Speech Separation On Libri5Mix
Metrics
SI-SDRi
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | SI-SDRi |
|---|---|
| many-speakers-single-channel-speech | 12.72 |
| separate-and-diffuse-using-a-pretrained | 14.2 |
| sepit-approaching-a-single-channel-speech | 13.7 |
| ocd-learning-to-overfit-with-conditional | 13.4 |