Speaker Diarization On Callhome 109
Metriken
DER(%)
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
| Paper Title | ||
|---|---|---|
| d-vector + spectral | 12.54 | Speaker Diarization with LSTM |
| titanet-s | 1.11 | TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context |
0 of 2 row(s) selected.