一种基于语音信号的抑郁症智能诊断方法  

A intelligent diagnosis method of depression based on audio signal

作　　者：辛逸男 张莉[1] 吴鹏飞 刘欣阳 刘志宽 XIN Yinan;ZHANG Li;WU Pengfei;LIU Xinyang;LIU Zhikuan(School of Biomedical Engineering,South-Central Minzu University,Wuhan 430074)

机构地区：[1]中南民族大学生物医学工程学院,武汉430074

出　　处：《北京生物医学工程》2023年第1期38-44,共7页Beijing Biomedical Engineering

基　　金：国家自然基金(81601586);中央高校基本科研业务费专项资金(CZZ21007)资助。

摘　　要：目的提出一种基于语音特征的机器学习诊断新方法,以实现抑郁症的临床智能诊断。方法选择抑郁症患者与正常人群的语音信号作为信号源,语音信号特征采取短期特征与长期特征相结合的方法,将短期特征离散化后,分别通过独立组合和共同出现的方法生成组合特征,并结合随机森林算法和极度梯度提升算法进行分类与评估。结果组合特征作为分类特征相较于短期特征、长期特征以及深度学习的方法在F1分数上绝对提高21%、14%、14%,非抑郁类的敏感度上绝对提高36%、29%、7%。结论特征组合方法能够根据语音片段对抑郁程度进行很好的分类。Objective To propose a new method of machine learning diagnosis based on audio signal and to realize clinical intelligent diagnosis of depression.Methods We selects the audio signals of depressed patients and normal people as signal source,the audio signal feature adopts the method of combining short⁃term features and long⁃term features.After discretizing the short⁃term features,new long⁃term features are generated through independent combination and co⁃occurrence methods,and the random forest algorithm and extreme gradient boosting algorithm are combined for classification and evaluation.Results Compared with short⁃term features,long⁃term features and deep learning approaches,the combined features as classification features have absolute increases in F1 scores of 21%,14%,and 14%,and absolute increases in non⁃depression sensitivity of 36%,29%,and 7%.Conclusions The combined features as classification features was able to classify depression levels based on audio signal.

关 键 词：抑郁症智能诊断 短期特征 特征组合 长期特征 随机森林算法 

分 类 号：R318.04[医药卫生—生物医学工程]