Abstract | ||
---|---|---|
In this work, synthesis of facial animation is done by modelling the mapping between facial motion and speech using the shared Gaussian process latent variable model. Both data are processed separately and subsequently coupled together to yield a shared latent space. This method allows coarticulation to be modelled by having a dynamical model on the latent space. Synthesis of novel animation is done by first obtaining intermediate latent points from the audio data and then using a Gaussian Process mapping to predict the corresponding visual data. Statistical evaluation of generated visual features against ground truth data compares favourably with known methods of speech animation. The generated videos are found to show proper synchronisation with audio and exhibit correct facial dynamics. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1007/978-3-642-10331-5_9 | ISVC (1) |
Keywords | Field | DocType |
facial motion,facial animation,audio data,shared gaussian process latent,gaussian process latent,correct facial dynamic,ground truth data,variable model,intermediate latent point,shared latent space,speech-driven facial animation,corresponding visual data,latent space,latent variable model,gaussian process,ground truth | Computer science,Coarticulation,Computer facial animation,Gaussian process,Artificial intelligence,Computer vision,Synchronization,Pattern recognition,Gaussian process latent variable model,Speech recognition,Active appearance model,Ground truth,Animation | Conference |
Volume | ISSN | Citations |
5875 | 0302-9743 | 8 |
PageRank | References | Authors |
0.53 | 18 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Salil Deena | 1 | 27 | 3.61 |
Aphrodite Galata | 2 | 368 | 34.84 |