Vowel-non vowel decision using neural networks and rules

Author

Sirigos, John ; Darsinos, Vassilis ; Fakotakis, Nikos ; Kokkinakis, George

Author_Institution

Wire Commun. Lab., Patras Univ., Greece

Volume

1

fYear

1996

fDate

13-16 Oct 1996

Firstpage

510

Abstract

This paper describes a speaker independent vowel/non-vowel classifier based on neural networks and several rules. RASTA-PLP analysis of the speech signal resulting to mel-cepstral coefficients and a formant tracking method are used in order to provide the feature vectors for the MLP. To train and test the system we used a part of the TIMIT database. The results indicate that the performance of this classifier for speaker independent vowel classification is approximately 98.5% so it can be favorably used for speaker recognition or speech labeling purposes

Keywords

feature extraction; multilayer perceptrons; pattern classification; speaker recognition; speech processing; MLP; RASTA-PLP analysis; feature vectors; formant tracking method; mel-cepstral coefficients; neural networks; speaker independent vowel classifier; speaker recognition; speech labeling; speech signal analysis; vowel-non vowel decision; Cepstral analysis; Discrete Fourier transforms; Feature extraction; Frequency; Labeling; Neural networks; Spatial databases; Speaker recognition; Speech analysis; Speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Electronics, Circuits, and Systems, 1996. ICECS '96., Proceedings of the Third IEEE International Conference on

Conference_Location

Rodos

Print_ISBN

0-7803-3650-X

Type

conf

DOI

10.1109/ICECS.1996.582917

Filename

582917