Metraipolis › archive › dc_ce743725d4bd
DiaWhisper-DPO: Role-Attributed Transcription of Clinical Interviews via Failure-Mined Preference Optimization — arXiv:2609.16661
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.16661
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T19:19:17.121Z
- SHA-256 of the archived text
c4cf461a37be561564a3351c1a7dffb85efd9d5531df08aa4dc360c0e8e038c4- Stable URL of this page
https://metraipolis.com/documento/dc_ce743725d4bd
How to cite
DiaWhisper-DPO: Role-Attributed Transcription of Clinical Interviews via Failure-Mined Preference Optimization — arXiv:2609.16661 — arXiv (en), https://arxiv.org/abs/2609.16661 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ce743725d4bd (Metraipolis archive dc_ce743725d4bd, sha256 c4cf461a37be561564a3351c1a7dffb85efd9d5531df08aa4dc360c0e8e038c4)
BibTeX
@misc{dcce743725d4bd,
title = {DiaWhisper-DPO: Role-Attributed Transcription of Clinical Interviews via Failure-Mined Preference Optimization — arXiv:2609.16661},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.16661},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ce743725d4bd; sha256 c4cf461a37be561564a3351c1a7dffb85efd9d5531df08aa4dc360c0e8e038c4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.16661. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Automated depression screening from clinical interviews requires attribution of utterances to the clinician or patient. We evaluate two datasets: DAIC-WOZ, where participant-only recordings require re-synthesizing both sides for controlled two-party evaluation, and PDCH-HAMD, comprising voice-converted real Chinese interviews for cross-lingual validation. Cascaded systems combine speaker diarization with role-assignment heuristics, so errors can propagate across stages. We propose an end-to-end model, which we named DiaWhisper, that fine-tunes Whisper-large-v3 with LoRA and an auxiliary frame-level role head for transcription and attribution, together with DiaWhisper-DPO, a failure-mined refinement that uses genuine decoding failures as DPO rejected completions without human preference annotation. On 29 DAIC-WOZ test sessions, DiaWhisper-DPO achieves 0.973 role accuracy and 0.119 DER, 72% below the strongest cascaded baseline, and reduces seed variation from {\sigma} = .205 to .002. Retrained on PDCH-HAMD, it achieves 0.757 role accuracy and improves all 78 session-seed pairs.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-16 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.16661 — 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 2026-10-15T18:32:32.823Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).