Metraipolis › archive › dc_feea613f3c61
When Forgetting Looks Like Improvement: Metric Masking in Streaming Diarizer Adaptation and the Price of Rehearsal — arXiv:2610.08828
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.08828
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T11:25:57.987Z
- SHA-256 of the archived text
17c450d0cf7b8dced6494445034ef18e2441d3de23786b1bc1095848ae81eaef- Stable URL of this page
https://metraipolis.com/documento/dc_feea613f3c61
How to cite
When Forgetting Looks Like Improvement: Metric Masking in Streaming Diarizer Adaptation and the Price of Rehearsal — arXiv:2610.08828 — arXiv (en), https://arxiv.org/abs/2610.08828 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_feea613f3c61 (Metraipolis archive dc_feea613f3c61, sha256 17c450d0cf7b8dced6494445034ef18e2441d3de23786b1bc1095848ae81eaef)
BibTeX
@misc{dcfeea613f3c61,
title = {When Forgetting Looks Like Improvement: Metric Masking in Streaming Diarizer Adaptation and the Price of Rehearsal — arXiv:2610.08828},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.08828},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_feea613f3c61; sha256 17c450d0cf7b8dced6494445034ef18e2441d3de23786b1bc1095848ae81eaef},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08828. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Small-data adaptation can improve speech detection while degrading speaker attribution. We study this discrepancy in a released streaming diarizer adapted on 7.5 h of two-party conversation and evaluated across six corpora. Adaptation substantially improves in-domain diarization performance and transfers to an independent corpus. However, this improvement is not consistent across evaluation scenarios as the additional confusion is mainly associated with impaired temporal identity consistency rather than speaker-count errors. A local-remapping diagnostic reveals different patterns of identity degradation across corpora, indicating that adaptation may alter how streaming models maintain speaker assignments over time. Rehearsal reduces the observed degradation but reduces the cross-domain transfer performance. These results highlight the need to jointly evaluate detection accuracy, identity consistency, and retention behavior when adapting streaming diarization systems. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL) ; Sound (cs.SD); Audio and Speech Processing (eess.AS). Pagina del lavoro: https://arxiv.org/abs/2610.08828 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T10:24:06.302Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).