Speaker Diarization On Dihard 1
Metrics
DER(%)
FA
Miss
Results
Performance results of various models on this benchmark
Model Name | DER(%) | FA | Miss | Paper Title | Repository |
|---|---|---|---|---|---|
| pyannote (MFCC) | 10.5 | 6.8 | 3.7 | pyannote.audio: neural building blocks for speaker diarization | - |
| Baseline (the best result in the literature as of Oct.2019) | 11.2 | 6.5 | 4.7 | pyannote.audio: neural building blocks for speaker diarization | - |
| pyannote (waveform) | 9.9 | 5.7 | 4.2 | pyannote.audio: neural building blocks for speaker diarization | - |
0 of 3 row(s) selected.