The use of wavelet packet transform and artificial neural networks in analysis and classification of dysphonic voices

César David Paredes Crovato; Adalberto Schuck

doi:10.1109/TBME.2006.889780

The use of wavelet packet transform and artificial neural networks in analysis and classification of dysphonic voices

IEEE Trans Biomed Eng. 2007 Oct;54(10):1898-900. doi: 10.1109/TBME.2006.889780.

Authors

César David Paredes Crovato¹, Adalberto Schuck

Affiliation

¹ Departamento de Engenharia Elétrica, Universidade Federal do Rio Grande do Sul, Porto Alegre, RS, CEP 90.035-190, Brazil. cesarcrovato@yahoo.com.br

PMID: 17926690
DOI: 10.1109/TBME.2006.889780

Abstract

This paper presents a dysphonic voice classification system using the wavelet packet transform and the best basis algorithm (BBA) as dimensionality reductor and 06 artificial neural networks (ANN) acting as specialist systems. Each ANN was a 03-layer multilayer perceptron with 64 input nodes, 01 output node and in the intermediary layer the number of neurons depends on the related training pathology group. The dysphonic voice database was separated in five pathology groups and one healthy control group. Each ANN was trained and associated with one of the 06 groups, and fed by the best base tree (BBT) nodes' entropy values, using the multiple cross validation (MCV) method and the leave-one-out (LOO) variation technique and success rates obtained were 87.5%, 95.31%, 87.5%, 100%, 96.87% and 89.06% for the groups 01 to 06, respectively.

MeSH terms

Algorithms*
Artificial Intelligence*
Diagnosis, Computer-Assisted / methods*
Humans
Neural Networks, Computer
Reproducibility of Results
Sensitivity and Specificity
Signal Processing, Computer-Assisted*
Sound Spectrography / methods*
Voice Disorders / diagnosis*