The Lincoln large-vocabulary stack-decoder HMM CSR

Author

Paul, Douglas B. ; Necioglu, B.F.

Author_Institution

MIT Lincoln Lab., Lexington, MA, USA

Volume

2

fYear

1993

fDate

27-30 April 1993

Firstpage

660

Abstract

Recognition of the Wall Street Journal (WSJ) pilot database, a continuous-speech-recognition (CSR) database which supports 5 K, 20 K, and up to 64 K-word CSR tasks, is examined. The original Lincoln tied-mixture hidden Markov model (HMM) CSR was implemented using a time-synchronous beam-pruned search of a static network which does not extend well to this task because the recognition network would be too large. Therefore, the recognizer has been converted to a stack decoder-based search strategy. This decoder has been shown to function effectively on up to 64 K-word recognition of continuous speech. Recognition-time adaptation has also been added to the recognizer. The acoustic modeling techniques and the implementation of the stack decoder used to obtain these results are described.<>

Keywords

decoding; hidden Markov models; search problems; speech recognition; vocabulary; HMM; Lincoln large-vocabulary stack-decoder; Wall Street Journal; acoustic modeling techniques; beam-pruned search; continuous speech recognition; search strategy; stack decoder; tied-mixture hidden Markov model;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1993. ICASSP-93., 1993 IEEE International Conference on

Conference_Location

Minneapolis, MN, USA

ISSN

1520-6149

Print_ISBN

0-7803-7402-9

Type

conf

DOI

10.1109/ICASSP.1993.319396

Filename

319396