Speech Separation On Voxceleb2
Métriques
SDRi
SI-SNRi
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | SDRi | SI-SNRi |
|---|---|---|
| rtfs-net-recurrent-time-frequency-modelling | 12.4 | 11.5 |
| rtfs-net-recurrent-time-frequency-modelling | 13.6 | 12.4 |
| scanet-a-self-and-cross-attention-network-for | 15.1 | 14.0 |
| rtfs-net-recurrent-time-frequency-modelling | 12.8 | 11.8 |
| an-audio-visual-speech-separation-model | - | 11.9 |