Speaker Diarization On Ami Lapel
Métriques
DER(%)
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | DER(%) | Paper Title | Repository |
|---|---|---|---|
| TitaNet-M (NME-SC) | 1.99 | TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context | - |
| TitaNet-L (NME-SC) | 2.03 | TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context | - |
| ECAPA (SC) | 2.36 | TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context | - |
| TitaNet-S (NME-SC) | 2.00 | TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context | - |
0 of 4 row(s) selected.