Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/30369
Title: Speaker verification via high-level feature-based phonetic-class pronunciation modeling
Authors: Zhang, SX
Mak, MW 
Meng, HM
Keywords: Articulatory features
NIST speaker recognition evaluation
Phonetic classes
Pronunciation modeling
Speaker verification
Issue Date: 2007
Publisher: Institute of Electrical and Electronics Engineers
Source: IEEE transactions on computers, 2007, v. 56, no. 9, p. 1189-1198 How to cite?
Journal: IEEE transactions on computers 
Abstract: It has recently been shown that the pronunciation characteristics of speakers can be represented by articulatory featurebased conditional pronunciation models (AFCPMs). However, the pronunciation models are phoneme dependent, which may lead to speaker models with low discriminative power when the amount of enrollment data is limited. This paper proposes mitigating this problem by grouping similar phonemes into phonetic classes and representing background and speaker models as phonetic-class dependent density functions. Phonemes are grouped by 1) vector quantizing the discrete densities in the phoneme-dependent universal background models, 2) using the phone properties specified in the classical phoneme tree, or 3) combining vector quantization and phone properties. Evaluations based on the 2000 NIST SRE show that this phonetic-class approach effectively alleviates the data spareness problem encountered in conventional AFCPM, which results in better performance when fused with acoustic features.
URI: http://hdl.handle.net/10397/30369
ISSN: 0018-9340
EISSN: 1557-9956
DOI: 10.1109/TC.2007.1081
Appears in Collections:Journal/Magazine Article

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

SCOPUSTM   
Citations

10
Last Week
0
Last month
0
Citations as of Nov 10, 2017

WEB OF SCIENCETM
Citations

9
Last Week
0
Last month
1
Citations as of Sep 30, 2017

Page view(s)

42
Last Week
2
Last month
Checked on Nov 19, 2017

Google ScholarTM

Check

Altmetric



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