Adaptive recognition method based on posterior use of distribution pattern of output probabilities

Author

Jin-Song Zhong ; Dai, Beiqian ; Wang, Changfu ; Kwan, Hingkeung ; Hirose, Keikichi

Author_Institution

Dept. of Electr. Eng., China Univ. of Sci. & Technol., Anhui, China

Volume

2

fYear

1996

fDate

3-6 Oct 1996

Firstpage

1129

Abstract

Proposes a new adaptation scheme for speaker-independent recognition. The basic idea lies in the change of the likelihood from ordinary HMM scores to combined observational scores. The new likelihood is computed based on a combination of HMM scores which we call a `pattern of output probabilities distribution´ (POPD). The system needs to calculate only the POPD for each new speaker. Re-estimation of acoustic model parameters is unnecessary. Preliminary experiments on Chinese isolated-syllable recognition indicate the method´s effectiveness

Keywords

adaptive signal processing; hidden Markov models; probability; speech recognition; Chinese isolated-syllable recognition; acoustic model parameters; adaptation scheme; combined observational scores; hidden Markov model scores; likelihood; output probabilities distribution pattern; posterior use; speaker-independent recognition; Acoustic measurements; Adaptive systems; Distributed computing; Hidden Markov models; Loudspeakers; Partial response channels; Pattern recognition; Probability; Speech processing; Speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Spoken Language, 1996. ICSLP 96. Proceedings., Fourth International Conference on

Conference_Location

Philadelphia, PA

Print_ISBN

0-7803-3555-4

Type

conf

DOI

10.1109/ICSLP.1996.607805

Filename

607805