Comparison between extended training and retraining
| Method | Noise set | PESQ-WB↑ | SISDR↑ | STOI↑ | MOS↑ | ||
|---|---|---|---|---|---|---|---|
| Csig | Cbak | Covl | |||||
| Retraining | N15 | 2.2317 | 8.6627 | 0.9216 | 3.3851 | 2.7422 | 2.7662 |
| Extended | N9, N6 | 2.2337 | 8.6254 | 0.9238 | 3.3810 | 2.7264 | 2.7653 |
| Extended (best of the ten) | N9, N6 | 2.2514 | 8.6851 | 0.9258 | 3.3865 | 2.7863 | 2.8237 |
| Method | Noise set | PESQ-WB | |||||
|---|---|---|---|---|---|---|---|
| Csig | Cbak | Covl | |||||
| Retraining | N15 | 2.2317 | 0.9216 | ||||
| Extended | N9, N6 | 8.6254 | 3.3810 | 2.7264 | 2.7653 | ||
| Extended (best of the ten) | N9, N6 | ||||||
Sharing content requires targeting cookies to be enabled. Please update your cookie preferences to use this feature.