Title :
Use of a statistical model for lip synthesis
Author_Institution :
Genoa Univ., Italy
Abstract :
The goal of this work is to develop a statistical model of the lip movements for a specific speaker. The system is based on a Markov model trained on the visual part of the speech production. Such a model allows for an automatic generation of mouth shapes having fairly good natural looking dynamics. Applications might be both in image analysis and in image synthesis
Keywords :
Markov processes; self-organising feature maps; speaker recognition; speech recognition; unsupervised learning; Markov model; automatic mouth shape generation; competitive networks; image analysis; image synthesis; lip movements; lip synthesis; natural looking dynamics; self organizing maps; specific speaker; speech production; statistical model; video sequence; Hidden Markov models; Lips; Mouth; Neural networks; Neurons; Production systems; Shape; Speech synthesis; Tracking; Unsupervised learning;
Conference_Titel :
Electronics, Circuits and Systems, 1998 IEEE International Conference on
Conference_Location :
Lisboa
Print_ISBN :
0-7803-5008-1
DOI :
10.1109/ICECS.1998.814076
