Bilinear Model-Based Maximum Likelihood Linear Regression Speaker Adaptation Framework | IEEE Journals & Magazine | IEEE Xplore

Bilinear Model-Based Maximum Likelihood Linear Regression Speaker Adaptation Framework


Abstract:

This letter proposes a novel framework for speaker adaptation, using bilinear model-based maximum likelihood linear regression (MLLR) method. First, a set of speaker mode...Show More

Abstract:

This letter proposes a novel framework for speaker adaptation, using bilinear model-based maximum likelihood linear regression (MLLR) method. First, a set of speaker models is decomposed into the style factor identified as each speaker's characteristics and the common content factor across the speakers, by the bilinear model. Then, using some adaptation data from a new speaker, the speaker-specific model is generated by properly adjusting the dimensionality of the content factor and estimating a new style factor simultaneously. Experimental results show that the proposed framework outperforms MLLR with fewer number of parameters to be estimated.
Published in: IEEE Signal Processing Letters ( Volume: 16, Issue: 12, December 2009)
Page(s): 1063 - 1066
Date of Publication: 11 August 2009

ISSN Information:


References

References is not available for this document.