A new trainable trajectory formation system for facial animation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2006

A new trainable trajectory formation system for facial animation

Résumé

A new trainable trajectory formation system for facial animation is here proposed that dissociates parametric spaces and methods for movement planning and execution. Movement planning is achieved by HMM-based trajectory formation. Movement execution is performed by concatenation of multi-represented diphones. Movement planning ensures that the essential visual characteristics of visemes are reached (lip closing for bilabials, rounding and opening for palatal fricatives, etc) and that appropriate coarticulation is planned. Movement execution grafts phonetic details and idiosyncratic articulatory strategies (dissymetries, importance of jaw movements, etc) to the planned gestural score.
Fichier principal
Vignette du fichier
og_EXPLIN06.pdf (585.88 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00366487 , version 1 (08-03-2009)

Identifiants

  • HAL Id : hal-00366487 , version 1

Citer

Oxana Govokhina, Gérard Bailly, Gaspard Breton, Paul Bagshaw. A new trainable trajectory formation system for facial animation. Workshop on Experimental Linguistics, Aug 2006, Athens, Greece. pp.25-32. ⟨hal-00366487⟩

Collections

UGA CNRS ICP
159 Consultations
75 Téléchargements

Partager

Gmail Facebook X LinkedIn More