Synthesizing Sign Language by Connecting Linguistically Structured Descriptions to a Multi-track Animation System

Animating sign language requires both a model of the structure of the target language and a computer animation system capable of producing the resulting avatar motion. On the language modelling side, AZee proposes a methodology and formal description mechanism to build grammars of Sign languages. It has mostly assumed the existence of an avatar capable of rendering its low-level articulation specifications. On the computer animation side, the Paula animator system proposes a multi-track SL generation platform designed for realism of movements, programmed from its birth to be driven by linguistic input. This paper presents a system architecture making use of the advantages of the two research efforts that have matured in recent years to the point where a connection is now possible. This paper describes the essence of both systems and describes the foundations of a connected system, resulting in a full process from abstract linguistic input straight to animated video. The main contribution is in addressing the trade-off between coarser natural-looking segments and composition of linguistically relevant atoms.