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

sentences
Speech recognition
Statistics
conversation
speech recognition
travel
fragments
statistics

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.

Fast word-graph generation for spontaneous conversational speech translation. / Shimizu, Tohru; Singer, Harald; Sagisaka, Yoshinori.

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. ed. / Anon. Vol. 1 IEEE, 1997. p. 95-98.

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

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, IEEE, pp. 95-98, Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP. Part 1 (of 5), Munich, Ger, 97/4/21.
Shimizu T, Singer H, Sagisaka Y. Fast word-graph generation for spontaneous conversational speech translation. In Anon, editor, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Vol. 1. IEEE. 1997. p. 95-98
Shimizu, Tohru ; Singer, Harald ; Sagisaka, Yoshinori. / Fast word-graph generation for spontaneous conversational speech translation. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. editor / Anon. Vol. 1 IEEE, 1997. pp. 95-98
@inproceedings{f73a248120de4639bc0392c5a41de52f,
title = "Fast word-graph generation for spontaneous conversational speech translation",
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.",
author = "Tohru Shimizu and Harald Singer and Yoshinori Sagisaka",
year = "1997",
language = "English",
volume = "1",
pages = "95--98",
editor = "Anon",
booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "IEEE",

}

TY - GEN

T1 - Fast word-graph generation for spontaneous conversational speech translation

AU - Shimizu, Tohru

AU - Singer, Harald

AU - Sagisaka, Yoshinori

PY - 1997

Y1 - 1997

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=0030701360&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030701360&partnerID=8YFLogxK

M3 - Conference contribution

VL - 1

SP - 95

EP - 98

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

A2 - Anon, null

PB - IEEE

ER -