JANUS 93: towards spontaneous speech translation
- 17 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. i (15206149) , I/345-I/348
- https://doi.org/10.1109/icassp.1994.389285
Abstract
We present first results from our efforts toward translation of spontaneously spoken speech. Improvements include increasing coverage, robustness, generality and speed of JANUS, the speech-to-speech translation system of Carnegie Mellon and Karlsruhe University. The recognition and machine translation engine have been upgraded to deal with requirements introduced by spontaneous human to human dialogs. To allow for development and evaluation of our system on adequate data, a large database with spontaneous scheduling dialogs is being gathered for English, German and Spanish.<>Keywords
This publication has 6 references indexed in Scilit:
- Learning state-dependent stream weights for multi-codebook HMM speech recognition systemsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A speech to speech translation system built from standard componentsPublished by Association for Computational Linguistics (ACL) ,1993
- Recent advances in JanusPublished by Association for Computational Linguistics (ACL) ,1993
- Testing generality in JANUS: a multi-lingual speech translation systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1992
- PARSEC: a structured connectionist parsing system for spoken languagePublished by Institute of Electrical and Electronics Engineers (IEEE) ,1992
- Efficient grammar processing for a spoken language translation systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1992