Realistic visual speech synthesis in WebGL

Authors: Andoni Mujika, Helen Diez, Aitor Alvarez, Miren Urteaga, David Oyarzun

Date: 20.06.2013


PDF

Abstract

This paper presents the work that has been done to develop a web application that shows the face of a virtual character pronouncing the sentences the user sets. The level of realism was high and the performance was fast enough. The application makes use of WebGL, speech processing, text to speech and co-articulation technologies to obtain the virtual pronunciation. The paper shows the implementation of the technologies and the optimization strategies that have been followed to ensure the efficiency of the application.

BIB_text

@Article {
author = {Andoni Mujika, Helen Diez, Aitor Alvarez, Miren Urteaga, David Oyarzun},
title = {Realistic visual speech synthesis in WebGL},
pages = {207},
keywds = {

WebGL, facial animation parameters, visual speech synthesis


}
abstract = {

This paper presents the work that has been done to develop a web application that shows the face of a virtual character pronouncing the sentences the user sets. The level of realism was high and the performance was fast enough. The application makes use of WebGL, speech processing, text to speech and co-articulation technologies to obtain the virtual pronunciation. The paper shows the implementation of the technologies and the optimization strategies that have been followed to ensure the efficiency of the application.


}
isbn = {978-1-4503-2133-4},
isi = {1},
date = {2013-06-20},
year = {2013},
}
Vicomtech

Parque Científico y Tecnológico de Gipuzkoa,
Paseo Mikeletegi 57,
20009 Donostia / San Sebastián (Spain)

+(34) 943 309 230

close overlay