Triseme decision trees in the continuous speech recognition system for talking head animation

Xie Lei, Zhao Rongchun, Jiang Dongmei, Cravyse Ilse, Sahli Hichem, Conlenis Jan

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Viseme is an audio-visual model for speech-driven talking head animation. In this paper, a viseme HMM based speech recogntion system is built to drive a talking head. Triseme is used to take mouth shape contextual information into account to achieve accurate models. As models mushroomed, to get robust models using the limited training data, decision tree based state tying is adopted in the triseme modeling. Similarity of mouth shapes (SMS) is brought forward to design visual question set in the tree building process. Experimental results show that SMS is a good measurement of mouth shape contexts. Decision tree is a feasible way to get robust model parameter estimations.

源语言英语
主期刊名Proceedings of the International Conference on Active Media Technology
编辑J.P. Li, J. Liu, N. Zhong, J. Yen, J. Zhao, J.P. Li, J. Liu, N. Zhong, J. Yen, J. Zhao
389-395
页数7
出版状态已出版 - 2003
活动Proceedings of the Second International Conference on Active Media Technology - Chongqing, 中国
期限: 29 5月 200331 5月 2003

出版系列

姓名Proceedings of the International Conference on Active Media Technology

会议

会议Proceedings of the Second International Conference on Active Media Technology
国家/地区中国
Chongqing
时期29/05/0331/05/03

指纹

探究 'Triseme decision trees in the continuous speech recognition system for talking head animation' 的科研主题。它们共同构成独一无二的指纹。

引用此