Time-synchronous continuous speech recognizer driven by a context-free grammar

Author

Shimizu, Tsuyoshi ; Monzen, Seikou ; Singer, Harald ; Matsunaga, Shoichi

Author_Institution

ATR Interpreting Telecommun. Res. Labs., Kyoto, Japan

Volume

1

fYear

1995

fDate

9-12 May 1995

Firstpage

584

Abstract

This paper proposes a time-synchronous continuous speech recognizer driven by a context-free grammar that integrates generalized LR parser based phoneme context prediction and context-dependent HMMs. In this method, a phoneme hypotheses trie is introduced for the phoneme history representation of possible LR states, and an LR state network is introduced for LR path merging. Both techniques reduce the amount of computation. The experimental results show that this new method is more efficient than the conventional LR parser driven phoneme-synchronous continuous speech recognizer

Keywords

acoustic signal processing; context-free grammars; hidden Markov models; speech recognition; synchronisation; LR path merging; LR state network; LR states; context-dependent HMM; context-free grammar; experimental results; generalized LR parser; phoneme context prediction; phoneme history representation; phoneme hypotheses trie; time-synchronous continuous speech recognizer; Acoustic beams; Computational efficiency; Data structures; Hidden Markov models; History; Merging; Speech recognition; Viterbi algorithm;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1995. ICASSP-95., 1995 International Conference on

Conference_Location

Detroit, MI

ISSN

1520-6149

Print_ISBN

0-7803-2431-5

Type

conf

DOI

10.1109/ICASSP.1995.479665

Filename

479665