Metraipolis › archive › dc_e89593fb747d

Who Said What, and Will It Be Remembered? Evaluating Persistent Speaker Attribution Across Meetings — arXiv:2609.39344

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.39344
License (as archived): CC0-1.0
Archived: 2026-10-07T12:45:16.294Z
SHA-256 of the archived text: 613f5c59b15e71317449106a41bbc9a661d07e5ce1483b81593d4cc498ddd364
Stable URL of this page: https://metraipolis.com/documento/dc_e89593fb747d

How to cite

Who Said What, and Will It Be Remembered? Evaluating Persistent Speaker Attribution Across Meetings — arXiv:2609.39344 — arXiv (en), https://arxiv.org/abs/2609.39344 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e89593fb747d (Metraipolis archive dc_e89593fb747d, sha256 613f5c59b15e71317449106a41bbc9a661d07e5ce1483b81593d4cc498ddd364)

BibTeX

@misc{dce89593fb747d,
  title = {Who Said What, and Will It Be Remembered? Evaluating Persistent Speaker Attribution Across Meetings — arXiv:2609.39344},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.39344},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e89593fb747d; sha256 613f5c59b15e71317449106a41bbc9a661d07e5ce1483b81593d4cc498ddd364},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39344. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Speech transcripts used as long-term memory must preserve both words and stable speaker identities. Existing meeting-transcription metrics either ignore speakers or remap anonymous speakers independently in each recording, so they cannot measure whether the same person retains one identity across meetings. We evaluate persistent speaker attribution with Speaker Identified cpWER (SI-cpWER), which scores a corpus under one global speaker-ID assignment. The benchmark covers five commercial diarize-then-identify cascades, two open academic baselines, and ThyVoice on the full 129-meeting CHiME-8 NOTSOFAR evaluation set in clean and noiseaugmented form, plus CHiME-6. ThyVoice is our end-to-end reference system; it repairs overlap and gates the evidence used to create and update voiceprints. Requiring persistent identity changes the commercial ranking: ThyVoice records lower SI-cpWER than every evaluated commercial cascade in all three conditions and the lowest mean in the full panel, 47.13 versus 54.75 for the next system. Complementary lexical, diarization, per-recording attribution, and speaker-clustering diagnostics characterize upstream error surfaces in the final attributed record. These results show why persistent attribution must be evaluated directly in systems that reuse conversations across time.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI).
Categorie arXiv: Sound (cs.SD) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.39344 — 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 2026-10-07T12:14:14.061Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).