Timezone: »
Oral
A probabilistic model for generating realistic lip movements from speech
Gwenn Englebienne · Tim Cootes · Magnus Rattray
The present work aims to model the correspondence between facial motion and speech. The face and sound are modelled separately, with phonemes being the link between both. We propose a sequential model and evaluate its suitability for the generation of the facial animation from a sequence of phonemes, which we obtain from speech. We evaluate the results both by computing the error between generated sequences and real video, as well as with a rigorous double-blind test with human sub jects. Experiments show that our model compares favourably to other existing methods and that the sequences generated are comparable to real video sequences.
Author Information
Gwenn Englebienne (University of Amsterdam)
Tim Cootes
Magnus Rattray (The University of Sheffield)
Related Events (a corresponding poster, oral, or spotlight)
-
2007 Poster: A probabilistic model for generating realistic lip movements from speech »
Wed. Dec 5th 06:30 -- 06:40 PM Room
More from the Same Authors
-
2012 Poster: Fast Variational Inference in the Conjugate Exponential Family »
James Hensman · Magnus Rattray · Neil D Lawrence -
2008 Poster: Efficient Sampling for Gaussian Process Inference using Control Variables »
Michalis Titsias · Neil D Lawrence · Magnus Rattray -
2008 Spotlight: Efficient Sampling for Gaussian Process Inference using Control Variables »
Michalis Titsias · Neil D Lawrence · Magnus Rattray -
2006 Poster: Modelling transcriptional regulation using Gaussian Processes »
Neil D Lawrence · Guido Sanguinetti · Magnus Rattray