skip to main content
10.5555/1289189.1289241dlproceedingsArticle/Chapter ViewAbstractPublication PageshltConference Proceedingsconference-collections
Article
Free Access

An automatic speech translation system for travel conversation

Authors Info & Claims
Published:24 March 2002Publication History

ABSTRACT

We present a speech-to-speech translation system for notebook PC's that helps oral communication between Japanese and English speakers in the various situations in the travel abroad. Due to the high accuracy of the compact continuous speech recognition engine and our lexicalized grammar approach to machine translation that utilizes corpus but is oriented to model general linguistic phenomena as well as word-specific ones, a versatile speech-to-speech translation system for travel abroad is achieved, which is with much larger vocabulary (50,000 Japanese words and 10,000 English words) and capable of translating spoken conversations in more situations compared to previous work [1].

References

  1. Watanabe, T et al., An experimental automatic interpretation system: INTERTALKER, Proc. of Acoustic Soc. of Japan, (Spring 1992), 101--102 (In Japanese).Google ScholarGoogle Scholar
  2. Schabes, Y. et al., Parsing Strategies with 'Lexicalized' Grammars, COLING'88, (1988) 578--583. Google ScholarGoogle ScholarDigital LibraryDigital Library
  3. Yamabana, K. et al. Lexicalized Tree Automata-based Grammars for Translating Conversational Texts, COLING 2000, (2000) 926--932. Google ScholarGoogle ScholarDigital LibraryDigital Library

Recommendations

Comments

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Sign in
  • Published in

    cover image DL Hosted proceedings
    HLT '02: Proceedings of the second international conference on Human Language Technology Research
    March 2002
    436 pages

    Publisher

    Morgan Kaufmann Publishers Inc.

    San Francisco, CA, United States

    Publication History

    • Published: 24 March 2002

    Qualifiers

    • Article

    Acceptance Rates

    Overall Acceptance Rate240of768submissions,31%

PDF Format

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader