Interpretation of Situated Human-Robot Dialogues

Abstract

Robust speech understanding is an important prerequisite for intelligent human-robotinteraction. This paper presents an approach for an adept analysis of speech in a multi-modal dialogue system. In this paper, we provide an analysis of spontaneous speech dialogues between humans and autonomous mobile service robots. Based on this analysis, we are developing a system for robust speech understanding for BIRON, a mobile service robot for oce environments. As a result of a corpus analysis in form of an experiment, we have shown that for this kind of application it is insucient to generate robot instructions based on speech input solely. Moreover, we propose that additional information like gestures and environmental data have to be incorporated into the analysis.