Humans’ voice offers the widest variety of motor phenomena of any human activity. However, its clinical evaluation in people with movement disorders such as Parkinson’s disease (PD) lags behind current knowledge on advanced analytical automatic speech processing methodology. Here, we use deep learning-based speech processing to differentially analyze voice recordings in 14 people with PD before and after dopaminergic medication, using personalized Convolutional Recurrent Neural Networks (p-CRNN) and Phone Attribute Codebooks (PAC). p-CRNN yields an accuracy of 82.35% in the binary classification of ON and OFF motor states at a sensitivity/specificity of 0.86/0.78. The PAC-based approach’s accuracy was slightly lower with 73.08% at a sensitivity/specificity of 0.69/0.77, but this method offers easier interpretation and understanding of the computational biomarkers. Both p-CRNN and PAC provide a differentiated view and novel insights into the distinctive components of the speech of persons with PD. Both methods detect voice qualities that are amenable to dopaminergic treatment, including active phonetic and prosodic features. Our findings may pave the way for quantitative measurements of speech in persons with PD.

中文翻译：

---

语音分析可区分帕金森氏病患者的多巴胺能反应

人类的声音可以提供任何人类活动中最广泛的运动现象。但是，其对运动障碍患者（如帕金森氏病（PD））的临床评估落后于当前对先进分析自动语音处理方法的了解。在这里，我们使用基于深度学习的语音处理，通过个性化卷积神经网络（p-CRNN）和电话属性密码本（PAC），对多巴胺能药物治疗前后14位PD患者的语音记录进行差异分析。p-CRNN在ON和OFF电机状态的二进制分类中的准确度/特异性为0.86 / 0.78时，准确度为82.35％。基于PAC的方法的灵敏度/特异性为0.69 / 0.77时，其准确性稍低，为73.08％，但是这种方法可以更轻松地解释和理解计算生物标志物。p-CRNN和PAC都为PD患者言语的独特成分提供了不同的观点和新颖的见解。两种方法都可以检测出适合多巴胺能治疗的声音质量，包括主动的语音和韵律特征。我们的发现可能为定量测量PD患者的语音铺平了道路。