Parsing continuous speech by HMM-LR method

Kenji Kita, Takeshi Kawabata, Hiroaki Saito

Research output: Contribution to conferencePaperpeer-review

2 Citations (Scopus)


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 method 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.

Original languageEnglish
Number of pages6
Publication statusPublished - 1989
Externally publishedYes
Event1st International Workshop on Parsing Technologies, IWPT 1989 - Pittsburgh, United States
Duration: 1989 Aug 281989 Aug 31


Conference1st International Workshop on Parsing Technologies, IWPT 1989
Country/TerritoryUnited States

ASJC Scopus subject areas

  • Linguistics and Language
  • Language and Linguistics
  • Computer Science Applications


Dive into the research topics of 'Parsing continuous speech by HMM-LR method'. Together they form a unique fingerprint.

Cite this