Show simple item record

dc.contributor.authorHati, Yliess
dc.contributor.authorRousseaux, Francis
dc.contributor.authorDuhart, Clement
dc.date.accessioned2019-07-25T19:19:50Z
dc.date.available2019-07-25T19:19:50Z
dc.date.issued2019-06
dc.identifier.urihttp://hdl.handle.net/1853/61509
dc.descriptionPresented at the 25th International Conference on Auditory Display (ICAD 2019) 23-27 June 2019, Northumbria University, Newcastle upon Tyne, UK.
dc.description.abstractPersonal 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.
dc.publisherGeorgia Institute of Technology
dc.rightsLicensed under Creative Commons Attribution Non-Commercial 4.0 International License.
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0/
dc.subjectAuditory display
dc.subjectPersonal assistants
dc.titleText-driven mouth animation for human computer interaction with personal assistant
dc.typeProceedings
dc.contributor.corporatenameLeonard de Vinci Pole Universitaire. Research Center
dc.contributor.corporatenamel'Université de Reims Champagne. CRESTIC
dc.contributor.corporatenameMassachusettes Institute of Technology. Media Lab
dc.publisher.originalInternational Community on Auditory Display
dc.identifier.doihttps://doi.org/10.21785/icad2019.032


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Licensed under Creative Commons Attribution Non-Commercial 4.0 International License.
Except where otherwise noted, this item's license is described as Licensed under Creative Commons Attribution Non-Commercial 4.0 International License.