Multi-lingual Interoperability in Speech Technology (MIST) September 13-14, 1999 Leusden, The Netherlands

A Platform For Multilingual Research In Spoken Dialogue Systems

Ronald A. Cole (1), Ben Serridge (2), John-Paul Hosom (3), Andrew Cronk (3), and Ed Kaiser (3)

(1) Center for Spoken Language Understanding; University of Colorado, Boulder, CO, USA
(2) Universidad de las Americas, Puebla, Mexico
(3) Center for Spoken Language Understanding (CSLU), Oregon Graduate Institute, USA

Multilingual speech technology research would be greatly facilitated by an integrated and comprehensive set of software tools that enable research and development of core language technologies and interactive language systems in any language. Such a multilingual platform has been one of our goals in developing the CSLU Toolkit. The Toolkit is composed of components that are essentially language-independent, and support research and development of recognition, understanding, text-to-speech synthesis, facial animation, and spoken dialogue systems. Portions of the Toolkit have already been ported to Italian, German, and Vietnamese. In addition, a complete Mexican-Spanish version of the Toolkit has been created, and is in daily use at the Universidad de las Americas in Puebla (UDLA). In this paper we outline some of the issues involved in porting the Toolkit to a new language, and describe why the Toolkit is well suited to multilingual adaptation.

Full Paper

Bibliographic reference.  Cole, Ronald A. / Serridge, Ben / Hosom, John-Paul / Cronk, Andrew / Kaiser, Ed (1999): "A platform for multilingual research in spoken dialogue systems", In MIST-1999.