Speech Separation on Libri2Mix
Metric: SDRi (higher is better)
Metric: SDRi (higher is better)
| # | Model↕ | SDRi▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | TF-Locoformer (M) | 22.2 | No | TF-Locoformer: Transformer with Local Modeling b... | 2024-08-06 | Code |
| 2 | Conv-Tasnet (Libri1Mix speech enhancement pre-trained) | 14.6 | Yes | Stabilizing Label Assignment for Speech Separati... | 2020-10-29 | Code |
| 3 | Conv-Tasnet (Libri1Mix speech enhancement multi-task) | 14.1 | Yes | Stabilizing Label Assignment for Speech Separati... | 2020-10-29 | Code |
| 4 | Conv-Tasnet | 13.6 | No | Stabilizing Label Assignment for Speech Separati... | 2020-10-29 | Code |