Articulatory-feature based sequence kernel for high-level speaker verification

Shi Xiong Zhang, Man Wai Mak

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

Abstract

Research has shown that articulatory feature-based phoneticclass pronunciation models (AFCPMs) can capture the pronunciation characteristics of speakers. However, the scoring method used in AFCPMs does not explicitly use the discriminative information available in the training data. To harness this information, this paper proposes converting speaker models to supervectors by stacking the discrete densities in AFCPMs. An AF-kernel is constructed from the supervectors of target speakers, background speakers, and claimants. An AF-kernel based SVM is then trained to classify the supervectors. Results show that AF-kernel scoring is complementary to likelihood-ratio scoring, leading to better performance when the two scoring methods are combined.
Original languageEnglish
Title of host publicationProceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC
Pages2799-2804
Number of pages6
Volume5
DOIs
Publication statusPublished - 25 Dec 2008
Event7th International Conference on Machine Learning and Cybernetics, ICMLC - Kunming, China
Duration: 12 Jul 200815 Jul 2008

Conference

Conference7th International Conference on Machine Learning and Cybernetics, ICMLC
Country/TerritoryChina
CityKunming
Period12/07/0815/07/08

Keywords

  • Articulatory features
  • Kernels
  • Pronunciation models
  • Speaker verification
  • SVM

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction
  • Control and Systems Engineering

Cite this