Title :
Reference Speaker Weighting Adaptation for Sub-Phonetic Polynomial Segment Models
Author :
Yeung, Siu-Kei Au ; Siu, Man-Hung
Author_Institution :
Dept. of Electr. & Electron. Eng., Hong Kong Univ. of Sci. & Technol., Kowloon
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
Keywords :
polynomials; speaker recognition; large vocabulary continuous speech recognition; reference speaker weighting adaptation; speech recognition; sub-phonetic polynomial segment models; Acoustics; Gold; Hidden Markov models; Loudspeakers; Maximum likelihood linear regression; Notice of Violation; Polynomials; Speech processing; Speech recognition; Vocabulary;
Conference_Titel :
Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. 2006 IEEE International Conference on
Conference_Location :
Toulouse
Print_ISBN :
1-4244-0469-X
DOI :
10.1109/ICASSP.2006.1660000