Document Type
Conference Proceeding
Publication Date
12-1999
Abstract
This paper presents a new recursive Bayesian learning approach for transformation parameter estimation in speaker adaptation. Our goal is to incrementally transform (or adapt) the entire set of HMM parameters for a new speaker or new acoustic enviroment from a small amount of adaptation data. By establishing a clustering tree of HMM Gaussian mixture components, the finest affine transformation parameters for individual HMM Gaussian mixture components can be dynamically searched. The on-line Bayesian learning technique proposed in our recent work is used for recursive maximum a posteriori estimation of affine transformation parameters. Speaker adaptation experiments using a 26-letter English alphabet vocabulary are conducted, and the viability of the on-line learning framework is confirmed.
Repository Citation
Wang, S.,
& Zhao, Y.
(1999). On-Line Bayesian Tree-Structured Transformation of Hidden Markov Models for Speaker Adaptation. .
https://corescholar.libraries.wright.edu/knoesis/1021
Included in
Bioinformatics Commons, Communication Technology and New Media Commons, Databases and Information Systems Commons, OS and Networks Commons, Science and Technology Studies Commons
Comments
Presented at the IEEE Automatic Speech Recognition and Understanding Workshop, Keystone, CO, December 12-15, 1999.