EUROSPEECH 2003 - INTERSPEECH 2003
8th European Conference on Speech Communication and Technology

Geneva, Switzerland
September 1-4, 2003

        

Generation of Natural Response Timing Using Decision Tree Based on Prosodic and Linguistic Information

Masashi Takeuchi, Norihide Kitaoka, Seiichi Nakagawa

Toyohashi University of Technology, Japan

If a dialog system can respond to the user as reasonable as a human, the interaction will be more smooth. Timing of response such as backchannels and turn-taking plays important role in such a smooth dialog as in human-human interaction. We are now developing a dialog system which can generate response timing in real time. In this paper, we introduce a response timing generator for such a dialog system. First, we analyzed conversations between two persons and extracted prosodic and linguistic information which had effects on the timing. Then we constructed a decision tree based on the features coming from the information and developed a timing generator using rules derived from the decision tree. The timing generator decides the action of the system at every 100ms in user's pause. We evaluated the timing generator by subjective and objective evaluation.

Full Paper

Bibliographic reference.  Takeuchi, Masashi / Kitaoka, Norihide / Nakagawa, Seiichi (2003): "Generation of natural response timing using decision tree based on prosodic and linguistic information", In EUROSPEECH-2003, 609-612.