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

Visual Speech Recognition research benchmarks – Page 2 · SOTA2 Research

Visual Speech Recognition

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

CMU-MOSEAS French

VSR model with prediction-based auxiliary tasks

59.1Mean WER

4

Feb 26, 2026

Multilingual TEDx-Portuguese (MTpt) (test)

70.2Mean Accuracy

4

Feb 26, 2026

Multilingual TEDx Italian (MTit) (test)

VSR model with prediction-based auxiliary tasks

57.9Mean WER

4

Feb 26, 2026

LRS3-TED Full (test)

55.1WER

2

Feb 26, 2026

LRS3-TED Filtered (test)

47WER

1

Feb 26, 2026

Page 2 of 2

Popular datasets

LRS3 CMLR Multilingual TEDx CMU-MOSEAS LRS2

Follow for updates

Join SOTA2 Contact