The paper proposes a transparent framework that links speech acoustic features—such as pitch variability, pauses, and speech tempo—to DSM‑5 indicators of depression, offering interpretable, indicator‑level outputs instead of opaque black‑box models. It runs locally on commodity hardware to preserve privacy and has been preliminarily evaluated on the DAIC‑WOZ dataset, showing consistent associations between acoustic cues and DSM‑5 indicators of psychomotor change and concentration difficulty. Future work aims to validate the approach on longitudinal data and expand multimodal integration while keeping edge constraints.
arXiv:2607. 03744v1 Announce Type: new Abstract: Automatic depression detection from clinical interviews typically models the semantic content and acoustic characteristics of participant speech.
arXiv:2607. 25888v1 Announce Type: cross Abstract: This study identifies new depression biomarkers based on the dynamical properties of tract variables, which represent geometric features describing the configuration of the speech articulators.
MERID is a framework that uses recursive self‑improvement agents to autonomously develop multimodal pipelines for detecting major depressive disorder. It aligns multimodal records with depression targets, jointly modifies representations, fusion, and predictors, and guides revisions through evidence‑guided evolution to validate improvements before inheritance. Experiments on depression benchmarks show MERID outperforms existing multimodal and agent‑based baselines, especially highlighting the importance of acoustic and linguistic cues.
EviDep is a multimodal evidential regression framework for estimating depression severity from audio–visual recordings, incorporating multi‑scale temporal modeling and shared–private representation learning. It uses frequency‑aware feature extraction to decompose behavioral sequences into multiple frequency bands, refined by scale‑specific experts, and applies disentangled evidential learning to separate cross‑modal shared and modality‑specific information. The model outputs Normal‑Inverse‑Gamma distributions via multi‑branch evidential regression, enabling estimation of depression severity along with aleatoric and epistemic uncertainty, and demonstrates competitive accuracy on several benchmark datasets.
arXiv:2606. 05561v1 Announce Type: cross Abstract: Speech-based mental health screening offers scalable depression detection, yet clinical deployment faces a significant barrier: users' privacy concerns about demographic information exposure.
arXiv:2501. 16106v2 Announce Type: replace Abstract: Recent advances in multimodal depression recognition for clinical interviews (MDRC) have demonstrated the potential of AI systems by integrating textual, acoustic, and facial cues.
arXiv:2606. 11197v1 Announce Type: cross Abstract: Speech-based automatic estimation of depression levels is essential for enabling early detection and timely intervention, particularly in resource-constrained mental health settings.
The study investigates how a large language model, Gemma-3-27B-PT, internally represents depressive symptoms. By applying mechanistic interpretability methods to the model’s residual stream, researchers found that symptom groups are geometrically distinct at layer 21, and that projected symptom vectors align with clinician-annotated rankings across mood, somatic, and suicidality dimensions. Additionally, a single depression vector at this layer can differentiate depressive from non-depressive text with an AUC of 0.789, suggesting a potential emotional valence gate for symptom projection.
Automatic depression detection using audio-visual data faces significant challenges, particularly in disentangling overlapping feature distributions and establishing robust decision boundaries. To address this, we propose a fine-grained multimodal framework featuring a temporal encoder and a mutual transformer to facilitate deep cross-modal fusion.
The paper presents a bi‑modal speech‑level transformer that eliminates segment‑level labeling and introduces a hierarchical attention interpretation method. By using gradient‑weighted attention maps from all attention layers, the model provides both speech‑level and sentence‑level explanations of depression detection. Experimental results show the transformer outperforms a segment‑level model (p=0.854 vs. 0.732, r=0.947 vs. 0.808, F1=0.897 vs. 0.768).
arXiv:2607. 00986v1 Announce Type: new Abstract: Automatically detecting stress in speech provides an unobtrusive way to gain insights relevant to behavioral research or clinical assessment.
arXiv:2607. 21496v1 Announce Type: cross Abstract: Cognitive impairment (CI) is a growing public health concern.