5th International Conference on Spoken Language Processing

Sydney, Australia
November 30 - December 4, 1998

A Context-Dependent Approach for Speaker Verification Using Sequential Decision

Hideki Noda (1), Katsuya Harada (1), Eiji Kawaguchi (1), Hidefumi Sawai (2)

(1) Kyushu Institute of Technology, Japan
(2) Communications Research Laboratory, Japan

This paper is concerned about speaker verification (SV) using the sequential probability ratio test (SPRT). In the SPRT input samples are usually assumed to be i.i.d. samples from a probability density function because an on-line probability computation is required. Feature vectors used in speech processing obviously do not satisfy the assumption and therefore the correlation between successive feature vectors has not been considered in conventional SV using the SPRT. The correlation can be modeled by the hidden Markov model (HMM) but unfortunately the HMM can not be directly applied to the SPRT because of statistical dependence of input samples. This paper proposes a method of HMM probability computation using the mean field approximation to resolve this problem, where the probability of whole input samples is nominally represented as the product of probability of each sample as if input samples were independent each other.

Full Paper

Bibliographic reference.  Noda, Hideki / Harada, Katsuya / Kawaguchi, Eiji / Sawai, Hidefumi (1998): "A context-dependent approach for speaker verification using sequential decision", In ICSLP-1998, paper 0108.