GENERATIVE VIDEO MODELS FOR VISUAL SPEECH SYNTHESIS

Lead Research Organisation: Imperial College London
Department Name: Dept of Computing

Abstract

The purpose of this research is the exploration of new methods on the problem realistic
video synthesis, particularly on the application of visual speech synthesis, by mainly utilizing
the generative adversarial machine learning setting.

Research category: AI, Speech recognition, machine learning

Publications

10 25 50

Studentship Projects

Project Reference Relationship Related To Start End Student Name
EP/N509486/1 01/10/2016 30/09/2021
2295766 Studentship EP/N509486/1 01/04/2018 30/09/2021 Michal Doukas