Extending the AZee-Paula shortcuts to enable natural proform synthesis
Résumé
Proform structures such as classifier predicates have traditionally challenged Sign Language (SL) synthesis systems, particularly in
respect to the production of smooth natural motion. To address this issue a synthesizer must necessarily leverage a structured linguistic
model for such constructs to specify the linguistic constraints, and also an animation system that is able to provide natural avatar motion
within the confines of those constraints. The proposed system bridges two existing technologies, taking advantage of the ability of
AZee to encode both the form and functional linguistic aspects of the proform movements and on the Paula avatar system to provide
convincing human motion. The system extends a previous principle that more natural motion arises from leveraging knowledge of larger
structures in the linguistic description.
Origine : Fichiers produits par l'(les) auteur(s)
Loading...