Paper: Incremental Adaptation of Speech-to-Speech Translation

ACL ID N09-2038
Title Incremental Adaptation of Speech-to-Speech Translation
Venue Human Language Technologies
Session Short Paper
Year 2009

In building practical two-way speech-to-speech translation systems the end user will always wish to use the system in an environment different from the original training data. As with all speech sys- tems, it is important to allow the system to adapt to the actual usage situations. This paper investi- gates how a speech-to-speech translation system can adapt day-to-day from collected data on day one to improve performance on day two. The platform is the CMU Iraqi-English portable two-way speech- to-speech system as developed under the DARPA TransTac program. We show how machine transla- tion, speech recognition and overall system perfor- mance can be improved on day 2 after adapting from day 1 in both a supervised and unsupervised way.