| Paper | Code | SI-SDRi | ModelName | ReleaseDate |
|---|---|---|---|---|
| Boosting Unknown-number Speaker Separation with Transformer Decoder-based Attractor | 21.0 | SepTDA | 2024-01-23 | |
| Many-Speakers Single Channel Speech Separation with Optimal Permutation Training | ✓ Link | 13.22 | Hungarian PIT | 2021-04-18 |
| Sequence to Multi-Sequence Learning via Conditional Chain Mapping for Mixture Signals | 11.7 | Conditional TasNet | 2020-06-25 | |
| Toward Speech Separation in The Pre-Cocktail Party Problem with TasTas | ✓ Link | 11.14 | TasTas | 2020-10-28 |
| Voice Separation with an Unknown Number of Multiple Speakers | ✓ Link | 10.56 | Gated DualPathRNN | 2020-02-29 |
| Multi-Decoder DPRNN: High Accuracy Source Counting and Separation | ✓ Link | 5.9 | Multi-Decoder DPRNN | 2020-11-24 |