Please use this identifier to cite or link to this item:
Title: A new two-stage scoring normalization approach to speaker verification
Authors: Mak, MW 
Zhang, WD
He, MX
Keywords: Decision theory
Formal verification
Speaker recognition
Issue Date: 2001
Source: Proceedings of 2001 International Symposium on Intelligent Multimedia, Video and Speech Processing, 2001, 02 May 2001-04 May 2001, Hong Kong, p. 107-110 How to cite?
Abstract: In speaker verification, the cohort and world models have been separately used for scoring normalization. The authors embed the two models in elliptical basis function networks and propose a two-stage decision procedure for improving verification performance. The procedure begins with normalization of an utterance by a world model. If the difference between the resulting score and a world threshold is sufficiently large, the claimant is accepted or rejected immediately. Otherwise, the score will be normalized by a cohort model, and the resulting score will be compared with a cohort threshold to make a final accept/reject decision. Experimental evaluations based on the YOHO corpus suggest that the two-stage method achieves a lower error rate as compared to the case where only one background model is used
ISBN: 962-85766-2-3
DOI: 10.1109/ISIMP.2001.925343
Appears in Collections:Conference Paper

View full-text via PolyU eLinks SFX Query
Show full item record


Last Week
Last month
Citations as of Feb 18, 2019

Page view(s)

Last Week
Last month
Citations as of Feb 17, 2019

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.