@inproceedings{0d94581cea284c37b4c07c0836c863de,
title = "Real-time speech-driven 3D face animation",
abstract = "In this paper, we present an approach for real-time speech-driven 3D face animation using neural networks. We first analyze a 3D facial movement sequence of a talking subject and learn a quantitative representation of the facial deformations, called the 3D motion units (MUs). A 3D facial deformation can be approximated by a linear combination of the MUs weighted by the MU parameters (MUPs) - the visual features of the facial deformation. The facial movement sequence synchronizes with a audio track. The audio track is digitized and the audio features of each frame are calculated. A real-time audio-to-MUP mapping is constructed by training a set of neural networks using the calculated audio-visual features. The audio-visual features are divided into several groups based on the audio features. One neural network is trained per group to map the audio features to the corresponding MUPs. Given a new audio feature vector, we first classify it into one of the groups and select the corresponding neural network to map the audio feature vector to MUPs, which are used for face animation. The quantitative evaluation shows the effectiveness of the proposed approach.",
author = "Pengyu Hong and Zhen Wen and Huang, {T. S.} and Shum, {Heung Yeung}",
note = "Publisher Copyright: {\textcopyright} 2002 IEEE.; 1st International Symposium on 3D Data Processing Visualization and Transmission, 3DPVT 2002 ; Conference date: 19-06-2002 Through 21-06-2002",
year = "2002",
doi = "10.1109/TDPVT.2002.1024147",
language = "English (US)",
series = "Proceedings - 1st International Symposium on 3D Data Processing Visualization and Transmission, 3DPVT 2002",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "713--716",
booktitle = "Proceedings - 1st International Symposium on 3D Data Processing Visualization and Transmission, 3DPVT 2002",
address = "United States",
}