Speech Separation On Wsj0 4Mix
Metriken
SI-SDRi
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | SI-SDRi |
|---|---|
| sequence-to-multi-sequence-learning-via | 12.5 |
| boosting-unknown-number-speaker-separation | 22.0 |
| Modell 3 | 10.2 |
| multi-decoder-dprnn-high-accuracy-source | 9.3 |
| voice-separation-with-an-unknown-number-of | 12.88 |