Technical Program

Paper Detail

Paper:	SLP-L10.5
Session:	Speaker Adaptation
Time:	Friday, May 19, 11:20 - 11:40
Presentation:	Lecture
Topic:	Speech and Spoken Language Processing: Speaker adaptation and normalization (e.g., VTLN)
Title:	Reference Speaker Weighting Adaptation for Sub-phonetic Polynomial Segment Model
Authors:	Siu-Kei Au yeung, Man-Hung Siu, Hong Kong University of Science and Technology, Hong Kong SAR of China
Abstract:	Speaker adaptation has been widely used in speech recognition. With small amount of adaptation data, Reference Speaker Weighting (RSW) adaptation was previously proposed for fast HMM adaptation, and has been shown to outperform the more commonly used maximum likelihood linear regression (MLLR) adaptation. Extending our previous work of applying the Polynomial Segment Models (PSMs) in large vocabulary continuous speech recognition (LVCSR) on the WSJ Nov 92 evaluation, we derive the PSM-based RSW fast adaptation technique in this paper. Different from the HMMs, in which the model means are constants within a state, the PSM means are curves represented by polynomials. Experimental results showed that the PSM-based RSW gave approximately the same relative improvement over the unadapted model as in the HMM case. Comparing the PSM-based RSW and MLLR, the PSM-based RSW is more powerful when the amount of adaptation data available is limited. However, it could quickly saturate with increase in adaptation data.