MOTHER: A new generation of talking heads providing a flexible articulatory control for video-realistic speech animation

Abstract : This article presents the first version of a talking head, called MOTHER (MOrphable Talking Head for Enhanced Reality), based on an articulatory model describing the degrees-offreedom of visible (lips, cheeks...) but also partially or indirectly visible (jaw, tongue...) speech articulators. Skin details are rendered using texture mapping/blending techniques. We illustrate here the flexibility of such an articulatory control of video-realistic speaking faces by first demonstrating its ability in tracking facial movements by an optical-to-articulatory inversion using an analysis-by-synthesis technique. The stability and reliability of the results allow the automatic inversion of large video sequences. Inversion results are here used to build automatically a coarticulation model for the generation of facial movements from text. It improves the previous Text-To- AudioVisual-Speech (TTAVS) synthesizer developed at the ICP both in terms of the accuracy and realism.
Type de document :
Communication dans un congrès
Int. Conference of Spoken Language Processing, ICSLP'2000, Oct 2000, Pekin, China. 2000
Liste complète des métadonnées

Littérature citée [11 références]  Voir  Masquer  Télécharger


https://hal.inria.fr/inria-00389362
Contributeur : Lionel Reveret <>
Soumis le : jeudi 28 mai 2009 - 16:00:46
Dernière modification le : mercredi 14 février 2018 - 15:48:01
Document(s) archivé(s) le : jeudi 10 juin 2010 - 23:59:27

Fichiers

Identifiants

  • HAL Id : inria-00389362, version 1

Collections

ICP | UGA

Citation

Lionel Reveret, Gérard Bailly, Pierre Badin. MOTHER: A new generation of talking heads providing a flexible articulatory control for video-realistic speech animation. Int. Conference of Spoken Language Processing, ICSLP'2000, Oct 2000, Pekin, China. 2000. 〈inria-00389362〉

Partager

Métriques

Consultations de la notice

553

Téléchargements de fichiers

579