{"ID":5937908,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-07T07:32:41.825041382Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.03744","arxiv_id":"2607.03744","title":"Can Conversational Temporal Dynamics Improve Depression Detection in Dyads? A Preliminary Investigation in Multi-Modality Perspectives","abstract":"Automatic depression detection from clinical interviews typically models the semantic content and acoustic characteristics of participant speech. However, the interactional timing between the clinician and participant remains comparatively under-modeled. We investigate conversational temporal dynamics, specifically dyadic turn-pair timing, as a primary modality fused with self-supervised encoders. Evaluated on the DAIC-WOZ dataset, we compare a compact 24-dimensional timing module against frozen WavLM-large and RoBERTa-large baseline detectors. This temporal module achieves the highest single-modality performance on the development set. Furthermore, a convex-weighted late fusion strategy improves overall performance to 0.804 and 0.669 macro-F1 on the development and test sets, respectively. The learned fusion effectively assigns zero weight to acoustics, demonstrating that conversational timing serves as a lightweight, interpretable complement for dyadic depression screening.","short_abstract":"Automatic depression detection from clinical interviews typically models the semantic content and acoustic characteristics of participant speech. However, the interactional timing between the clinician and participant remains comparatively under-modeled. We investigate conversational temporal dynamics, specifically dya...","url_abs":"https://arxiv.org/abs/2607.03744","url_pdf":"https://arxiv.org/pdf/2607.03744v1","authors":"[\"Hanie Kang\",\"Huang-Cheng Chou\",\"Sudarsana Reddy Kadiri\",\"Shrikanth Narayanan\"]","published":"2026-07-04T07:33:22Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[]","has_code":false}