DMCA
Trainable Videorealistic Speech Animation (2002)
Cached
Download Links
| Venue: | PROCEEDINGS OF SIGGRAPH 2002, SAN ANTONIO TEXAS |
| Citations: | 205 - 4 self |
BibTeX
@INPROCEEDINGS{Ezzat02trainablevideorealistic,
author = {Tony Ezzat and Gadi Geiger and Tomaso Poggio},
title = {Trainable Videorealistic Speech Animation},
booktitle = {PROCEEDINGS OF SIGGRAPH 2002, SAN ANTONIO TEXAS},
year = {2002},
pages = {388--398},
publisher = {ACM Press}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
We describe how to create with machine learning techniques a generative, videorealistic, speech animation module. A human subject is first recorded using a videocamera as he/she utters a predetermined speech corpus. After processing the corpus automatically, a visual speech module is learned from the data that is capable of synthesizing the human subject's mouth uttering entirely novel utterances that were not recorded in the original video. The synthesized utterance is re-composited onto a background sequence which contains natural head and eye movement. The final output is videorealistic in the sense that it looks like a video camera recording of the subject. At run time, the input to the system can be either real audio sequences or synthetic audio produced by a text-to-speech system, as long as they have been phonetically aligned. The two key
Keyphrases
trainable videorealistic speech animation human subject video camera recording synthetic audio novel utterance visual speech module predetermined speech corpus run time eye movement speech animation module background sequence original video synthesized utterance text-to-speech system natural head real audio sequence final output
