A Novel Transfer Learning Approach for Mental Stability Classification from Voice Signal

TL;DR

This paper introduces a transfer learning and data augmentation method for classifying mental stability from voice signals, significantly improving accuracy and AUC scores using CNNs, especially DenseNet121, as a non-invasive mental health diagnostic tool.

Contribution

It proposes a novel transfer learning approach combined with data augmentation for voice-based mental stability classification, demonstrating substantial performance improvements.

Findings

DenseNet121 achieved 94% accuracy and 99% AUC.

Transfer learning outperformed baseline models.

Data augmentation enhanced model performance.

Abstract

This study presents a novel transfer learning approach and data augmentation technique for mental stability classification using human voice signals and addresses the challenges associated with limited data availability. Convolutional neural networks (CNNs) have been employed to analyse spectrogram images generated from voice recordings. Three CNN architectures, VGG16, InceptionV3, and DenseNet121, were evaluated across three experimental phases: training on non-augmented data, augmented data, and transfer learning. This proposed transfer learning approach involves pre-training models on the augmented dataset and fine-tuning them on the non-augmented dataset while ensuring strict data separation to prevent data leakage. The results demonstrate significant improvements in classification performance compared to the baseline approach. Among three CNN architectures, DenseNet121 achieved the highest accuracy of 94% and an AUC score of 99% using the proposed transfer learning approach. This finding highlights the effectiveness of combining data augmentation and transfer learning to enhance CNN-based classification of mental stability using voice spectrograms, offering a promising non-invasive tool for mental health diagnostics.