pole tracking applied to vocal fold nodule signals

This letter describes a novel algorithm that is based on autoregressive decomposition and pole tracking used to recognize two patterns of speech data: normal voice and disphonic voice caused by nodules. The presented method relates the poles and the peaks of the signal spectrum which represent the periodic components of the voice. The results show that the perturbation contained in the signal is clearly depicted by poles positions. Their variability is related to jitter and shimmer. The pole dispersion for pathological voices is about 20% higher than for normal voices, therefore, the proposed approach is a more trustworthy measure than the classical ones.

Support vector machines and wavelets for voice disorder sorting

We present an algorithm to distinguish between pathological and normal human voice signals based on discrete wavelet transforms (DWT) and support vector machines (SVM). The former is used for time-frequency analysis and provides quantitative evaluation of signal characteristics. The latter is used for the final classification. The technique leads to an adequate larynx pathology classifier with over 95% of classification accuracy

Larynx virtual surgery

This paper presents a novel computational method designed to assist phonologists to anticipate the effects produced in the voice, as a result of physical and mechanical alterations of the larynx model, due to a surgery to correct dysphonia. The technique is based on images obtained from endoscopic exams of the larynx. The main objective of the study was to use the active contours method to develop a larynx model based on vocal fold and glottis movements. Starting with the recorded voice signal of subject, we filter the characteristics of the glottal pulse obtained from the image exam, assuming that the dysphonia is caused by irregularities of the larynx. The modifications made in the glottis model are used to estimate a new glottal filter, which is then added to the filtered signal. Using this method, one can obtain a new voice that maintains the individuals personal characteristics after virtual surgery modifications.

Linear prediction and discrete wavelet transform to identify pathology in voice signals

This work describes an algorithm to help in the identification of pathologically affected voices. Based on inverse linear prediction filter (LPC) and discrete wavelet transform (DWT), this method can be used in conjunction with other classifiers in order to improve them, by the addition of the new parameter we propose, DWT-RMS. Using no association with other methods, DWT-RMS gives quantitative evaluation of voice signals from male and female subjects of different ages and leads to an adequate larynx pathology classifier with 85.94% of classification accuracy, 0% of false negatives and 14.06% of false positives, to identify nodules in vocal folds.

A Fractal and Wavelet-Based Approach for Audio Coding.

Towards an optimization-oriented approach for audio coding, this paper presents improved rate-distortion and perceptual strategies for bit allocation. The algorithm is based on best basis wavelet-packet trees and fractal dimension calculation. Transparent coding of high quality audio, signals sampled at 44.1 KHz using 16 bits PCM, is effectively achieved at low bit rates. Real time working of the decoder is confirmed, reassuring the usability of the proposed technique