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-visual speech separation and enhancement research benchmarks · SOTA2 Research

Audio-visual speech separation and enhancement

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Audio-Visual Speech Codec

1.482PESQ

4

Feb 26, 2026

Audio-Visual Speech Codec

1.354PESQ

4

Feb 26, 2026

Mandarin dataset (test)

2.51PESQ

4

Feb 26, 2026

Popular datasets

Lip2Wav Mandarin dataset Facestar

Follow for updates

Join SOTA2 Contact