SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 15, 2026 · UTC

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-

Read original source ↗ Open in workspace

recordType

paper

region

Global