TC-STAR is envisioned as a long term effort focused on advanced research in all core technologies for speech to speech translation (SST): speech recognition, speech translation and speech synthesis.
The objectives of the project are extremely ambitious: making a breakthrough in SST research to significantly reduce the gap between human and machine performance. The focus will be 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 modeling 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 will target 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. This second phase will give rise to a new proposal for funding to be evaluated in a later FP6 competitive call.
Prof. Dr. Alexander Waibel
Dr. Sebastian Stüker, e-mail: Sebastian.Stueker∂kit.edu