TC-STAR: Technology and Corpora for Speech to Speech Translation
Project summary:
The objective of the TC-STAR project is to significantly reduce the
gap between human and machine performance for speech to speech
translation (SST). The focus is on the development of new, possibly
revolutionary, algorithms and methods, integrating relevant human
knowledge which is available at translation time into a data-driven
framework. Examples of such new approaches are the integration of
linguistic knowledge in the statistical approach of spoken language
translation, the statistical modelling of pronunciation of
unconstrained conversational speech in automatic speech recognition,
and new acoustic and prosodic models for generating expressive speech
in synthesis. TC-STAR is planned for a duration of six years, which
is the time needed for exploring and evaluating new approaches to SST,
and for creating the infrastructure needed for accelerating the rate
of progress in the field. The project has been divided in two phases
of three years length. The first three years of the project's
work-plan has been granted and is targeting a selection of
unconstrained conversational speech domains - i.e. broadcast news and
speeches - and a few languages relevant for Europe's society and
economy: native and non native European English, European Spanish and
Chinese. The second three years, will target more complex
unconstrained conversational speech domains - i.e. meetings and social
conversations - adding to the previous languages other relevant
European languages.
Consortium:
For more information: TC-STAR WEB site
TC-STAR ASR working area (WP2)
Last modified: Tuesday,13-December-05 02:32:05 CET