We present recent advances from our efforts in increasing coverage, robustness, generality and speed of JANUS, CM IPs speech-to-speech translation system. JANUS is a speaker-independent system which translates spoken utterances in English and also in German into one of German, English or Japanese. The system has been designed around the task of conference registration (OR). It has initially been built based on a speech database of 12 read dialogs, encompassing a vocabulary of around 500 words. We have since been expanding the system along several dimensions to improve speed, robustness and coverage and to move toward spontaneous input.
Bibliographic reference. Woszczyna, Monika / Coccaro, N. / Eisele, A. / Lavie, A. / McNair, A. / Polzin, T. / Rogina, Ivica / Rose, C. P. / Sloboda, Tilo / Tomita, M. / Tsutsumi, J. / Aoki-Waibel, N. / Waibel, Alex / Ward, Wayne (1993): "Recent advances in JANUS: a speech translation system", In EUROSPEECH'93, 1295-1298.