En poursuivant votre navigation sur ce site, vous acceptez le dépôt de cookies dans votre navigateur. (En savoir plus)

PhD: Analysis and synthesis of Sign Language movement

This offer is available in the following languages:
Français - Anglais

Date Limite Candidature : vendredi 4 décembre 2020

Assurez-vous que votre profil candidat soit correctement renseigné avant de postuler. Les informations de votre profil complètent celles associées à chaque candidature. Afin d’augmenter votre visibilité sur notre Portail Emploi et ainsi permettre aux recruteurs de consulter votre profil candidat, vous avez la possibilité de déposer votre CV dans notre CVThèque en un clic !

Faites connaître cette offre !

General information

Reference : UPR3251-MICFIL-001
Workplace : ORSAY
Date of publication : Friday, November 13, 2020
Scientific Responsible name : Michael Filhol
Type of Contract : PhD Student contract / Thesis offer
Contract Period : 36 months
Start date of the thesis : 1 April 2021
Proportion of work : Full time
Remuneration : 2 135,00 € gross monthly

Description of the thesis topic

The formal model AZee developed in our research team enables the synthesis of Sign Language with virtual signers (3D avatars). The model specifies the motion pieces to generate, together with their synchronisation. But at the low level of articulation, if used directly, the formal specification raises problems in terms of the dynamics of the rendered motion, which tends to look robotic. The solution is to combine coarser, pre-animated blocks instead of minimal articulatory constraints only. These blocks can be of various types: recorded as motion capture (mocap) data, generated by a dynamic geometric process (model), manually pre-animated by an artist... The goal of this thesis work is to determine the best way in which to animate each of the elements specified by AZee, and to implement an animation system, for example based on Blender, a free/libre software 3D animation platform. To achieve this, data analysis will be possible on actual Sign Language data, already recorded and available to study, whether mocap or video, and more can be cpatured if needed.

Work Context

The thesis is supported by a gestural server project, a service comparable to telephone voice servers. Hosted at the lab, with dedicated office space and work station. Financial support planned for further equipment and travel.

We talk about it on Twitter!