Multimodal Human Machine Interactions in Virtual and Augmented Reality

摘要: Virtual worlds are developing rapidly over the Internet. They visited by avatars and staffed with Embodied Conversational Agents (ECAs). An avatar is a representation of physical person. Each person controls one or several usually receives feedback from virtual world on an audio-visual display. Ideally, all senses should be used to feel fully embedded in world. Sound, vision sometimes touch available modalities. This paper reviews technological developments which enable interactions augmented reality worlds. Emphasis placed speech gesture interfaces, including talking face analysis synthesis.