发明名称 |
FACE SYNTHESIS SYSTEM AND METHODOLOGY |
摘要 |
A system and method for synthesizing a facial image, compares a speech frame from an incoming speech signal with acoustic features stored within visually similar entries in an audio-visual codebook to produce a set of weights. The audio-visual codebook also stores visual features corresponding to the acoustic features. A composite visual feature is generated as a weighted sum of the corresponding visual features, from which the facial image is synthesized. The audio-visual codebook may include multiple samples of the acoustic and visual features for each entry, which corresponds to a sequence of one or more phonemes.
|
申请公布号 |
WO9946734(A1) |
申请公布日期 |
1999.09.16 |
申请号 |
WO1999US05289 |
申请日期 |
1999.03.11 |
申请人 |
ENTROPIC, INC. |
发明人 |
ARSLAN, LEVENT;TALKIN, DAVID |
分类号 |
G06T13/20;G06T13/40;G10L21/06;H04N5/262;(IPC1-7):G06T15/70 |
主分类号 |
G06T13/20 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|