Name
Abstract | ||
|---|---|---|
In this paper a system that transforms speech waveforms to animated faces are proposed. The system relies on continuous state space models to perform the mapping, this makes it possible to ensure video with no sudden jumps and allows continuous control of the parameters in 'face space'. The performance of the system is critically dependent on the number of hidden variables, with too few variables the model cannot represent data, and with too many overfitting is noticed Simulations are performed on recordings of 3-5 sec. video sequences with sentences from the Timit database. From a subjective point of view the model is able to construct an image sequence from an unknown noisy speech sequence even though the number of training examples are limited. |
Year | DOI | Venue |
|---|---|---|
2004 | 10.1007/978-3-540-30568-2_12 | MLMI |
Keywords | Field | DocType |
animated face,continuous control,image sequence,speech waveform,timit database,hidden variable,continuous state space model,unknown noisy speech sequence,face space,video sequence,hidden variables,state space model | Pattern recognition,Face space,Computer science,Timit database,Speech recognition,Active appearance model,Artificial intelligence,Hidden variable theory,Overfitting,State space,Image sequence,Machine learning | Conference |
Volume | ISSN | ISBN |
3361 | 0302-9743 | 3-540-24509-X |
Citations | PageRank | References |
7 | 0.73 | 14 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Tue Lehn-Schiøler | 1 | 114 | 8.47 |
| Lars Kai Hansen | 2 | 2776 | 341.03 |
| Jan Larsen | 3 | 55 | 6.62 |