Index

This website provides supplementary figures, data and checkpoint to the paper “On the calibration of powerset speaker diarization models”. The structure of the paper is as follow:

  1. Introduction
  2. Model calibration
  3. Annotation-efficient domain adaptation
    1. Finding a minimal training subset
    2. Finding a minimal validation subset
  4. Conclusion

Sections with an hyperlink contain supplementary material. Due to interactive figures, some pages weigh a few megabytes.

Github Google Scholar