TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Speech/Speech Separation/WSJ0-3mix

Speech Separation on WSJ0-3mix

Metric: SI-SDRi (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕SI-SDRi▼Extra DataPaperDate↕Code
1SepTDA23.7NoBoosting Unknown-number Speaker Separation with ...2024-01-23-
2MossFormer222.2No--Code
3MossFormer (L) + DM21.2NoMossFormer: Pushing the Performance Limit of Mon...2023-02-23Code
4Separate And Diffuse20.9NoSeparate And Diffuse: Using a Pretrained Diffusi...2023-01-25-
5MossFormer (M) + DM20.8NoMossFormer: Pushing the Performance Limit of Mon...2023-02-23Code
6SepIt20.1NoSepIt: Approaching a Single Channel Speech Separ...2022-05-24-
7SepFormer19.5NoAttention is All You Need in Speech Separation2020-10-25Code
8Sandglasset17.1NoSandglasset: A Light Multi-Granularity Self-atte...2021-03-01Code
9Gated DualPathRNN16.85NoVoice Separation with an Unknown Number of Multi...2020-02-29Code