The JANUS speech translation system translates spoken language, much like a human interpreter. It operates on a number of limited domains such as appointment scheduling, hotel reservation, or travel planning.
The JANUS project is aiming to make human-to-human communication across language barriers easier. Unlike a human interpreter, JANUS can also access databases to automatically provide additional information such as train schedules or city maps to the user.

All systems are designed to work without a conventional keyboard. Whenever speech input is insufficient, other modalities such as handwriting and gesture recognition can be used to create a user friendly interface.

To provide translation for conversational speech, the system has to handle fragmentary, errorful and disfluent language and heavily coarticulated and noisy speech. In stead of literal translation it has to provide useful interpretation of a user's intent.

For the discourse domain of human-to-human appointment scheduling negotiations a vocabulary size of 3,000 to 5,000 words was observed, depending on language. Perplexities in this task range between 30 and 70. The system runs in less than two times real time.

Languages

For the travel domain, the JANUS system currently supports English and German as input languages and translates into Engish, German and Japanese. For other tasks we have also developed Korean and Spanish components.

JANUS is used as CMU's system in the CSTAR-II consortium, where a number of international partners develop speech translation between English, French, German, Italian, Japanese, and Korean.

More
to topback to top

page designed by: Céline Morel

 





Questions or Comments? Contact the Webmaster