A Frequency-aware Augmentation Network for Mental Disorders Assessment from Audio

TL;DR

This paper introduces a frequency-aware augmentation network with dynamic convolution for improved assessment of depression and ADHD from speech spectrograms, outperforming existing methods in accuracy and robustness.

Contribution

It presents a novel frequency-aware network with multi-scale and dynamic convolution modules, enhancing feature extraction for mental disorder assessment from audio signals.

Findings

Achieved RMSE of 9.23 for depression severity estimation

Attained 89.8% accuracy in ADHD detection

Proved robustness on AVEC 2014 and ADHD datasets

Abstract

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.