A confidence-score based unsupervised MAP adaptation for speech recognition

Author

Wang, Dagen ; Narayanan, Shrikanth S.

Author_Institution

Dept. of Electr. Eng., Univ. of Southern California, Los Angeles, CA, USA

Volume

1

fYear

2002

fDate

3-6 Nov. 2002

Firstpage

222

Abstract

In this paper, a method of confidence-score based MAP (maximum a posteriori) adaptation in speech recognition is proposed and evaluated. Using confidence scores to dynamically decide the weight of the priors is shown to have good performance improvement in an unsupervised incremental adaptation. The side effect of vocabulary mismatch in adaptation is also effectively controlled by this way. This paper first gives theoretical analysis and then shows some experimental results. Several extensions are made and also discussed.

Keywords

maximum likelihood estimation; speech recognition; ASR; MAP; MLLR; automatic speech recognition; confidence score; maximum a posteriori adaptation; maximum likelihood linear regression adaptation; speech adaptation; vocabulary mismatch; Adaptation model; Automatic control; Automatic speech recognition; Automatic testing; Decoding; Hidden Markov models; Maximum likelihood linear regression; Probability; Speech recognition; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Signals, Systems and Computers, 2002. Conference Record of the Thirty-Sixth Asilomar Conference on

Conference_Location

Pacific Grove, CA, USA

ISSN

1058-6393

Print_ISBN

0-7803-7576-9

Type

conf

DOI

10.1109/ACSSC.2002.1197181

Filename

1197181