Multi-Track Bottom-Up Synthesis from Non-Flattened AZee Scores - Archive ouverte HAL Access content directly
Conference Papers Year : 2022

Multi-Track Bottom-Up Synthesis from Non-Flattened AZee Scores

Abstract

We present an algorithm to improve the pre-existing bottom-up animation system for AZee descriptions to synthesize sign language utterances. Our algorithm allows us to synthesize AZee descriptions by preserving the dynamics of underlying blocks. This bottom-up approach aims to deliver procedurally generated animations capable of generating any sign language utterance if an equivalent AZee description exists. The proposed algorithm is built upon the modules of an open-source animation toolkit and takes advantage of the integrated inverse kinematics solver and a non-linear editor.

Keywords

Fichier principal
Vignette du fichier
70018_Paper.pdf (3.23 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03721720 , version 1 (12-07-2022)

Identifiers

  • HAL Id : hal-03721720 , version 1

Cite

Paritosh Sharma, Michael Filhol. Multi-Track Bottom-Up Synthesis from Non-Flattened AZee Scores. 7th Workshop on Sign Language Translation and Avatar Technology: The Junction of the Visual & the Textual Challenges and Perspectives (SLTAT 7), Jun 2022, Marseille, France. ⟨hal-03721720⟩
112 View
52 Download

Share

Gmail Facebook X LinkedIn More