Paper Info
Title
Double Gauss Based Unsupervised Score Normalization in Speaker Verification
Abstract
In text-independent speaker verification, unsupervised mode can improve system performance. In traditional systems, the speaker model is updated when a test speech has a score higher than a particular threshold; we call this unsupervised model training. In this paper, an unsupervised score normalization is proposed. A target speaker score Gauss and an impostor score Gauss are set up as a prior; the parameters of the impostor score model are updated using the test score. Then the test score is normalized by the new impostor score model. When the unsupervised score normalization, unsupervised model training and factor analysis are adopted in the NIST 2006 SRE core test, the EER of the system is 4.29%.
Year
DOI
Venue
2008
10.1109/CHINSL.2008.ECP.53
ISCSLP
Keywords
Field
DocType
unsupervised model training,text-independent speaker verification,unsupervised score normalization,index terms— speaker verification,speaker recognition,target speaker score gauss,gaussian processes,unsupervised mode,factor analysis,mathematical model,system performance,indexing terms,speech,nist
Speaker verification,Gauss,Normalization (statistics),Pattern recognition,Test score,Computer science,Speech recognition,NIST,Speaker recognition,Artificial intelligence,Gaussian process
Conference
ISBN
Citations 
PageRank 
978-1-4244-2943-1
1
0.36
References 
Authors
5
3
Name
Order
Citations
PageRank
Wu Guo1126.80
Li-Rong Dai21070117.92
Ren-Hua Wang334441.36