@article{pixitjointtrainingofspeakerdiarization,
  title = {PixIT: Joint Training of Speaker Diarization and Speech Separation from Real-world Multi-speaker Recordings},
  author = {Joonas Kalda and Clément Pagés and Ricard Marxer and Tanel Alumäe and Hervé Bredin},
  year = {2024},
  eprint = {2403.02288},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2403.02288v2},
}