3543 articles – 5273 references  [version française]

hal-00587016, version 1

Animation of generic 3D Head models driven by speech

Lucas Terissi () 1, Mauricio Cerda () a2, Juan C. Gomez () b1, Nancy Hitschfeld-Kahler () c3, Bernard Girau () 2, Renato Valenzuela () c3

IEEE International Conference on Multimedia and Expo - ICME 2011 (2011) To appear

Abstract: In this paper, a system for speech-driven animation of generic 3D head models is presented. The system is based on the inversion of a joint Audio-Visual Hidden Markov Model to estimate the visual information from speech data. Estimated visual speech features are used to animate a simple face model. The animation of a more complex head model is then obtained by automatically mapping the deformation of the simple model to it. The proposed algorithm allows the animation of 3D head models of arbitrary complexity through a simple setup procedure. The resulting animation is evaluated in terms of intelligibility of visual speech through subjective tests, showing a promising performance.

  • a –  INRIA
  • b –  Universidad Nacional de Rosario
  • c –  Universidad de Chile
  • 1:  Laboratory for System Dynamics and Signal Processing
  • Universidad Nacional de Rosario – CIFASIS - CONICET
  • 2:  CORTEX (INRIA Lorraine - LORIA)
  • INRIA – CNRS : UMR7503 – Université Henri Poincaré - Nancy I – Université Nancy II – Institut National Polytechnique de Lorraine (INPL)
  • 3:  Departemento de Ciencias de la Computacion (DCC)
  • Universidad de Chile
  • Collaboration : stic amsud BAVI (09STIC06)
  • Domain : Computer Science/Computer Graphics and Virtual Reality
    Computer Science/Multimedia
    Computer Science/Computational Geometry
  • Keywords : Facial Animation – Hidden Markov Models – Audio-Visual Speech Processing
 
  • hal-00587016, version 1
  • oai:hal.archives-ouvertes.fr:hal-00587016
  • From: 
  • Submitted on: Tuesday, 19 April 2011 10:01:36
  • Updated on: Monday, 16 May 2011 14:48:39