Loading [MathJax]/extensions/MathMenu.js
A General Bayesian Model for Speaker Verification | CIE Journals & Magazine | IEEE Xplore

A General Bayesian Model for Speaker Verification


Abstract:

This paper presents a general Bayesian model for speaker verification tasks. It is a generative probability model. Due to its simple analytical property, a computationall...Show More

Abstract:

This paper presents a general Bayesian model for speaker verification tasks. It is a generative probability model. Due to its simple analytical property, a computationally efficient expectation-maximization algorithm can be derived to obtain the model parameters. A closed-form solution, which allows the scalable size of enrollment set, is given in a full Bayesian way for making speaker verification decisions. Factor analysis technique is employed to model the speaker-specific components, then the redundant information in this model will be dropped. Experimental results are evaluated by both equal error rate and minimum detection cost function. The proposed approach shows promising results on the National institute of standards and technology (NIST) Speaker recognition evaluation (SRE) 2010 extended and 2012 core tasks. Significant improvement is obtained when comparing with Gaussian probabilistic linear discriminant analysis, especially under phone-call conditions and mismatched train-test channel conditions. Contrast experimental results with other popular generative probability models are also presented in this paper.
Published in: Chinese Journal of Electronics ( Volume: 25, Issue: 6, November 2016)
Page(s): 1045 - 1051
Date of Publication: November 2016

ISSN Information:

Funding Agency:


References

References is not available for this document.