Key result
Frequency-aware augmentation network achieves ~90% accuracy detecting ADHD and estimating depression severity from audio signals.
Why the study?
Current methods for mental disorder assessment from speech signals rely on hand-crafted features or simplistic time-frequency representations, often overlooking critical details by ignoring differential impacts of frequency bands and temporal fluctuations.
The proposed frequency-aware augmentation network demonstrates robust performance in assessing depression severity and detecting ADHD from audio signals.
Should not yet change clinical practice; leaves open prospective validation of audio-based mental health tools.
Depression and Attention Deficit Hyperactivity Disorder (ADHD) stand out as the common mental health challenges today. In affective computing, speech signals serve as effective biomarkers for mental disorder assessment. Current research, relying on labor-intensive hand-crafted features or simplistic time-frequency representations, often overlooks critical details by not accounting for the differential impacts of various frequency bands and temporal fluctuations. Therefore, we propose a frequency-aware augmentation network with dynamic convolution for depression and ADHD assessment. In the proposed method, the spectrogram is used as the input feature and adopts a multi-scale convolution to help the network focus on discriminative frequency bands related to mental disorders. A dynamic convolution is also designed to aggregate multiple convolution kernels dynamically based upon their attentions which are input-independent to capture dynamic information. Finally, a feature augmentation block is proposed to enhance the feature representation ability and make full use of the captured information. Experimental results on AVEC 2014 and self-recorded ADHD dataset prove the robustness of our method, an RMSE of 9.23 was attained for estimating depression severity, along with an accuracy of 89.8% in detecting ADHD.
No takes yet. Share an insight, caveat, or question.
Li et al. (2025) studied Depression and Attention Deficit Hyperactivity Disorder (ADHD). Frequency-aware augmentation network with dynamic convolution was evaluated on Depression severity and ADHD detection. A proposed frequency-aware augmentation network with dynamic convolution achieved an RMSE of 9.23 for estimating depression severity and an accuracy of 89.8% in detecting ADHD from audio signals.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: