Parsing Continuous Speech by HMM-LR Method

Kenji Kita, Takeshi Kawabata, Hiroaki Saito


Abstract
This paper describes a speech parsing method called HMM-LR. In HMM-LR, an LR parsing table is used to predict phones in speech input, and the system drives an HMM-based speech recognizer directly without any intervening structures such as a phone lattice. Very accurate, efficient speech parsing is achieved through the integrated processes of speech recognition and language analysis. The HMM-LR m ethod is applied to large-vocabulary speaker-dependent Japanese phrase recognition. The recognition rate is 87.1% for the top candidates and 97.7% for the five best candidates.
Anthology ID:
W89-0213
Volume:
Proceedings of the First International Workshop on Parsing Technologies
Month:
August
Year:
1989
Address:
Pittsburgh, Pennsylvania, USA
Editor:
Masaru Tomita
Venue:
IWPT
SIG:
SIGPARSE
Publisher:
Carnegy Mellon University
Note:
Pages:
126–131
Language:
URL:
https://aclanthology.org/W89-0213
DOI:
Bibkey:
Cite (ACL):
Kenji Kita, Takeshi Kawabata, and Hiroaki Saito. 1989. Parsing Continuous Speech by HMM-LR Method. In Proceedings of the First International Workshop on Parsing Technologies, pages 126–131, Pittsburgh, Pennsylvania, USA. Carnegy Mellon University.
Cite (Informal):
Parsing Continuous Speech by HMM-LR Method (Kita et al., IWPT 1989)
Copy Citation:
PDF:
https://aclanthology.org/W89-0213.pdf