Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/18809
Title: Environment adaptation for robust speaker verification by cascading maximum likelihood linear regression and reinforced learning
Authors: Yiu, KK
Mak, MW 
Kung, SY
Issue Date: 2007
Publisher: Academic Press Ltd Elsevier Science Ltd
Source: Computer speech and language, 2007, v. 21, no. 2, p. 231-246 How to cite?
Journal: Computer Speech and Language 
Abstract: In speaker verification over public telephone networks, utterances can be obtained from different types of handsets. Different handsets may introduce different degrees of distortion to the speech signals. This paper attempts to combine a handset selector with (1) handset-specific transformations, (2) reinforced learning, and (3) stochastic feature transformation to reduce the effect caused by the acoustic distortion. Specifically, during training, the clean speaker models and background models are firstly transformed by MLLR-based handset-specific transformations using a small amount of distorted speech data. Then reinforced learning is applied to adapt the transformed models to handset-dependent speaker models and handset-dependent background models using stochastically transformed speaker patterns. During a verification session, a GMM-based handset classifier is used to identify the most likely handset used by the claimant; then the corresponding handset-dependent speaker and background model pairs are used for verification. Experimental results based on 150 speakers of the HTIMIT corpus show that environment adaptation based on the combination of MLLR, reinforced learning and feature transformation outperforms CMS, Hnorm, Tnorm, and speaker model synthesis.
URI: http://hdl.handle.net/10397/18809
DOI: 10.1016/j.csl.2006.05.001
Appears in Collections:Journal/Magazine Article

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

SCOPUSTM   
Citations

6
Last Week
0
Last month
0
Citations as of Aug 13, 2017

WEB OF SCIENCETM
Citations

6
Last Week
0
Last month
0
Citations as of Aug 20, 2017

Page view(s)

35
Last Week
3
Last month
Checked on Aug 20, 2017

Google ScholarTM

Check

Altmetric



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