Conversion of continuous speech sound to articulation animation as an application of visual coarticulation modeling
A voice to facial animation conversion system is presented in this paper. In particular the temporal structure of the multimodal speech is discussed. Mutual information and neural network training is used to estimate the optimal temporal scope for audio to video conversion.
Saved in:
| Main Authors: | |
|---|---|
| Corporate Author: | |
| Format: | Article |
| Published: |
2007
|
| Series: | Acta cybernetica
18 No. 2 |
| Kulcsszavak: | Számítástechnika, Nyelvészet - számítógép alkalmazása |
| Subjects: | |
| Online Access: | http://acta.bibl.u-szeged.hu/12822 |
| Summary: | A voice to facial animation conversion system is presented in this paper. In particular the temporal structure of the multimodal speech is discussed. Mutual information and neural network training is used to estimate the optimal temporal scope for audio to video conversion. |
|---|---|
| Physical Description: | 355-362 |
| ISSN: | 0324-721X |