| Paper | Code | SI-SDRi | ModelName | ReleaseDate |
|---|---|---|---|---|
| Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation | ✓ Link | 18.4 | SepReformer-L + DM | 2024-06-10 |
| MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation | ✓ Link | 18.1 | MossFormer2 | 2023-12-19 |
| MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions | ✓ Link | 17.3 | MossFormer (L) + DM | 2023-02-23 |
| An efficient encoder-decoder architecture with top-down attention for speech separation | ✓ Link | 15.2 | TDANet Large | 2022-09-30 |
| An efficient encoder-decoder architecture with top-down attention for speech separation | ✓ Link | 14.8 | TDANet | 2022-09-30 |
| Wanna hear your voice? A sample is all we need! | 12.964 | WHYV | 2024-10-01 |