Fuzzy C-Means Clustering-Based Speaker Verification

Dat Tran, Max Wagner

Research output: A Conference proceeding or a Chapter in BookConference contributionpeer-review

18 Citations (Scopus)

Abstract

In speaker verification, a claimed speaker’s score is computed to accept or reject the speaker claim. Most of the current normalisation methods compute the score as the ratio of the claimed speaker’s and the impostors’ likelihood functions. Based on analysing false acceptance error occured by the current methods, we propose a fuzzy c-means clusteringbased normalisation method to find a better score which can reduce that error. Experiments performed on the TI46 and the ANDOSL speech corpora show better results for the proposed method
Original languageEnglish
Title of host publicationAFSS International Conference on Fuzzy Systems, AFSS 2002
Subtitle of host publicationAdvances in Soft Computing
EditorsN. R. Pal, M. Sugeno
Place of PublicationGermany
PublisherSpringer
Pages318-324
Number of pages7
ISBN (Print)9783540431503
DOIs
Publication statusPublished - 2002
Event2002 AFSS International Conference on Fuzzy Systems - Calcutta, India
Duration: 3 Feb 20026 Feb 2002

Conference

Conference2002 AFSS International Conference on Fuzzy Systems
Country/TerritoryIndia
CityCalcutta
Period3/02/026/02/02

Fingerprint

Dive into the research topics of 'Fuzzy C-Means Clustering-Based Speaker Verification'. Together they form a unique fingerprint.

Cite this