DiaWhisper-DPO: Role-Attributed Transcription of Clinical Interviews via Failure-Mined Preference Optimization

2026-09-15

AI Summary

为了解决临床访谈中自动抑郁症筛查时的发言者角色归属问题，提出了一种端到端模型DiaWhisper-DPO，通过LoRA微调和基于真实解码失败案例的优化方法，显著提高了角色归属准确率。

Abstract

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 σ = .205 to .002. Retrained on PDCH-HAMD, it achieves 0.757 role accuracy and improves all 78 session-seed pairs.

Problem

• depression screening
• clinical interviews
• speaker diarization
• role attribution
• cascaded systems

Innovation

• end-to-end model
• LoRA fine-tuning
• frame-level role head
• failure-mined refinement
• DPO rejected completions