Speech Separation on WSJ0-3mix
Metric: SI-SDRi (higher is better)
Metric: SI-SDRi (higher is better)
| # | Model↕ | SI-SDRi▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | SepTDA | 23.7 | No | Boosting Unknown-number Speaker Separation with ... | 2024-01-23 | - |
| 2 | MossFormer2 | 22.2 | No | - | - | Code |
| 3 | MossFormer (L) + DM | 21.2 | No | MossFormer: Pushing the Performance Limit of Mon... | 2023-02-23 | Code |
| 4 | Separate And Diffuse | 20.9 | No | Separate And Diffuse: Using a Pretrained Diffusi... | 2023-01-25 | - |
| 5 | MossFormer (M) + DM | 20.8 | No | MossFormer: Pushing the Performance Limit of Mon... | 2023-02-23 | Code |
| 6 | SepIt | 20.1 | No | SepIt: Approaching a Single Channel Speech Separ... | 2022-05-24 | - |
| 7 | SepFormer | 19.5 | No | Attention is All You Need in Speech Separation | 2020-10-25 | Code |
| 8 | Sandglasset | 17.1 | No | Sandglasset: A Light Multi-Granularity Self-atte... | 2021-03-01 | Code |
| 9 | Gated DualPathRNN | 16.85 | No | Voice Separation with an Unknown Number of Multi... | 2020-02-29 | Code |