Iterative speaker adaptation for speech recognition

Author

Scholtz, F.J. ; du Preez, J.A.

Author_Institution

Dept. of Electr. & Electron. Eng., Stellenboch Univ., South Africa

fYear

1992

fDate

9/11/1992 12:00:00 AM

Firstpage

33

Lastpage

37

Abstract

A speaker-independent speech recognition system is desirable in many applications where speaker-specific data does not exist. It speaker-independent data is available, the system could be adapted to the specific speaker, thereby reducing the recognition error rate. A new, unsupervised speaker adaptation scheme which requires no prior training phase is proposed. The algorithm improves the recognition rate as more speech data becomes available, making it most suitable for real-time implementation. In the tests conducted this algorithm yields an improvement of almost 50% on the recognition error rate

Keywords

iterative methods; speech recognition; unsupervised learning; algorithm; real-time implementation; recognition error rate; speech recognition system; unsupervised speaker adaptation scheme; Cepstral analysis; Data engineering; Feature extraction; Filter bank; Hidden Markov models; Iterative algorithms; Speech recognition; Training data; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

Communications and Signal Processing, 1992. COMSIG '92., Proceedings of the 1992 South African Symposium on

Conference_Location

Cape Town

Print_ISBN

0-7803-0807-7

Type

conf

DOI

10.1109/COMSIG.1992.274317

Filename

274317