Authoring scenes for adaptive, interactive performances
AAMAS '03 Proceedings of the second international joint conference on Autonomous agents and multiagent systems
Describing and generating multimodal contents featuring affective lifelike agents with MPML
New Generation Computing
| Hi-index | 0.00 |
Abstract: This paper proposes a visual authoring tool for presentation agent system on the Web. In presentation systems, it is more fascinating when we conduct the presentation stream by the explanation or conversation of presenters. And in order to provide the presentation on demand on the Web, we need character based presentation Agent. There are several ways to control such agents but some are too complex to be used by general users. We try to propose an easy way for the uses. For this purpose, we have developed Multimodal Presentation Markup Language (MPML), which allows many users to write attractive multimodal presentations easily. MPML is a markup language conformed to Extensible Markup Language (XML). It supports functions for controlling verbal presentation and agent behavior. In this paper, we present its specification, visual authoring tool, and application of MPML when used as a tool for composing multimodal presentations on the WWW.