The MT engine of the Janus speech-to-speech translation system is designed around four main principles: 1 an interlingua approach that allows the e cient addition of new languages,...
Monika Woszczyna, Matthew Broadhead, Donna Gates, ...
Across language portability of a spoken language understanding system (SLU) deals with the possibility of reusing with moderate effort in a new language knowledge and data acquire...
Christophe Servan, Nathalie Camelin, Christian Ray...
Our research aims at developing a system that paraphrases written language text to spoken language style. In such a system, it is important to distinguish between appropriate and i...
We describe and experimentally evaluate a system, FeasPar, that learns parsing spontaneous speech. To train and run FeasPar (Feature Structure Parser), only limited handmodeled kn...
Data-driven Spoken Language Understanding (SLU) systems need semantically annotated data which are expensive, time consuming and prone to human errors. Active learning has been su...