Towards perceptually realistic talking heads: models, methods and McGurk

Abstract

Motivated by the need for an informative, unbiased, and quantitative perceptual method for the evaluation of a talking head we are developing, we propose a new test based on the &#8220;McGurk Effect.&#8221; Our approach helps to identify strengths and weaknesses in visual--speech synthesis algorithms for talking heads and facial animations, in general, and uses this insight to guide further development. We also evaluate the <i>behavioral</i> quality of our facial animations in comparison to real-speaker footage and demonstrate our tests by applying them to our current speech-driven facial animation system.

DOI: 10.1145/1077399.1077405

Extracted Key Phrases

11 Figures and Tables

Cite this paper

@article{Cosker2004TowardsPR, title={Towards perceptually realistic talking heads: models, methods and McGurk}, author={Darren Cosker and Susan Paddock and A. David Marshall and Paul L. Rosin and Simon K. Rushton}, journal={TAP}, year={2004}, volume={2}, pages={270-285} }