Overlap in the audio

[YashThakran]

Hi, I have been using pyaanote for speaker diarization, and the results seem to be mostly good. However, I have observed some issues when there is an overlap of multiple speakers in the audio, pyannote labels it as any of the single speakers.

Is there any way to fix this problem or improve performance in case of overlaps?

I have tried embedding_exclude_overlap param but it doesn't help.

[github-actions[bot]]

Thank you for your issue. We found the following entries in the FAQ which you may find helpful:

• Can I apply pretrained pipelines on audio already loaded in memory?
• Does pyannote support streaming speaker diarization?

Feel free to close this issue if you found an answer in the FAQ.

If your issue is a feature request, please read this first and update your request accordingly, if needed.

If your issue is a bug report, please provide a minimum reproducible example as a link to a self-contained Google Colab notebook containing everthing needed to reproduce the bug:

• installation
• data preparation
• model download
• etc.

Providing an MRE will increase your chance of getting an answer from the community (either maintainers or other power users).

Companies relying on pyannote.audio in production may contact me via email regarding:

• paid scientific consulting around speaker diarization and speech processing in general;
• custom models and tailored features (via the local tech transfer office).

This is an automated reply, generated by FAQtory

[hbredin]

Your best guess is to finetune the segmentation model on your own data. See this tutorial.

Also, I'd be happy to have a look at a short excerpt of your file where this does not work as expected.

[stale[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.