用语音谱图识别心理稳定性，结合数据增强与迁移学习提升效果
A Novel Transfer Learning Approach for Mental Stability Classification from Voice Signal
- 先在增广数据上预训练，再在原始数据上微调模型
- DenseNet121达到94%准确率和99%的AUC值
- 适合缺乏标注数据的心理健康研究者参考
本研究提出一种新的迁移学习方法和数据增强技术，用于基于人声信号的心理稳定性分类，解决了数据量有限的问题。采用卷积神经网络（CNN）分析从语音录制生成的频谱图图像。评估了三种CNN架构：VGG16、InceptionV3和DenseNet121，分别在三阶段实验中进行训练：非增广数据、增广数据和迁移学习。所提迁移学习方法包括在增广数据集上预训练模型，并在非增广数据集上微调，同时严格确保数据分离以防止数据泄露。结果表明，相比基线方法，分类性能显著提升。在三种架构中，DenseNet121使用该迁移学习方法取得了94%的准确率和99%的AUC得分。这一发现表明，结合数据增强与迁移学习可有效提升基于语音频谱图的CNN心理稳定性分类效果，为心理健康无创诊断提供了有前景的工具。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。