arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.03510cs.SDcs.AIeess.AS
收藏

基于语音的临床抑郁症筛查:一项实证研究

Speech-based Clinical Depression Screening: An Empirical Study

Suzhou Fubian Medical Technology Co., Ltd(苏州阜边医疗科技有限公司);Peking University Sixth Hospital(北京大学第六医院);The First Clinical College of Xinxiang Medical University(新乡医学院第一临床学院)

Yangbin Chen, Chenyang Xu, Chunfeng Liang, Yanbao Tao, Chuan Shi

AI总结:

该研究通过精神科访谈、聊天机器人对话和文本朗读场景,提取声学与深度语音特征并采用神经网络或SVM分类,验证了语音用于临床抑郁症筛查的有效性。

摘要:

本研究考察了在多种交互场景中利用语音信号进行基于AI的抑郁症筛查的效用,这些场景包括精神科访谈、聊天机器人对话和文本朗读。参与者包括从北京大学第六医院门诊部招募的抑郁症患者,以及来自社区的对照组成员;所有人员均由精神科医生按照标准化诊断方案进行诊断。我们从每位参与者的分段录音中提取了声学特征和深度语音特征。分类使用神经网络或SVM进行,并通过汇总各语音片段的结果来确定最终评估。我们围绕交互场景、语音处理技术和特征类型开展的分析证实,语音是抑郁症筛查的重要标志物。具体而言,人机交互的效果与临床访谈相当,并优于朗读任务。语音片段的时长和数量会显著影响模型性能,且深度语音特征显著优于传统声学特征。

英文摘要:

This study investigates the utility of speech signals for AI-based depression screening across varied interaction scenarios, including psychiatric interviews, chatbot conversations, and text readings. Participants include depressed patients recruited from the outpatient clinics of Peking University Sixth Hospital and control group members from the community, all diagnosed by psychiatrists following standardized diagnostic protocols. We extracted acoustic and deep speech features from each participant's segmented recordings. Classifications were made using neural networks or SVMs, with aggregated clip outcomes determining final assessments. Our analysis across interaction scenarios, speech processing techniques, and feature types confirms speech as a crucial marker for depression screening. Specifically, human-computer interaction matches clinical interview efficacy, surpassing reading tasks. Segment duration and quantity significantly affect model performance, with deep speech features substantially outperforming traditional acoustic features.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑