Visual authoring tool for presentation agent based on Multimodal Presentation Markup Language

摘要

The paper proposes a visual authoring tool for a presentation agent system on the Web. In presentation systems, it is more fascinating when we conduct the presentation stream via the explanation or conversation of presenters. In order to provide a presentation on demand on the Web, we need a character based presentation agent. There are several ways to control such agents but some are too complex to be used by general users; we propose an easy method for controlling agents. 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 conforming to Extensible Markup Language (XML) and it supports functions for controlling verbal presentation and agent behavior. The authors present MPML's specification, visual authoring tool, and the application of MPML when used as a tool for composing multimodal presentations on the WWW.