KAZOO: A Sign Language Generation Platform Based on Production Rules

Annelies Braffort (1) , Michael Filhol (1) , Maxime Delorme (1) , Laurence Bolot (1) , Annick Choisier (1) , Cyril Verrecchia (1)

1 LIMSI - Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur

This paper describes KAZOO, a web application for sign language (SL) generation using a virtual signer. Firstly, it explains the motivation to this project, which is grounded on an approach designed solely from SL corpus analysis and modelling. Then, various projects conducted in the past few years on linguistic modelling and 3D animation are presented. The platform's architecture integrates parts of this work and new pieces of software allowing control and linking of all these components. This is an ongoing project, though the current version offers the possibility to animate a virtual signer automatically and synthesize the contents using an abstract representation, the authors' own linguistic model AZee, providing a means of validating this model.

Mots clés: Sign Language Generation; Virtual Signer; Signing Avatar; Sign Language Generation Virtual Signer Signing Avatar; Sign Language Generation

Domaines: Informatique [cs]

Annelies Braffort, Michael Filhol, Maxime Delorme, Laurence Bolot, Annick Choisier, et al.. KAZOO: A Sign Language Generation Platform Based on Production Rules. Universal Access in the Information Society, 2016, 15, pp.541-550. ⟨10.1007/s10209-015-0415-2⟩. ⟨hal-01633619⟩