YuGui

How diarization assign speakers in overlapped sppech?

4

How does speaker diarization assign speakers in overlapped speech? I saw it was masked in pyannote.audio.pipelines.speaker_diarization line 294. I also question the relation between speech segmentation, resegmentation, and speaker diarization...

I am confused about the calculation clip_nll loss. If my predict : clipwise_output = [-1.2 , -2.3, -0.5] target = [0, 0, 1] torch.mean(clipwise_output * target) = torch.mean([0, 0, -0.5])...