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