Pose-Aware Speech Driven Facial Landmark Animation Pipeline for Automated Dubbing

Pose-Aware Speech Driven Facial Landmark Animation Pipeline for Automated Dubbing

A novel neural pipeline allowing one to generate pose aware 3D animated facial landmarks synchronised to a target speech signal is proposed for the task of automatic dubbing. The goal is to automatically synchronize a target actors’ lips and facial motion to an unseen speech sequence, whi...

Full description

Bibliographic Details
Main Authors: Dan Bigioi, Hugh Jordan, Rishabh Jain, Rachel McDonnell, Peter Corcoran
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
Machine learning
computer vision
lip synchronization
talking head generation
automatic dubbing
audio driven deep fakes
Online Access:https://ieeexplore.ieee.org/document/9994681/

Internet

https://ieeexplore.ieee.org/document/9994681/

Similar Items