Temporal decomposition: a promising approach to VQ-based speaker identification

Author

Nguyen, Phu Chien ; Akagi, Masato ; Ho, Tu Bao

Author_Institution

Japan Adv. Inst. of Sci. & Technol., Ishikawa, Japan

Volume

1

fYear

2003

fDate

6-10 April 2003

Abstract

A new set of features is proposed that has been found to improve the performance of automatic speaker identification systems. The new set of features is referred to as "event targets". The new features have been derived from line spectral frequency (LSF) parameters using the so-called "temporal decomposition" (TD) technique. The number of feature vectors required for both the training and testing phases has been reduced by one-fifth compared to that of the traditional Mel-frequency cepstrum coefficients (MFCC) features, while the identification results obtained are comparable or even better. Also, we introduce one more application of TD (speaker recognition) in addition to speech coding, speech segmentation, and speech recognition. It shows that the event targets in TD can convey information about the identity of a speaker.

Keywords

learning (artificial intelligence); speaker recognition; vector quantisation; MFCC; Mel-frequency cepstrum coefficients; automatic speaker identification; event targets; feature vectors; line spectral frequency parameters; speaker recognition; speech coding; speech recognition; speech segmentation; temporal decomposition; Cepstrum; Feature extraction; Hidden Markov models; Mel frequency cepstral coefficient; Speaker recognition; Spectral analysis; Speech coding; Speech recognition; Testing; Vector quantization;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). 2003 IEEE International Conference on

ISSN

1520-6149

Print_ISBN

0-7803-7663-3

Type

conf

DOI

10.1109/ICASSP.2003.1198747

Filename

1198747