Attention-based acoustic feature fusion network for depression detection

Depression, a common mental disorder, significantly influences individuals and imposes considerable societal impacts. The complexity and heterogeneity of the disorder necessitate prompt and effective detection, which nonetheless, poses a difficult challenge. This situation highlights an urgent requirement for improved detection methods. Exploiting auditory data through advanced machine learning paradigms presents promising research directions. Yet, existing techniques mainly rely on single-dimensional feature models, potentially neglecting the abundance of information hidden in various speech features. To rectify this, we present the novel Attention-Based Acoustic Feature Fusion Network (ABAFnet) for depression detection. ABAFnet combines four different acoustic features into a comprehensive deep neural network, thereby effectively integrating and blending multi-tiered features. We present a novel Type-Adaptive CNN for feature process, a LSTM-Attention Mechanism for features' temporal-spatial computation, and a Dynamic Weight Adjustment module for Linear Late Fusion Network that boosts performance by efficaciously synthesizing these features. The effectiveness of our approach is confirmed via extensive validation on two novel speech databases, CNRAC and CS-NRAC, thereby outperforming previous methods in depression detection and subtype classification. Further in-depth analysis confirms the key role of each feature and highlights the importance of MFCC-related features in speech-based depression detection (SDD).