Fast word-graph generation for spontaneous conversational speech translation

Tohru Shimizu, Harald Singer, Yoshinori Sagisaka

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

2 Citations (Scopus)

Abstract

This paper introduces the latest advances in research at ATR on speech translation for spontaneous conversations, especially focusing on speech recognition efforts. For recognition, we employ a word search technique that generates moderate sized word graphs in real-time. To cope with a variety in length of utterances, e.g., word, phrase, sentence fragment, sentence, and concatenated sentences in spontaneous speech, we have adopted a two pass search strategy that uses variable-order word n-gram statistics in the first stage and task dependent language constraints in the second stage. This strategy is evaluated using the `ATR Travel Arrangement' corpus.

Original languageEnglish
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Editors Anon
PublisherIEEE
Pages95-98
Number of pages4
Volume1
Publication statusPublished - 1997
Externally publishedYes
EventProceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP. Part 1 (of 5) - Munich, Ger
Duration: 1997 Apr 211997 Apr 24

Other

OtherProceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP. Part 1 (of 5)
CityMunich, Ger
Period97/4/2197/4/24

    Fingerprint

ASJC Scopus subject areas

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

Cite this

Shimizu, T., Singer, H., & Sagisaka, Y. (1997). Fast word-graph generation for spontaneous conversational speech translation. In Anon (Ed.), ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (Vol. 1, pp. 95-98). IEEE.