Building of turn-taking avatars that express utterance attitudes: a social scientific approach to behavioral design of conversational agents

Authors:
Masahide Yuasa;Naoki Mukawa
Affiliations:
School of Information Environment, Tokyo Denki University, Muzai Gakuendai, Inzai, Chiba, Japan;School of Information Environment, Tokyo Denki University, Muzai Gakuendai, Inzai, Chiba, Japan
Venue:
UAHCI'11 Proceedings of the 6th international conference on Universal access in human-computer interaction: applications and services - Volume Part IV
Year:
2011

Citing 5
Cited 0

BodyChat: autonomous communicative behaviors in avatars

AGENTS '98 Proceedings of the second international conference on Autonomous agents
Embodied agents for multi-party dialogue in immersive virtual worlds

Proceedings of the first international joint conference on Autonomous agents and multiagent systems: part 2
Gestural mind markers in ECAs

AAMAS '03 Proceedings of the second international joint conference on Autonomous agents and multiagent systems
Can local avatars satisfy a global audience? A case study of high-fidelity 3D facial avatar animation in subject identification and emotion perception by US and international groups

Computers in Entertainment (CIE) - SPECIAL ISSUE: Media Arts and Games (Part II)
An utterance attitude model in human-agent communication: from good turn-taking to better human-agent understanding

CHI '10 Extended Abstracts on Human Factors in Computing Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

In everyday communication, humans comprehend the attitudes of others conveyed via nonverbal behavior, such as facial expression, body posture and gaze behavior. In this paper, we describe a model for comprehending participants' desire to start to speak or to listen based on nonverbal behavior during conversation. We use a social scientific approach that is based on both an analysis of a video observation and an experiment using avatars. We explain the building of the model. We discuss detecting participant's attitudes using computer vision and the expression of their attitudes using their avatars' facial expressions and body postures.