AVSP 2003 - International Conference on Audio-Visual Speech Processing

September 4-7, 2003
St. Jorioz, France

Evaluation of a Talking Head based on Appearance Models

Barry-John Theobald (1), J. Andrew Bangham (1), Iain Matthews (2), Gavin Cawley (1)

(1) School of Information Systems, University of East Anglia, Norwich, UK
(2) Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA

In this paper we describe how 2D appearance models can be applied to the problem of creating a near-videorealistic talking head. A speech corpus of a talker uttering a set of phonetically balanced training sentences is analysed using a generative model of the human face. Segments of original parameter trajectories corresponding to the synthesis unit are extracted from a codebook, normalised, blended, concatenated and smoothed before being applied to the model to give natural, realistic animations of novel utterances. We also present some early results of subjective tests conducted to determine the realism of the synthesiser.


Full Paper

Bibliographic reference.  Theobald, Barry-John / Bangham, J. Andrew / Matthews, Iain / Cawley, Gavin (2003): "Evaluation of a talking head based on appearance models", In AVSP 2003, 187-192.