Skip to main content
GameDev.net gamedev.net
2 sources covering this story

The GENEA Challenge 2026: A Large-Scale Disentangled Evaluation of Speech-Driven Gesture Generation on the Seamless Interaction Dataset

A new GENEA Challenge benchmark pushed speech-driven gesture generation through four large-scale human studies, with more than 23,000 votes from 869 testers. The results were sobering: motion realism improved on filtered dataset clips, but most submissions still lagged far behind motion-capture baselines for alignment, responsiveness, and semantic expressiveness.

First reported 1 month, 2 weeks ago • gesture-generation animation embodied-ai benchmark
Want to discuss what this means for developers?
Open discussion

All Sources

View article page
PRIMARY SOURCE
arXiv cs.GR arXiv cs.GR

The GENEA Challenge 2026: A Large-Scale Disentangled Evaluation of Speech-Driven Gesture Generation on the Seamless Interaction Dataset

1 month, 2 weeks ago Read source
arXiv cs.GR arXiv cs.GR 0% match

A Browser-Based Gesture-Driven Avatar Interaction Framework for Metaverse Onboarding Environments

1 month, 2 weeks ago Read source
Read Full Article Back to Feed