HMM continuous speech recognition using predictive LR parsing

Kenji Kita, Takeshi Kawabata, Hiroaki Saito

Research output: Chapter in Book/Report/Conference proceedingConference contribution

20 Citations (Scopus)

Abstract

The authors propose a continuous-speech recognition method that uses an accurate and efficient parsing mechanism, an LR parser, and drives HMM (hidden Markov model) modules directly without any intervening structures such as a phoneme lattice. The method was tested in Japanese phrase recognition experiments. Two grammars were prepared, a general Japanese grammar and a task-specific grammar. The phrase recognition rate with the general grammar was 72% for top candidates and 95% for the five best candidates. With the task-specific grammar, recognition rate was 80% and 99%, respectively.

Original languageEnglish
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Editors Anon
PublisherPubl by IEEE
Pages703-706
Number of pages4
Volume2
Publication statusPublished - 1989
Externally publishedYes
Event1989 International Conference on Acoustics, Speech, and Signal Processing - Glasgow, Scotland
Duration: 1989 May 231989 May 26

Other

Other1989 International Conference on Acoustics, Speech, and Signal Processing
CityGlasgow, Scotland
Period89/5/2389/5/26

Fingerprint

grammars
Continuous speech recognition
speech recognition
Hidden Markov models
Experiments
phonemes
modules

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering
  • Acoustics and Ultrasonics

Cite this

Kita, K., Kawabata, T., & Saito, H. (1989). HMM continuous speech recognition using predictive LR parsing. In Anon (Ed.), ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (Vol. 2, pp. 703-706). Publ by IEEE.

HMM continuous speech recognition using predictive LR parsing. / Kita, Kenji; Kawabata, Takeshi; Saito, Hiroaki.

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. ed. / Anon. Vol. 2 Publ by IEEE, 1989. p. 703-706.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kita, K, Kawabata, T & Saito, H 1989, HMM continuous speech recognition using predictive LR parsing. in Anon (ed.), ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. vol. 2, Publ by IEEE, pp. 703-706, 1989 International Conference on Acoustics, Speech, and Signal Processing, Glasgow, Scotland, 89/5/23.
Kita K, Kawabata T, Saito H. HMM continuous speech recognition using predictive LR parsing. In Anon, editor, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Vol. 2. Publ by IEEE. 1989. p. 703-706
Kita, Kenji ; Kawabata, Takeshi ; Saito, Hiroaki. / HMM continuous speech recognition using predictive LR parsing. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. editor / Anon. Vol. 2 Publ by IEEE, 1989. pp. 703-706
@inproceedings{2fed78211aed4304a005d8873872ca61,
title = "HMM continuous speech recognition using predictive LR parsing",
abstract = "The authors propose a continuous-speech recognition method that uses an accurate and efficient parsing mechanism, an LR parser, and drives HMM (hidden Markov model) modules directly without any intervening structures such as a phoneme lattice. The method was tested in Japanese phrase recognition experiments. Two grammars were prepared, a general Japanese grammar and a task-specific grammar. The phrase recognition rate with the general grammar was 72{\%} for top candidates and 95{\%} for the five best candidates. With the task-specific grammar, recognition rate was 80{\%} and 99{\%}, respectively.",
author = "Kenji Kita and Takeshi Kawabata and Hiroaki Saito",
year = "1989",
language = "English",
volume = "2",
pages = "703--706",
editor = "Anon",
booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - HMM continuous speech recognition using predictive LR parsing

AU - Kita, Kenji

AU - Kawabata, Takeshi

AU - Saito, Hiroaki

PY - 1989

Y1 - 1989

N2 - The authors propose a continuous-speech recognition method that uses an accurate and efficient parsing mechanism, an LR parser, and drives HMM (hidden Markov model) modules directly without any intervening structures such as a phoneme lattice. The method was tested in Japanese phrase recognition experiments. Two grammars were prepared, a general Japanese grammar and a task-specific grammar. The phrase recognition rate with the general grammar was 72% for top candidates and 95% for the five best candidates. With the task-specific grammar, recognition rate was 80% and 99%, respectively.

AB - The authors propose a continuous-speech recognition method that uses an accurate and efficient parsing mechanism, an LR parser, and drives HMM (hidden Markov model) modules directly without any intervening structures such as a phoneme lattice. The method was tested in Japanese phrase recognition experiments. Two grammars were prepared, a general Japanese grammar and a task-specific grammar. The phrase recognition rate with the general grammar was 72% for top candidates and 95% for the five best candidates. With the task-specific grammar, recognition rate was 80% and 99%, respectively.

UR - http://www.scopus.com/inward/record.url?scp=0024934095&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024934095&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0024934095

VL - 2

SP - 703

EP - 706

BT - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

A2 - Anon, null

PB - Publ by IEEE

ER -