Speech Separation on GRID corpus (mixed-speech)
Metric: SDR (higher is better)
LeaderboardDataset
Loading chart...
Results
Submit a result| # | Model↕ | SDR▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | 9.6 | No | MIDI: Multi-Instance Diffusion for Single Image ... | 2024-12-04 | - | |
| 2 | Audio-Visual concat-ref | 8.05 | No | Face Landmark-based Speaker-Independent Audio-Vi... | 2018-11-06 | Code |