Density Adaptive Attention-based Speech Network: Enhancing Feature Understanding for Mental Health Disorders
This work addresses the problem of data scarcity and individual variability in speech-based depression detection for mental health diagnostics, representing an incremental improvement with enhanced interpretability.
The paper tackles automated depression detection from speech by introducing two parameter-efficient and explainable models, DAAMAudioCNNLSTM and DAAMAudioTransformer, which achieve state-of-the-art F1 macro scores of 0.702 and 0.72 on the DAIC-WOZ dataset without relying on supplementary information.
Speech-based depression detection poses significant challenges for automated detection due to its unique manifestation across individuals and data scarcity. Addressing these challenges, we introduce DAAMAudioCNNLSTM and DAAMAudioTransformer, two parameter efficient and explainable models for audio feature extraction and depression detection. DAAMAudioCNNLSTM features a novel CNN-LSTM framework with multi-head Density Adaptive Attention Mechanism (DAAM), focusing dynamically on informative speech segments. DAAMAudioTransformer, leveraging a transformer encoder in place of the CNN-LSTM architecture, incorporates the same DAAM module for enhanced attention and interpretability. These approaches not only enhance detection robustness and interpretability but also achieve state-of-the-art performance: DAAMAudioCNNLSTM with an F1 macro score of 0.702 and DAAMAudioTransformer with an F1 macro score of 0.72 on the DAIC-WOZ dataset, without reliance on supplementary information such as vowel positions and speaker information during training/validation as in previous approaches. Both models' significant explainability and efficiency in leveraging speech signals for depression detection represent a leap towards more reliable, clinically useful diagnostic tools, promising advancements in speech and mental health care. To foster further research in this domain, we make our code publicly available.