Generation of Multimodal Bahaviors
Résumé
One of the main challenges when developing Embodied Conversational Agents ECAs is to give them the ability to autonomously produce meaningful and coordinated verbal and nonverbal behaviors. Those behaviors concern the movement of some body parts, simultaneously or not, that usually suits the context of the speech, accentuate its effect or give it another interpretation.
There are different models that can compute multimodal behaviors for virtual agent. Our goal is to merge some of them to have a large range of behaviors to create expressive ECAs.
Origine | Fichiers produits par l'(les) auteur(s) |
---|