This paper describes a robot who converses with multi-person using his multi-modal interface. The multi-person conversation includes many new problems, which are not cared in the conventional one-to-one conversation: such as information ow problems (recognizing who is speaking and to whom he is speaking / appealing to whom the system is speaking), space information sharing problem and turn holder estimation problem (estimating who is the next speaker). We solved these problems by utilizing multi-modal interface: face direction recognition, gesture recognition, sound direction recognition, speech recogni tion and gestural expression. The systematic combination of these functions realized human friendly multi-person conversation system.
Cite as: Matsusaka, Y., Tojo, T., Kubota, S., Furukawa, K., Tamiya, D., Hayata, K., Nakano, Y., Kobayashi, T. (1999) Multi-person conversation via multi-modal interface - a robot who communicate with multi-user -. Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999), 1723-1726, doi: 10.21437/Eurospeech.1999-387
@inproceedings{matsusaka99_eurospeech,
author={Yosuke Matsusaka and Tsuyoshi Tojo and Sentaro Kubota and Kenji Furukawa and Daisuke Tamiya and Keisuke Hayata and Yuichiro Nakano and Tetsunori Kobayashi},
title={{Multi-person conversation via multi-modal interface - a robot who communicate with multi-user -}},
year=1999,
booktitle={Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999)},
pages={1723--1726},
doi={10.21437/Eurospeech.1999-387}
}