Enhanced Machine Learning Framework for Autonomous Depression Detection Using Modwave Cepstral Fusion and Stochastic Embedding

Depression is a prevalent mental illness that requires autonomous detection systems due to its complexity. Existing machine learning techniques face challenges such as background noise sensitivity, slow adaptation speed, and imbalanced data. To address these limitations, this study proposes a novel ModWave Cepstral Fusion and Stochastic Embedding Framework for depression prediction. Then, the Gain Modulated Wavelet Technique removes background noise and normalises audio signals. Difficulties with generalisation, which results in a lack of interpretability, hinder extracting relevant characteristics from speech. To address these issues, an Auto Cepstral Fusion extracts relevant features from speech, capturing temporal and spectral characteristics caused by background voice. Feature selection becomes imperative when choosing relevant features for classification. Selecting irrelevant features can result in overfitting, the curse of dimensionality, and less robustness to noise. Hence, the Principal Stochastic Embedding technique handles high-dimensional data, minimising noise influence and dimensionality. Furthermore, the XGBoost classifier differentiates between depressed and non-depressed individuals. As a result, the proposed method uses the DAIC-WOZ dataset from USC for detecting depressions, achieving an accuracy of 97.02%, precision of 97.02%, recall of 97.02%, F1-score of 97.02%, RMSE of 2.00, and MAE of 0.9, making it a promising tool for autonomous depression detection.