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 Extraction on WSJ0-mix benchmark leaderboard · SOTA2 Research

Research Benchmarks

Audio-Visual Speech Extraction on WSJ0-mix

12SI-SDR (dB)Gu et al.

Updated 2mo ago

Evaluation Results

Method	Links
Gu et al.2026.05		12	—	—

SOTA Paper

Gu et al.

Multi-modal Multi-channel Target Speech Separation

Dataset

WSJ0

Follow for updates

Join SOTA2 Contact

Related Benchmarks

Speech Separation on Hard (test)Audio-Visual Speech Extraction on VoxCeleb-Sim Audio-Visual Speech Extraction on AVSpeech Audio-Visual Speech Extraction on FAIR-Play