Development of a speaker recognition system using wavelets and artificial neural networks

Author

Woo, Siew Chan ; Lim, Chee Peng ; Osman, R.

Author_Institution

Sch. of Distance Educ., Univ. Sains Malaysia, Penang, Malaysia

fYear

2001

fDate

2001

Firstpage

413

Lastpage

416

Abstract

We address the problem of speaker recognition from speech signals. The study focuses on the development of a speaker recognition system comprising two modules: a wavelet-based feature extractor, and a neural network-based classifier. We have conducted a number of experiments to investigate the applicability of a discrete Wavelet transform (DWT) in extracting discriminative features from the speech signals, and have examined various models from the adaptive resonance theory (ART) family of neural networks in classifying the extracted features. The results indicate that DWT could be a potential feature extraction tool for speaker recognition. In addition, the ART-based classifiers have yielded very promising recognition accuracy at more than 81%

Keywords

ART neural nets; discrete wavelet transforms; feature extraction; speaker recognition; ART neural networks; adaptive resonance theory neural networks; discrete Wavelet transform; feature classification; neural network-based classifier; speaker recognition system; speech signals; wavelet-based feature extraction; Artificial neural networks; Cepstral analysis; Continuous wavelet transforms; Data mining; Discrete wavelet transforms; Feature extraction; Filtering; Hidden Markov models; Speaker recognition; Speech;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Multimedia, Video and Speech Processing, 2001. Proceedings of 2001 International Symposium on

Conference_Location

Hong Kong

Print_ISBN

962-85766-2-3

Type

conf

DOI

10.1109/ISIMP.2001.925421

Filename

925421