@inproceedings{wang2010photo-real,
author = {Wang, Lijuan and Qian, Xiaojun and Han, Wei and Soong, Frank},
title = {Photo-Real Lips Synthesis with Trajectory-Guided Sample Selection},
booktitle = {Speech Synthesis Workshop (SSW7)},
year = {2010},
month = {September},
abstract = {In this paper, we propose an HMM trajectory-guided, real image sample concatenation approach to photo-real talking head synthesis. It renders a smooth and natural video of articulators in sync with given speech signals. An audio-visual database is used to train a statistical Hidden Markov Model (HMM) of lips movement first and the trained model is then used to generate a visual parameter trajectory of lips movement for given speech signals, all in the maximum likelihood sense. The HMM generated trajectory is then used as a guide to select, in the original training database, an optimal sequence of mouth images which are then stitched back to a background head video. The whole procedure is fully automatic and data driven. With an audio/video footage as short as 20 minutes from a speaker, the proposed system can synthesize a highly photo-real video in sync with the given speech signals. This system won the FIRST place in the Audio-Visual match contest in LIPS2009 Challenge, which was perceptually evaluated by recruited human subjects.},
publisher = {International Speech Communication Association},
url = {http://approjects.co.za/?big=en-us/research/publication/photo-real-lips-synthesis-with-trajectory-guided-sample-selection/},
edition = {Speech Synthesis Workshop (SSW7)},
}