郑州大学学报（理学版）2026，Vol.58Issue(3)：10-16,7.DOI:10.13705/j.issn.1671-6841.2024180
基于深度抑郁特征编码网络的语音抑郁检测
Speech Depression Detection Based on Deep Depression Feature Encoding Network
摘要
Abstract
Aiming at the problem of feature redundancy in the speech depression dataset,a speech de-pression detection method based on the deep depression feature encoding network(D-DFENet)was pro-posed.Firstly,the Wav2vec2.0 pre-training model was utilized to extract the latent representations of speech.Secondly,a convolutional variational autoencoder module was designed.By introducing the vari-ational autoencoder mechanism,the dimensionality reduction of the feature space was achieved,and con-volutional neural networks were embedded layer by layer in the multi-layer structure of its encoder,to ef-fectively filter out the redundant or interference information unrelated to the depressive state in the latent representations of speech.Finally,the performance of the model was evaluated on the DAIC-WOZ data-set.The experimental results showed that when the feature dimension of D-DFENet was reduced to 128,the detection accuracy reached 90%,which was superior to the existing methods in classification accuracy.关键词
抑郁症检测/语音特征/预训练模型/降维/自编码器Key words
depression detection/speech feature/pre-trained model/dimensionality reduction/autoencoder分类
信息技术与安全科学引用本文复制引用
李奇,姬生文,赵迪,武岩,奚洋,孟天宇..基于深度抑郁特征编码网络的语音抑郁检测[J].郑州大学学报（理学版）,2026,58(3):10-16,7.基金项目
吉林省自然科学基金面上项目(20240101344JC) （20240101344JC）
吉林省科技发展计划国际科技合作项目(20200801035GH) （20200801035GH）
