Title
Video Realistic Mouth Animation Based on an Audio Visual DBN Model with Articulatory Features and Constrained Asynchrony
Abstract
This paper presents a mouth animation construction method based on the DBN models with articulatory features (AF_AVDBN), in which the articulatory features of lips, tongue, glottis/velum can be asynchronous within a maximum asynchrony constraint to describe the speech production process more reasonably. Given an audio input and the trained AF_AVDBN models, the optimal visual feature learning algorithm is deduced based on the Maximum Likelihood Estimation criterion. The learned visual features are then used to construct the mouth images for the input speech. Objective and subjective evaluations on the mouth animations of 110 speech sentences show that the learned visual features from the AF_AVDBN models track the real visual features very closely, and the constructed mouth images from the AF_AVDBN models are very much like the real ones.
Year
DOI
Venue
2009
10.1109/ICIG.2009.51
ICIG
Keywords
Field
DocType
audio visual dbn model,constrained asynchrony,face recognition,visual feature,articulatory feature,maximum likelihood estimation,computer animation,asynchrony,maximum likelihood estimation criterion,mouth image,speech synthesis,visual feature learning algorithm,af_avdbn,optimal visual feature,trained af_avdbn model,real visual feature,video realistic mouth animation,mouth images,input speech,mouth animation,mouth animation construction method,af_avdbn model,articulatory features,facial animation,speech production,visualization,speech recognition,maximum likelihood estimate,speech,hidden markov models
Speech synthesis,Pattern recognition,Computer science,Visualization,Speech recognition,Artificial intelligence,Computer facial animation,Animation,Computer animation,Hidden Markov model,Speech production,Feature learning
Conference
ISBN
Citations 
PageRank 
978-1-4244-5237-8
1
0.35
References 
Authors
4
5
Name
Order
Citations
PageRank
Jiang Dongmei111515.28
Peizhen Liu230.73
Ravyse Ilse3436.24
Hichem Sahli447565.19
Werner Verhelst543151.55