Towards a True Acoustic-Visual Speech Synthesis - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2010

Towards a True Acoustic-Visual Speech Synthesis


This paper presents an initial bimodal acoustic-visual synthesis system able to generate concurrently the speech signal and a 3D animation of the speaker's face. This is done by concatenating bimodal diphone units that consist of both acoustic and visual information. The latter is acquired using a stereovision technique. The proposed method addresses the problems of asyn- chrony and incoherence inherent in classic approaches to audiovisual synthesis. Unit selection is based on classic target and join costs from acoustic-only synthesis, which are augmented with a visual join cost. Preliminary results indicate the benefits of this approach, since both the synthesized speech signal and the face animation are of good quality.
Fichier principal
Vignette du fichier
AVSP10-AT.pdf (935.4 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

inria-00526782 , version 1 (15-10-2010)


  • HAL Id : inria-00526782 , version 1


Asterios Toutios, Utpala Musti, Slim Ouni, Vincent Colotte, Brigitte Wrobel-Dautcourt, et al.. Towards a True Acoustic-Visual Speech Synthesis. 9th International Conference on Auditory-Visual Speech Processing - AVSP2010, Sep 2010, Hakone, Kanagawa, Japan. pp.POS1-8. ⟨inria-00526782⟩
284 View
167 Download


Gmail Facebook Twitter LinkedIn More