Testing generality in JANUS: A multi-lingual speech translation system

Louise Osterholtz, Charles Augustine, Arthur McNair, Ivica Rogina, Hiroaki Saito, Tilo Sloboda, Joe Tebelskis, Alex Waibel

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

11 Citations (Scopus)

Abstract

For speech translation to be practical and useful, speech translation systems should be portable to multiple languages without substantial modification. We present the results of expanding the English-based JANUS speech translation system [1] to translate from spoken German sentences to English and Japanese utterances. We also report the results of implementing part of the LPNN speech recognition module on a massively parallel machine. The JANUS approach generalizes well, with overall system performance of 97%. This surpasses English-based JANUS performance.

Original languageEnglish
Title of host publicationICASSP 1992 - 1992 International Conference on Acoustics, Speech, and Signal Processing
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages209-212
Number of pages4
Volume1
ISBN (Electronic)0780305329
DOIs
Publication statusPublished - 1992
Event1992 International Conference on Acoustics, Speech, and Signal Processing, ICASSP 1992 - San Francisco, United States
Duration: 1992 Mar 231992 Mar 26

Other

Other1992 International Conference on Acoustics, Speech, and Signal Processing, ICASSP 1992
CountryUnited States
CitySan Francisco
Period92/3/2392/3/26

Fingerprint

Testing
Speech recognition

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Osterholtz, L., Augustine, C., McNair, A., Rogina, I., Saito, H., Sloboda, T., ... Waibel, A. (1992). Testing generality in JANUS: A multi-lingual speech translation system. In ICASSP 1992 - 1992 International Conference on Acoustics, Speech, and Signal Processing (Vol. 1, pp. 209-212). [225935] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.1992.225935

Testing generality in JANUS : A multi-lingual speech translation system. / Osterholtz, Louise; Augustine, Charles; McNair, Arthur; Rogina, Ivica; Saito, Hiroaki; Sloboda, Tilo; Tebelskis, Joe; Waibel, Alex.

ICASSP 1992 - 1992 International Conference on Acoustics, Speech, and Signal Processing. Vol. 1 Institute of Electrical and Electronics Engineers Inc., 1992. p. 209-212 225935.

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

Osterholtz, L, Augustine, C, McNair, A, Rogina, I, Saito, H, Sloboda, T, Tebelskis, J & Waibel, A 1992, Testing generality in JANUS: A multi-lingual speech translation system. in ICASSP 1992 - 1992 International Conference on Acoustics, Speech, and Signal Processing. vol. 1, 225935, Institute of Electrical and Electronics Engineers Inc., pp. 209-212, 1992 International Conference on Acoustics, Speech, and Signal Processing, ICASSP 1992, San Francisco, United States, 92/3/23. https://doi.org/10.1109/ICASSP.1992.225935
Osterholtz L, Augustine C, McNair A, Rogina I, Saito H, Sloboda T et al. Testing generality in JANUS: A multi-lingual speech translation system. In ICASSP 1992 - 1992 International Conference on Acoustics, Speech, and Signal Processing. Vol. 1. Institute of Electrical and Electronics Engineers Inc. 1992. p. 209-212. 225935 https://doi.org/10.1109/ICASSP.1992.225935
Osterholtz, Louise ; Augustine, Charles ; McNair, Arthur ; Rogina, Ivica ; Saito, Hiroaki ; Sloboda, Tilo ; Tebelskis, Joe ; Waibel, Alex. / Testing generality in JANUS : A multi-lingual speech translation system. ICASSP 1992 - 1992 International Conference on Acoustics, Speech, and Signal Processing. Vol. 1 Institute of Electrical and Electronics Engineers Inc., 1992. pp. 209-212
@inproceedings{3636fcaae108424b8654d12bf4fefbf4,
title = "Testing generality in JANUS: A multi-lingual speech translation system",
abstract = "For speech translation to be practical and useful, speech translation systems should be portable to multiple languages without substantial modification. We present the results of expanding the English-based JANUS speech translation system [1] to translate from spoken German sentences to English and Japanese utterances. We also report the results of implementing part of the LPNN speech recognition module on a massively parallel machine. The JANUS approach generalizes well, with overall system performance of 97{\%}. This surpasses English-based JANUS performance.",
author = "Louise Osterholtz and Charles Augustine and Arthur McNair and Ivica Rogina and Hiroaki Saito and Tilo Sloboda and Joe Tebelskis and Alex Waibel",
year = "1992",
doi = "10.1109/ICASSP.1992.225935",
language = "English",
volume = "1",
pages = "209--212",
booktitle = "ICASSP 1992 - 1992 International Conference on Acoustics, Speech, and Signal Processing",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Testing generality in JANUS

T2 - A multi-lingual speech translation system

AU - Osterholtz, Louise

AU - Augustine, Charles

AU - McNair, Arthur

AU - Rogina, Ivica

AU - Saito, Hiroaki

AU - Sloboda, Tilo

AU - Tebelskis, Joe

AU - Waibel, Alex

PY - 1992

Y1 - 1992

N2 - For speech translation to be practical and useful, speech translation systems should be portable to multiple languages without substantial modification. We present the results of expanding the English-based JANUS speech translation system [1] to translate from spoken German sentences to English and Japanese utterances. We also report the results of implementing part of the LPNN speech recognition module on a massively parallel machine. The JANUS approach generalizes well, with overall system performance of 97%. This surpasses English-based JANUS performance.

AB - For speech translation to be practical and useful, speech translation systems should be portable to multiple languages without substantial modification. We present the results of expanding the English-based JANUS speech translation system [1] to translate from spoken German sentences to English and Japanese utterances. We also report the results of implementing part of the LPNN speech recognition module on a massively parallel machine. The JANUS approach generalizes well, with overall system performance of 97%. This surpasses English-based JANUS performance.

UR - http://www.scopus.com/inward/record.url?scp=85009149373&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85009149373&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.1992.225935

DO - 10.1109/ICASSP.1992.225935

M3 - Conference contribution

AN - SCOPUS:85009149373

VL - 1

SP - 209

EP - 212

BT - ICASSP 1992 - 1992 International Conference on Acoustics, Speech, and Signal Processing

PB - Institute of Electrical and Electronics Engineers Inc.

ER -