Testing Generality in JANUS: A Multi-lingual Speech Tranlslation System - Robotics Institute Carnegie Mellon University

Testing Generality in JANUS: A Multi-lingual Speech Tranlslation System

Louise Osterholtz, Charles Augustine, Arthur McNair, Hideo Saito, Tilo Sloboda, Joe Tebelskis, Alex Waibel, and Monika Woszczyna
Conference Paper, Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '92), Vol. 1, pp. 209 - 212, March, 1992

Abstract

For speech translation to be practical and useful, speech translation systems should be portable to multiple languages without substantial modification. The authors present results of expanding the English-based JANUS speech translation system to translate from spoken German sentences to English and Japanese utterances. The authors also report the results of implementing part of the linked predictive neural network (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.

BibTeX

@conference{Osterholtz-1992-15872,
author = {Louise Osterholtz and Charles Augustine and Arthur McNair and Hideo Saito and Tilo Sloboda and Joe Tebelskis and Alex Waibel and Monika Woszczyna},
title = {Testing Generality in JANUS: A Multi-lingual Speech Tranlslation System},
booktitle = {Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '92)},
year = {1992},
month = {March},
volume = {1},
pages = {209 - 212},
}