Describing and Generating Web-Based Affective Human-Agent Interaction

摘要

In this paper, we discuss our research on the multi-modal interaction markup language (MIML) which serves as a core for integrating various components, including lifelike agent ActiveX controller, facial expression recognition ActiveX controller and speech emotion recognition ActiveX controller, to describe and generate web-based affective human-agent interaction. Emotional control on lifelike agents provided by MIML makes the human-agent interaction even more intelligent. With the MIML and components we designed, web-based affective interaction can be described and generated easily.