Metraipolis › archive › dc_7b769a775c1e

JYVA at BeTraC: Audio-Based Medical Note Generation with SOAP Section-Specific Queries — arXiv:2610.40695

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.40695
License (as archived)
CC0-1.0
Archived
2026-11-03T06:00:52.665Z
SHA-256 of the archived text
b1cfec418a5a2d70fa2151529b15d6564d12ad564fc9214e4eb4c5fdff2ee7a6
Stable URL of this page
https://metraipolis.com/documento/dc_7b769a775c1e

How to cite

JYVA at BeTraC: Audio-Based Medical Note Generation with SOAP Section-Specific Queries — arXiv:2610.40695 — arXiv (en), https://arxiv.org/abs/2610.40695 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7b769a775c1e (Metraipolis archive dc_7b769a775c1e, sha256 b1cfec418a5a2d70fa2151529b15d6564d12ad564fc9214e4eb4c5fdff2ee7a6)
BibTeX
@misc{dc7b769a775c1e,
  title = {JYVA at BeTraC: Audio-Based Medical Note Generation with SOAP Section-Specific Queries — arXiv:2610.40695},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.40695},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7b769a775c1e; sha256 b1cfec418a5a2d70fa2151529b15d6564d12ad564fc9214e4eb4c5fdff2ee7a6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40695. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present our submission to the Beyond Transcription Challenge (BeTraC) on medical note generation from doctor-patient audio conversations. We propose a section-aware approach based on Qwen2.5-Omni-3B, in which a lightweight Q-Former learns SOAP section-specific queries to extract compact clinical representations from speech. In the lightweight track, our system ranks fourth and substantially outperforms the challenge baseline, achieving a Concept F1 of 0.5005 on the official test set. The organizers' analysis and our heuristic evaluation suggest improved robustness to hallucinations, and better stability under difficult audio conditions. These results show that explicitly modeling SOAP structure through section-specific queries is an effective way to improve the faithfulness and reliability of audio-based medical note generation.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv eess.AS, nuovi lavori del giorno).
Categorie arXiv: Sound (cs.SD) ; Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2610.40695 — 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 2026-11-03T05:42:49.540Z dalla pagina https://arxiv.org/list/eess.AS/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).