Speaker: Seyed Ahmad Hosseini
Date and place: April 29, 2021 at 10:30, VISIO-CONFERENCE
Digital people are on the rise. We see that emotionally responsive artificial humans are now presenting their appearance in various forms and industries. These digital representations, however, suffer from a lack of intelligibility and natural articulatory face gestures. In this presentation we expose the multilingual visual dubbing result of the joint “AI4EU” project with “InterDigital” and the integration of “Lipsync” to achieve dynamic realistic articulation for 3D digital people. Furthermore, we present the developed plugins, web services and a live demo to conclude the achievement.