We introduce an active multimodal interaction system with both a synthesized facial display and vision based user identification. This system can realize activeness to find and response to the user only sitting at the front of the system. Current speech dialog systems do not have the initiative of dialogs, and it is impossible to realize the initiative of dialogs only with speech I/O mode. This paper presents the advantages of an active multimodal interaction system in which two or more modes are integrated together and the configuration of the design of the prototype system.
Cite as: Itou, K., Hasegawa, O., Kurita, T., Hayamizu, S., Tanaka, K., Yamamoto, K., Otsu, N. (1995) An active multimodal interaction system. Proc. ESCA Workshop on Spoken Dialogue Systems, 169-172
@inproceedings{itou95_sds,
author={Katunobu Itou and Osamu Hasegawa and Takio Kurita and Satoru Hayamizu and Kazuyo Tanaka and Kazuhiko Yamamoto and Nobuyuki Otsu},
title={{An active multimodal interaction system}},
year=1995,
booktitle={Proc. ESCA Workshop on Spoken Dialogue Systems},
pages={169--172}
}