Home | Legals | Sitemap | KIT

Research

The ISL focuses on developing user interfaces that improve human-machine and human-to-human communication. The ISL has been one of the leading laboratories active in speech and language research, computer vision approaches for machine interfaces and has pioneered many speech translation technologies. The laboratories are affiliated with the computer science department at the Karlsruhe Institute of Technology (KIT), Germany, and has sister laboratories at the School of Computer Sci-ence Carnegie Mellon in Pittsburgh and Silicon Valley, USA. ISL is part of IMMI, a joint venture in Paris, France, a leading laboratory devoted to Multimedia and Multilingual Information Processing.

In 1991, ISL introduced JANUS, the first speech translation system in Europe and the US and demonstrated the feasibility of speaker-independent, continuous speech translation. In 1992, the ISL founded the international Consortium for Speech Translation Advanced Research (C-STAR), the earliest team effort on speech translation, together with partners in the US and Japan. C-STAR continues to host and manage the annual IWSLT workshops and evaluations. In 1993, it presented the first spontaneous speech translation system, and in 2005 the first real-time simultaneous speech translation system for lectures. ISL served as coordinating or founding partner in a number of European key speech translation programs including Verbmobil, Nespole, TC-STAR and the French-German collaborative R&D program ‘Quaero’. ISL is also leading efforts on multimodal interfaces for the DFG Sonderforschungsbereich ‘Humanoid Robots’, and served as the general scientific coordinator of CHIL, the largest Integrating Project on Multimodal Interfaces during FP-6. On February 01, 2012 the Integrated Project, EU-BRIDGE, started - funded by the European Commission under FP7 and coordinated by ISL. Furthermore ISL is partner in the French-German INTERREG-project EVEIL-3D (start Jan. 01, 2012).