Morphing Generic Organs To Speaker-Specific Anatomies

Maxime Berar (1) , Gérard Bailly (2) , Matthieu Chabanas (3) , Michel Desvignes (1) , Frédéric Elisei (2) , Matthias Odisio (2) , Yohan Payan (4)

1 LIS - Laboratoire des images et des signaux
2 ICP - Institut de la communication parlée
3 TIMC-IMAG - Techniques de l'Ingénierie Médicale et de la Complexité - Informatique, Mathématiques et Applications, Grenoble - UMR 5525
4 TIMC-IMAG-GMCAO - Gestes Medico-chirurgicaux Assistés par Ordinateur

We present here a framework for developing a generic talking head capable of reproducing the anatomy and the facial deformations induced by speech movements with only a few parameters. Speech-related facial movements are controlled by six parameters. We characterize the skull and mandible variability by six and seven free parameters respectively. Speaker-specific skull, jaw and face data are normalized using generic meshes of these organs and a robust 3D-to-3D matching procedure. Further analysis of these normalized data is performed using a decomposition of the 3D variance based on iterative principal component analysis aimed at identifying and predicting kinematic consequences of anatomical settings.

Mots clés: Statistical skull and face model; elastic registration

Domaines: Biomécanique [physics.med-ph]; Biomécanique [physics.med-ph]; Statistiques [math.ST]; Ingénierie biomédicale

Maxime Berar, Gérard Bailly, Matthieu Chabanas, Michel Desvignes, Frédéric Elisei, et al.. Morphing Generic Organs To Speaker-Specific Anatomies. J. Harrington & M. Tabain. Speech Production: Models, Phonetic Processes, and Techniques, Psychology Press, New York, pp.341-362, 2006, Chapter 20, ISBN 1841694371. ⟨hal-00108522⟩