Third European Conference on Speech Communication and Technology

Berlin, Germany
September 22-25, 1993


ATREUS: A Speech Recognition Front-end for a Speech Translation System

Shigeki Sagayama, Jun-ichi Takami, Akito Nagai, Harald Singer, Kouichi Yamaguchi, Kzumi Ohkura, Kenji Kita, Akira Kurematsu

ATR Interpreting Telephony Research Laboratories, Kyoto, Japan

This paper describes the continuous speech recognition subsystem "ATREUS" which is used as the speech input stage in the experimental speech translation system "ASURA." The speech recognition algorithm is SSS-LR/VFS which consists of context-dependent phone models (HMnet), a generalized LR parser, and vector field smoothing for speaker / environment adaptation.

Keywords: continuous speech recognition, context-dependent phone models, LR parser, speaker adaptation, speech translation

Full Paper

Bibliographic reference.  Sagayama, Shigeki / Takami, Jun-ichi / Nagai, Akito / Singer, Harald / Yamaguchi, Kouichi / Ohkura, Kzumi / Kita, Kenji / Kurematsu, Akira (1993): "ATREUS: a speech recognition front-end for a speech translation system", In EUROSPEECH'93, 1287-1290.