Modélisation d'un Système de Reconnaissance pour l'Apprentissage Automatique de Stratégies de Dialogue Optimales

Content Provider	Semantic Scholar
Author	Pietquin, Olivier Dutoit, Thierry
Copyright Year	2002
Abstract	This last decade, the field of spoken dialogue systems has developed quickly. However, rapid design of dialogue strategies remains uneasy. Automatic strategy learning has been investigated and the use of Reinforcement Learning algorithms introduced by Levin and Pieraccini is now part of the state of the art in this area. Obviously, the learned strategy's worth depends on the definition of the optimization criterion used by the learning agent and on the exactness of the environment model. In this paper, we propose to introduce a model of an ASR system in the simulated environment in order to enhance the learned strategy. To do so, we brought recognition error rates and confidence levels produced by ASR systems in the optimization criterion.
File Format	PDF HTM / HTML
Alternate Webpage(s)	http://www.lifl.fr/~pietquin/pdf/JEP_2002_OPTD.pdf
Alternate Webpage(s)	http://tcts.fpms.ac.be/publications/papers/2002/jep2002_optd.pdf
Language	English
Access Restriction	Open
Content Type	Text
Resource Type	Article