Discriminative algorithm for compacting mixture models with application to language recognition

Yossi Bar-Yosef*, Yuval Bistritz

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

In this paper we explore a discriminative algorithm for compacting large order mixture models. Several studies investigated efficient algorithms for finding a reduced-order model that best approximates a referenced model using only the original mixture parameters. Recently, a discriminative approach named maximum correct association (MCA) was introduced to efficiently construct a set of compact models for improved classification. In this paper we suggest a two stage procedure that applies the MCA algorithm after initially obtaining a compact model through the variational-EM method (which is a non-discriminative algorithm). The proposed method is validated in a language recognition task where large order mixture models are compacted into low order models. Experiments showed that the MCA-refined models performed consistently better than reduced models derived with the non-discriminative methods including boosting performance over the standard maximum-likelihood trained from the original data.

Original languageEnglish
Title of host publicationProceedings of the 20th European Signal Processing Conference, EUSIPCO 2012
Pages2203-2207
Number of pages5
StatePublished - 2012
Event20th European Signal Processing Conference, EUSIPCO 2012 - Bucharest, Romania
Duration: 27 Aug 201231 Aug 2012

Publication series

NameEuropean Signal Processing Conference
ISSN (Print)2219-5491

Conference

Conference20th European Signal Processing Conference, EUSIPCO 2012
Country/TerritoryRomania
CityBucharest
Period27/08/1231/08/12

Keywords

  • Gaussian mixture models
  • discriminative learning
  • hierarchical clustering
  • language recognition

Fingerprint

Dive into the research topics of 'Discriminative algorithm for compacting mixture models with application to language recognition'. Together they form a unique fingerprint.

Cite this