Glottal information based spectral recuperation in multi-channel speaker recognition

Authors:
Pu Yang;Yingchun Yang;Zhaohui Wu
Affiliations:
College of Computer Science and Technology, Zhejiang University, Hangzhou, P R China;College of Computer Science and Technology, Zhejiang University, Hangzhou, P R China;College of Computer Science and Technology, Zhejiang University, Hangzhou, P R China
Venue:
SINOBIOMETRICS'04 Proceedings of the 5th Chinese conference on Advances in Biometric Person Authentication
Year:
2004

Citing 1
Cited 0

Handset-Dependent Background Models for Robust Text-Independent Speaker Recognition

ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97)-Volume 2 - Volume 2

Quantified Score

Hi-index	0.00

Visualization

Abstract

Recently, expansion of mobile communication arise lots of research interests in robust speaker recognition under multi-channel environments Thus, building robust automatic speaker recognition (ASR) system becomes an urgent and necessary problem Though glottal information was successfully used in many speaker recognition systems, the spectral variations caused by it were not taken into account under multi-channel environment In this paper, a method that can utilize this influence, using both long-term and short-term glottal information, is proposed Through this recuperation, spectral features will behave more robust in text-independent ASR system under channel influences Our method was applied to the large multi-channel SRMC corpus The experimental works show promising results.