Metraipolis › archive › dc_cdd6f3d52cea

Toward accurate speaker inventories for online speaker diarization — arXiv:2610.11278

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.11278
License (as archived)
CC0-1.0
Archived
2026-10-09T07:14:06.774Z
SHA-256 of the archived text
882da49462e8505e750c28fafe94506e34895c53e0076b098aa705159ceec3f5
Stable URL of this page
https://metraipolis.com/documento/dc_cdd6f3d52cea

How to cite

Toward accurate speaker inventories for online speaker diarization — arXiv:2610.11278 — arXiv (en), https://arxiv.org/abs/2610.11278 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cdd6f3d52cea (Metraipolis archive dc_cdd6f3d52cea, sha256 882da49462e8505e750c28fafe94506e34895c53e0076b098aa705159ceec3f5)
BibTeX
@misc{dccdd6f3d52cea,
  title = {Toward accurate speaker inventories for online speaker diarization — arXiv:2610.11278},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.11278},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cdd6f3d52cea; sha256 882da49462e8505e750c28fafe94506e34895c53e0076b098aa705159ceec3f5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11278. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

An online speaker diarizer maintains a growing inventory of speakers, and applications read it directly: a live transcript enumerates them as they appear. Existing systems either fix the inventory's size in advance, so speakers beyond that size are merged, or grow it on distance alone, so noise and turn boundaries split speakers. Scored on speaker count over nine public datasets, both failures appear where DER reports neither: on VoxSRC-23 the fixed-capacity systems return 44-46% too few speakers and the unbounded tracker with the lowest DER 63% too many. We build on that embedding-based tracker and change only what triggers a registration. A candidate speaker pool keeps unregistered embeddings apart and registers a speaker only once one candidate has gathered enough mutually compatible embeddings; commit-gated label assignment holds an output while its candidate is undecided, so no speaker appears in the output before it is confirmed. Across the nine datasets the macro speaker-count error falls from 225% to 21% of the reference and macro DER from 17.59% to 15.95%, at a mean added latency of 0.109s over all outputs; on VoxSRC-23 the tracker obtains both the lowest DER and the most accurate speaker count of the systems compared.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv eess.AS, nuovi lavori del giorno).
Categorie arXiv: Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2610.11278 — 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 2026-10-09T07:08:27.910Z dalla pagina https://arxiv.org/list/eess.AS/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).