LIPS2008: Visual speech synthesis challenge

Barry-John Theobald (1) , Sascha Fagel (2) , Gérard Bailly (3) , Frédéric Elisei (4)

1 Department of Computer Science
2 ISC-TUB - Institute for Speech and Communication
3 GIPSA-MPACIF - GIPSA - Machines Parlantes, Agents Communicants & Interaction Face-à-face
4 GIPSA-Services - GIPSA-Services

In this paper we present an overview of LIPS2008: Visual Speech Synthesis Challenge. The aim of this challenge is to bring together researchers in the field of visual speech synthesis to firstly evaluate their systems within a common framework, and secondly to identify the needs of the wider community in terms of evaluation. In doing so we hope to better understand the differences between the various approaches and to identify the strengths/weaknesses of the competing approaches. In this paper we firstly motivate the need for the challenge, before describing the capture and preparation of the training data, the evaluation framework, and conclude with an outline of possible directions for standardising the evaluation of talking heads.

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

Barry-John Theobald, Sascha Fagel, Gérard Bailly, Frédéric Elisei. LIPS2008: Visual speech synthesis challenge. Interspeech 2008 - 9th Annual Conference of the International Speech Communication Association, Sep 2008, Brisbane, Australia. pp.2310-2313. ⟨hal-00333655⟩