AI RESEARCH

Toward Phonology-Guided Sign Language Motion Generation: A Diffusion Baseline and Conditioning Analysis

arXiv CS.CV

ArXi:2603.17388v1 Announce Type: new Generating natural, correct, and visually smooth 3D avatar sign language motion conditioned on the text inputs continues to be very challenging. In this work, we train a generative model of 3D body motion and explore the role of phonological attribute conditioning for sign language motion generation, using ASL-LEX 2.0 annotations such as hand shape, hand location and movement.