Fast scoring for mixture of PLDA in i-vector/PLDA speaker verification

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

2 Citations (Scopus)

Abstract

With the ubiquitous of mobile phones, users of speaker verification systems will perform authentication anywhere at anytime. As a result, practical speaker verification systems need to deal with utterances of different noise levels. Recently, an SNR-dependent mixture of PLDA model was proposed to deal with such practical situation. However, the scoring function of this model is significantly more complex than the conventional one. This paper proposes a method to reduce the computation burden of this mixture PLDA model. The idea is based on the observation that for most utterances, the posterior probabilities of SNR are very sparse so that it is possible to consider the top Gaussian only during scoring. The method effectively reduces the computational complexity from O(K2D3) to O(D3), where K and D are the number of mixtures and i-vector dimension, respectively. Experimental results based on NIST 2012 SRE suggest that the proposed method can reduce computation time by 60% with very minor degradation in performance.
Original languageEnglish
Title of host publication2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015
PublisherIEEE
Pages587-593
Number of pages7
ISBN (Electronic)9789881476807
DOIs
Publication statusPublished - 19 Feb 2016
Event2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015 - Hong Kong, Hong Kong
Duration: 16 Dec 201519 Dec 2015

Conference

Conference2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015
CountryHong Kong
CityHong Kong
Period16/12/1519/12/15

ASJC Scopus subject areas

  • Artificial Intelligence
  • Modelling and Simulation
  • Signal Processing

Cite this