Acoustic vector resampling for GMMSVM-based speaker verification

Man Wai Mak, Wei Rao

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

2 Citations (Scopus)

Abstract

Using GMM-supervectors as the input to SVM classifiers (namely, GMM-SVM) is one of the promising approaches to text-independent speaker verification. However, one unad-dressed issue of this approach is the severe imbalance between the numbers of speaker-class utterances and impostor-class utterances available for training a speaker-dependent SVM. This paper proposes a resampling technique - namely utterance partitioning with acoustic vector resampling (UP-AVR) - to mitigate the data imbalance problem. Specifically, the sequence order of acoustic vectors in an enrollment utterance is first randomized; then the randomized sequence is partitioned into a number of segments. Each of these segments is then used to produce a GMM-supervector via MAP adaptation and mean vector concatenation. A desirable number of speaker-class su-pervectors can be produced by repeating this randomization and partitioning process a number of times. Experimental evaluations suggest that UP-AVR can reduce the EER of GMM-SVM systems by about 10%.
Original languageEnglish
Title of host publicationProceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010
Pages1449-1452
Number of pages4
Publication statusPublished - 1 Dec 2010
Event11th Annual Conference of the International Speech Communication Association: Spoken Language Processing for All, INTERSPEECH 2010 - Makuhari, Chiba, Japan
Duration: 26 Sep 201030 Sep 2010

Conference

Conference11th Annual Conference of the International Speech Communication Association: Spoken Language Processing for All, INTERSPEECH 2010
CountryJapan
CityMakuhari, Chiba
Period26/09/1030/09/10

ASJC Scopus subject areas

  • Language and Linguistics
  • Speech and Hearing

Cite this