Title :
A Real-Time Lip SYNC System Using a Genetic Algorithm for Automatic Neural Network Configuration
Author :
Zoric, Goranka ; Pandzic, Igor S.
Author_Institution :
Dept. of Telecommun., Zagreb Univ.
Abstract :
In this paper we present a new method for mapping a natural speech to the lip shape animation in the real time. The speech signal, represented by MFCC vectors, is classified into viseme classes using neural networks. The topology of neural networks is automatically configured using genetic algorithms. This eliminates the need for tedious manual neural network design by trial and error and considerably improves the viseme classification results. This method is suitable for real-time and offline applications
Keywords :
genetic algorithms; neural nets; signal classification; signal representation; speech processing; MFCC vector; Mel-frequency cepstrum coefficients; genetic algorithm; lip shape animation; natural speech; neural network topology; real time lip sync system; speech signal representation; viseme classification; Computer networks; Facial animation; Genetic algorithms; Mouth; Neural networks; Real time systems; Shape; Speech analysis; Telecommunication computing; Tongue;
Conference_Titel :
Multimedia and Expo, 2005. ICME 2005. IEEE International Conference on
Conference_Location :
Amsterdam
Print_ISBN :
0-7803-9331-7
DOI :
10.1109/ICME.2005.1521684