@inproceedings{efd22e103e53498f9bd7905ef9d47911,
title = "Multimodal human machine interactions in virtual and augmented reality",
abstract = "Virtual worlds are developing rapidly over the Internet. They are visited by avatars and staffed with Embodied Conversational Agents (ECAs). An avatar is a representation of a physical person. Each person controls one or several avatars and usually receives feedback from the virtual world on an audio-visual display. Ideally, all senses should be used to feel fully embedded in a virtual world. Sound, vision and sometimes touch are the available modalities. This paper reviews the technological developments which enable audio-visual interactions in virtual and augmented reality worlds. Emphasis is placed on speech and gesture interfaces, including talking face analysis and synthesis.",
keywords = "Face, Gesture, Human machine interactions (HMI), Multimodality, Speech, Virtual words",
author = "G{\'e}rard Chollet and Anna Esposito and Annie Gentes and Patrick Horain and Walid Karam and Zhenbo Li and Catherine Pelachaud and Patrick Perrot and Dijana Petrovska-Delacr{\'e}taz and Dianle Zhou and Leila Zouari",
year = "2009",
month = jul,
day = "21",
doi = "10.1007/978-3-642-00525-1\_1",
language = "English",
isbn = "3642005241",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
pages = "1--23",
booktitle = "Multimodal Signals",
note = "COST Action 2102 and euCognition International School on Multimodal Signals: Cognitive and Algorithmic Issues ; Conference date: 21-04-2008 Through 26-04-2008",
}