Speaker Verification Using Complementary Information from Vocal Source and Vocal Tract

Abstract

This paper describes a speaker verification system which uses two complementary acoustic features: Mel-frequency cepstral coefficients (MFCC) and wavelet octave coefficients of residues (WOCOR). While MFCC characterizes mainly the spectral envelope, or the formant structure of the vocal tract system, WOCOR aims at representing the spectro-temporal characteristics of the vocal source excitation. Speaker verification experiments carried out on the ISCSLP 2006 SRE database demonstrate the complementary contributions of MFCC and WOCOR to speaker verification. Particularly, WOCOR performs even better than MFCC in single channel speaker verification task. Combining MFCC and WOCOR achieves higher performance than using MFCC only in both single and cross channel speaker verification tasks.

DOI: 10.1007/11939993_54

Extracted Key Phrases

5 Figures and Tables

Cite this paper

@inproceedings{Zheng2006SpeakerVU, title={Speaker Verification Using Complementary Information from Vocal Source and Vocal Tract}, author={Nengheng Zheng and Ning Wang and Tan Lee and Pak-Chung Ching}, booktitle={ISCSLP}, year={2006} }