Text-driven mouth animation for human computer interaction with personal assistant

View/ Open
Date
2019-06Author
Hati, Yliess
Rousseaux, Francis
Duhart, Clement
Metadata
Show full item recordAbstract
Personal assistants are becoming more pervasive in our environments but still do not provide natural interactions. Their lack of realism in term of expressiveness and their lack of visual feedback can create frustrating experiences and make users lose patience. In this sense, we propose an end-to-end trainable neural architecture for text-driven 3D mouth animations. Previous works showed such architectures provide better realism and could open the door for integrated affective Human Computer Interface (HCI). Our study shows that such visual feedback improves users� comfort for 78% of the candidates significantly while slightly improving their time perception.