Semi-Automatic Creation of Resources for Spoken Dialog Systems

Tatjana Scheffler, Roland Roller, Norbert Reithinger

In: B. Mertsching, M. Hund, Z. Aziz (Hrsg.). KI 2009: Advances in Artificial Intelligence. German Conference on Artificial Intelligence (KI-2009) 32nd Annual Conference on Artificial Intelligence September 15-18 Paderborn Germany Seiten 209-216 Lecture Notes in Artificial Intelligence (LNAI) 5803 Springer 2009.


The increasing number of spoken dialog systems calls for effcient approaches for their development and testing. Our goal is the minimization of hand-crafted resources to maximize the portability of this evaluation environment across spoken dialog systems and domains. In this paper we discuss the user simulation technique which allows us to learn general user strategies from a new corpus. We present this corpus, the VOICE Awards human-machine dialog corpus, and show how it is used to semi-automatically extract the resources and knowledge bases necessary in spoken dialog systems, e.g., the ASR grammar, the dialog classifier, the templates for generation, etc.


Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence