Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
| Paper: | MSP-P1.4 |
| Session: | Human Machine Interface; Signal Processing for Media Integration and Application |
| Time: | Friday, May 21, 09:30 - 11:30 |
| Presentation: |
Poster |
| Topic: |
Multimedia Signal Processing: Human-Machine Interface |
| Title: |
AUDIO TO VISUAL SIGNAL MAPPINGS WITH HMM |
| Authors: |
WenTao Liu; Beijing Polytechnic University | | |
| | BaoCai Yin; Beijing Polytechnic University | | |
| | XiBin Jia; Beijng Polytechnic University | | |
| | DeHui Kong; Beijing Polytechnic University | | |
| Abstract: |
There has been a large amount of research on speech driven face animation. Particularly, recently research efforts have been demonstrated that the Hidden Markov Model techniques could achieve a high level of success in the filed of audio/visual mapping without language information. In this paper, firstly a linear model based facial representation method was applied, which extract face feature as a global feature. Secondly a HMM based method was presented, which include a two-level frame to promote the audio-visual mapping result. |
| |
| Back | |