Lucimar Sasso Vieira

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.

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.

A Fractal-Based Approach for Speech Segmentation

Nowadays, fractal analysis has been successfully applied to digital speech processing, particularly for word and phoneme segmentation, which represents one of the fundamental steps in automatic speech recognition systems. The practical use of fractal analysis for this purpose should match two principles: low computational cost, to allow the use in real-time, and accuracy in the results, in order to produce a satisfactory segmentation, sending the correct data to the classifier. Aiming at meeting these two requirements, this work proposes a technique for speech segmentation based on the fractal dimension, which is obtained by using the discrete wavelet transform that avoids the use of 1/k pre-filtering. Many families of wavelets are presented and compared, and the results assure the efficacy of the proposed method.

SPOKEN DOCUMENT SUMMARIZATION BASED ON DYNAMIC TIME WARPING AND WAVELETS

This work presents a spoken document summarization (SDS) scheme that is based on an improved version of the Dynamic Time Warping (DTW) algorithm, and on the Discrete Wavelet Transform (DWT). Tests and results with sentences extracted from TIMIT speech corpus show the efficacy of the proposed technique.

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

Introducing the Discrete Morphlet Transform and its Applications for Voice Conversion

This paper introduces Morph let, a new wavelet transform adapted for voice conversion purposes. The paradigm of joint time-frequency-shape analysis of discrete-time signals, possible by means of the Discrete Shape let Transform (DST), is the basis used for the construction of Morph lets. The results assure the efficacy of the proposed transform, which is able, by itself and with the help of no other tool such as a neural network, to carry out the task, totally.

On the Determination of Epsilon during Discriminative GMM Training

Discriminative training of Gaussian Mixture Models (GMMs) for speech or speaker recognition purposes is usually based on the gradient descent method, in which the iteration step-size, epsilon, uses to be defined experimentally. In this letter, we derive an equation to adaptively determine epsilon, by showing that the second-order Newton-Raphson iterative method to find roots of equations is equivalent to the gradient descent algorithm.

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

A matched FIR filter bank for audio coding

This paper describes a novel technique for audio coding, a lossy compression algorithm, that considers perceptual and rate-distortion criteria. It is based on matched finite impulse response (FIR) wavelet-packet-like filter banks, the filter coefficients being produced adoptively according to the input signal. This technique achieves perceptually transparent coding of high-quality audio, signals sampled at 44.1 KHz - 16 bits PCM, at bit rates of about 54 - 64 Kbps. The matched filter-bank makes a time-frequency-shape analysis, reducing the number of sub-bands requiring quantization. The decoder that implements this algorithm works effectively in real time. This reassures the efficacy of our technique.