ESCA Workshop on Spoken Dialogue Systems Vigsø, Denmark May 30 - June 2, 1995

Spontaneous Speech Understanding for a Dialogue System

Masaru Hidano, Toshihiko Itoh, Mikio Yamamoto, Seiichi Nakagawa

Department of Information and Computer Sciences, Toyohashi University of Technology, Toyohashi, Japan

In this paper, we describe the spoken dialogue system that can understand spontaneous speech. It is difficult to recognize spontaneous speech, that is, misrecognition often occurs, because spontaneous speech has many ambiguous phenomena such as interjections, ellipses, inversions, repairs and so on. Also, a recognizer may output the sentence that human being never speaks. Therefore, the interpretation part that receives recognized sentences must cope not only with spontaneous sentences but also with illegal sentences having recognition errors. We developed the robust interpretation method that used some heuristics for understanding spontaneous or misrecognized sentences.

Full Paper

Bibliographic reference.  Hidano, Masaru / Itoh, Toshihiko / Yamamoto, Mikio / Nakagawa, Seiichi (1995): "Spontaneous speech understanding for a dialogue system", In SDS-1995, 25-28.