Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/7772
Title: Likelihood-ratio empirical kernels for i-vector based PLDA-SVM scoring
Authors: Rao, W
Mak, MW 
Keywords: I-vectors
Empirical kernel maps
Likelihood ratio kernels
Probabilistic linear discriminant analysis
Issue Date: 2013
Publisher: IEEE
Source: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 26-31 May 2013, Vancouver, BC, p. 7702-7706 How to cite?
Abstract: Likelihood ratio (LR) scoring in PLDA speaker verification systems only uses the information of background speakers implicitly. This paper exploits the notion of empirical kernel maps to incorporate background speaker information into the scoring process explicitly. This is achieved by training a scoring SVM for each target speaker based on a kernel in the empirical feature space. More specially, given a test i-vector and the identity of the target under test, a score vector is constructed by computing the LR scores of the test i-vector with respect to the target-speaker's i-vectors and a set of background-speakers' i-vectors. While in most situations, only one target-speaker i-vector is available for training the SVM, this paper demonstrates that if the enrollment utterance is sufficiently long, a number of target-speaker i-vectors can be generated by an utterance partitioning and resampling technique, resulting in much better scoring SVMs. Results on NIST 2010 SRE suggests that the idea of incorporating background speaker information into PLDA scoring through training speaker-dependent SVMs together with the utterance partitioning techniques can boost the performance of i-vector based PLDA systems significantly.
URI: http://hdl.handle.net/10397/7772
ISBN: 
ISSN: 1520-6149
DOI: 10.1109/ICASSP.2013.6639162
Appears in Collections:Conference Paper

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

SCOPUSTM   
Citations

5
Citations as of Sep 15, 2017

Page view(s)

38
Last Week
8
Last month
Checked on Sep 24, 2017

Google ScholarTM

Check

Altmetric



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