Maximum a Posteriori Adaptation of the Centroid Model for Speaker Verification

Author

Hautamaki, Ville ; Kinnunen, Tomi ; Karkkainen, I. ; Saastamoinen, Juhani ; Tuononen, Marko ; Franti, Pasi

Author_Institution

Univ. of Joensuu, Joensuu

Volume

15

fYear

2008

fDate

6/30/1905 12:00:00 AM

Firstpage

162

Lastpage

165

Abstract

Maximum a posteriori adapted Gaussian mixture model (GMM-MAP) is widely used in speaker verification. GMMs have three sets of parameters to be adapted: means, covariances, and weights. However, practice has shown that it is sufficient to adapt the means only. Motivated by this, we formulate maximum a posteriori vector quantization (VQ-MAP) procedure which stores and adapts the mean vectors (centroids) only. Experiments on the NIST 2001 and NIST 2006 corpora indicate that VQ-MAP gives comparable accuracy with GMM-MAP with simpler implementation and faster adaptation.

Keywords

Gaussian processes; maximum likelihood estimation; speaker recognition; vector quantisation; Gaussian mixture model; centroid model; maximum a posteriori adaptation; speaker verification; vector quantization; Application software; Computer science; Image processing; Maximum likelihood estimation; NIST; Speaker recognition; Speech processing; Testing; Training data; Vector quantization; Bayesian methods; centroid model; maximum a posteriori (MAP) adaptation; speaker verification; vector quantization;

fLanguage

English

Journal_Title

Signal Processing Letters, IEEE

Publisher

ieee

ISSN

1070-9908

Type

jour

DOI

10.1109/LSP.2007.914792

Filename

4439725