Wavelet packet cepstral analysis for speaker recognition

Author

Kinney, Albert ; Stevens, John

Author_Institution

U.S Naval Security Group Activity, Yokosuka, Japan

Volume

1

fYear

2002

fDate

3-6 Nov. 2002

Firstpage

206

Abstract

A novel processing technique for speaker recognition applications is introduced. It was shown that feature extraction based on cepstral analysis of the wavelet packet decomposition can provide significant inter-speaker separation. This idea is based on deconvolution of the vocal tract and excitation source components through homomorphic decomposition of a signal´s multiresolution wavelets. A simple neural network technique is employed to classify the feature vector obtained through wavelet packet cepstral analysis.

Keywords

cepstral analysis; deconvolution; feature extraction; neural nets; speaker recognition; wavelet transforms; cepstral analysis; excitation source components; homomorphic decomposition; interspeaker separation; neural network; signal multiresolution wavelets; speaker recognition; vocal tract deconvolution; wavelet packet decomposition; Cepstral analysis; Cepstrum; Feature extraction; Frequency; Loudspeakers; Signal resolution; Speaker recognition; Time domain analysis; Wavelet analysis; Wavelet packets;

fLanguage

English

Publisher

ieee

Conference_Titel

Signals, Systems and Computers, 2002. Conference Record of the Thirty-Sixth Asilomar Conference on

Conference_Location

Pacific Grove, CA, USA

ISSN

1058-6393

Print_ISBN

0-7803-7576-9

Type

conf

DOI

10.1109/ACSSC.2002.1197177

Filename

1197177