The power of a nod and a glance: Envelope vs. emotional feedback in animated conversational agents 论文

1999Applied Artificial Intelligence引用 384顶会
Social Robot Interaction and HRISpeech and dialogue systemsAI in Service Interactions

摘要

In this article we describe results from an experiment of user interaction with autonomous, human-like (humanoid) conversational agents.W e hypothesize that for embodied conversational agents, nonverbal behaviors related to the process of conversation, what we call envelope feedback, is much more important than other feedback, such as emotional expression.W e test this hypothesis by having subjects interact with three autonomous agents, all capable of full-duplex multimodal interaction: able to generate and recognize speech, intonation, facial displays, and gesture.Each agent, however, gave a di erent kind of feedback: (1) content-related only, (2) content 1 envelope feedback, and (3) content 1 emotional.Content-related feedback includes answering questions and executing commands ; envelope feedback includes behaviors such as gaze, manual beat gesture, and head movements ; emotional feedback includes smiles and looks of puzzlement.Subjects' evaluations of the system were collected with a questionnaire, and videotapes of their speech patterns and behaviors were scored according to how often the users repeated themselves, how often they hesitated, and how often they got frustrated.T he results con rm our hypothesis that envelope feedback is more important in interaction than emotional feedback and that envelope feedback plays a crucial role in supporting the process of dialog.A secondary result from this study shows that users give our multimodal conversational humanoids very high ratings of lifelikeness and uidity of interaction when the agents are capable of giving such feedback.Research intended to answer questions about the various features of embodied agent-oriented systems-systems that employ an embodied character as interface-has to date been hampered by the lack of real computer systems capable of sustaining and supporting multimodal dialog with a human user.To assess topics such as lifelikeness, trust, eVectiveness of com-

相关技术

暂无数据

相关事件

暂无数据

相关文章

暂无数据