@inproceedings{59acff0c039042588b5e3f02ac6218f7,
title = "Triseme decision trees in the continuous speech recognition system for a talking head",
abstract = "In this paper, we present a viseme (the basic speech units in the visual domain) based continuous speech recognition system, which segments speech into viseme sequences with timing boundaries to drive a talking head. In the viseme Hidden Markov Model (HMM) training, the instances of a viseme with different contexts are formulated as trisemes. Based on the mouth shape parameters Liprounding and the defined viseme similarity weight (VSW) from the 3D viseme facial models, 166 questions concerning the viseme contexts are designed to build triseme decision trees to tie the states of the trisemes with similar contexts, so that they can share the same parameters. To evaluate the system performance, the image related measurements are also taken to evaluate the resulting viseme sequences, with 'jerky instances' in Liprounding and VSW graphs evaluating their smoothness. Results show that compared to the phoneme based system, the tied-state triseme based speech recognition system gives talking head animation with smoother and more plausible mouth shapes.",
keywords = "Jerky instances, Liprounding, Triseme decision tree, Viseme, Viseme similarity weight",
author = "Jiang, {Dong Mei} and Lei Xie and Ilse Ravyse and Zhao, {Rong Chun} and Hichem Sahli and Jan Cornelis",
year = "2002",
language = "英语",
isbn = "0780375084",
series = "Proceedings of 2002 International Conference on Machine Learning and Cybernetics",
pages = "2097--2101",
booktitle = "Proceedings of 2002 International Conference on Machine Learning and Cybernetics",
note = "Proceedings of 2002 International Conference on Machine Learning and Cybernetics ; Conference date: 04-11-2002 Through 05-11-2002",
}