Effect of window size and shift period in mel-warped cepstral feature extraction on GMM-based speaker verification

Authors:
C. C. Leung;Y. S. Moon
Affiliations:
Department of Computer Science and Engineering, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong;Department of Computer Science and Engineering, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong
Venue:
AVBPA'03 Proceedings of the 4th international conference on Audio- and video-based biometric person authentication
Year:
2003

Citing 5
Cited 1

Fundamentals of speech recognition

Fundamentals of speech recognition
Speaker identification and verification using Gaussian mixture speaker models

Speech Communication
The world according to wavelets: the story of a mathematical technique in the making

The world according to wavelets: the story of a mathematical technique in the making
Speech recognition: theory and C++ implementation

Speech recognition: theory and C++ implementation
A speaker verification system using alpha-nets

ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference

Fixed-point GMM-based speaker verification over mobile embedded system

WBMA '03 Proceedings of the 2003 ACM SIGMM workshop on Biometrics methods and applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper investigates how window size and shift period affect the performance of a speaker verification system. Specifically, we investigate their effects on verification accuracy and computation time of speaker verification systems built using the mel-warped cepstral feature extraction and Guassian Mixture Model. Experiments show that window size should not be larger than a critical point, which is determined by testing with a set of registered speakers. Otherwise, the computation time increases while the verification accuracy decreases.