Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Audio-driven talking face generation research benchmarks · SOTA2 Research

Audio-driven talking face generation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

4.6Lip-sync Accuracy

7

Jun 5, 2026

CelebV (randomly sampled 50 videos)

17.921FID

6

Feb 26, 2026

HDTF (randomly sampled 50 videos)

9.084FID

6

Feb 26, 2026

7.99Sc

6

Feb 26, 2026

8.841Sc

6

Feb 26, 2026

Popular datasets

User Study VoxCeleb2 HDTF CelebV OneMin

Follow for updates

Join SOTA2 Contact