Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/16309
Title: Articulatory-feature based sequence kernel for high-level speaker verification
Authors: Zhang, SX
Mak, MW 
Keywords: SVM
Speaker verification
Articulatory
Features
Kernels
Pronunciation models
Issue Date: 2008
Publisher: IEEE
Source: 2008 International Conference on Machine Learning and Cybernetics, 12-15 July 2008, Kunming, p. 2799-2804 How to cite?
Abstract: Research has shown that articulatory feature-based phonetic-class pronunciation models (AFCPMs) can capture the pronunciation characteristics of speakers. However, the scoring method used in AFCPMs does not explicitly use the discriminative information available in the training data. To harness this information, this paper proposes converting speaker models to supervectors by stacking the discrete densities in AFCPMs. An AF-kernel is constructed from the supervectors of target speakers, background speakers, and claimants. An AF-kernel based SVM is then trained to classify the super-vectors. Results show that AF-kernel scoring is complementary to likelihood-ratio scoring, leading to better performance when the two scoring methods are combined.
URI: http://hdl.handle.net/10397/16309
ISBN: 978-1-4244-2095-7
978-1-4244-2096-4 (E-ISBN)
DOI: 10.1109/ICMLC.2008.4620884
Appears in Collections:Conference Paper

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

Page view(s)

28
Last Week
0
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.