Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/76009
Title: Fast scoring for PLDA with uncertainty propagation via i-vector grouping
Authors: Lin, WW 
Mak, MW 
Chien, JT
Keywords: Speaker verification
I-Vector/PLDA
Uncertainty Propagation
Duration mismatch
Issue Date: 2017
Publisher: Academic Press
Source: Computer speech and language, 2017, v. 45, p. 503-515 How to cite?
Journal: Computer speech and language 
Abstract: The i-vector/PLDA framework has gained huge popularity in text-independent speaker verification. This approach, however, lacks the ability to represent the reliability of i-vectors. As a result, the framework performs poorly when presented with utterances of arbitrary duration. To address this problem, a method called uncertainty propagation (UP) was proposed to explicitly model the reliability of an i-vector by an utterance-dependent loading matrix. However, the utterance-dependent matrix greatly complicates the evaluation of likelihood scores. As a result, PLDA with UP, or PLDA-UP in short, is far more computational intensive than the conventional PLDA. In this paper, we propose to group i-vectors with similar reliability, and for each group the utterance-dependent loading matrices are replaced by a representative one. This arrangement allows us to pre-compute a set of representative matrices that cover all possible i-vectors, thereby greatly reducing the computational cost of PLDA-UP while preserving its ability in discriminating the reliability of i-vectors. Experiments on NIST 2012 SRE show that the proposed method can perform as good as the PLDA with UP while the scoring time is only 3.18% of it.
URI: http://hdl.handle.net/10397/76009
ISSN: 0885-2308
EISSN: 1095-8363
DOI: 10.1016/j.csl.2017.02.009
Appears in Collections:Journal/Magazine Article

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

SCOPUSTM   
Citations

1
Citations as of May 12, 2018

WEB OF SCIENCETM
Citations

2
Last Week
0
Last month
Citations as of May 20, 2018

Page view(s)

3
Citations as of May 21, 2018

Google ScholarTM

Check

Altmetric


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