Johns Hopkins University, Department of Electrical and Computer Engineering, Baltimore, 21218, USA.
Universidad Politécnica de Madrid, Escuela Técnica Superior de Ingeniería y Sistemas de Telecomunicación, Madrid, 28031, Spain.
Sci Rep. 2019 Dec 13;9(1):19066. doi: 10.1038/s41598-019-55271-y.
Literature documents the impact of Parkinson's Disease (PD) on speech but no study has analyzed in detail the importance of the distinct phonemic groups for the automatic identification of the disease. This study presents new approaches that are evaluated in three different corpora containing speakers suffering from PD with two main objectives: to investigate the influence of the different phonemic groups in the detection of PD and to propose more accurate detection schemes employing speech. The proposed methodology uses GMM-UBM classifiers combined with a technique introduced in this paper called phonemic grouping, that permits observation of the differences in accuracy depending on the manner of articulation. Cross-validation results reach accuracies between 85% and 94% with AUC ranging from 0.91 to 0.98, while cross-corpora trials yield accuracies between 75% and 82% with AUC between 0.84 and 0.95, depending on the corpus. This is the first work analyzing the generalization properties of the proposed approaches employing cross-corpora trials and reaching high accuracies. Among the different phonemic groups, results suggest that plosives, vowels and fricatives are the most relevant acoustic segments for the detection of PD with the proposed schemes. In addition, the use of text-dependent utterances leads to more consistent and accurate models.
文献记载了帕金森病（PD）对言语的影响，但尚无研究详细分析不同音素组对疾病自动识别的重要性。本研究提出了新的方法，并在三个包含 PD 患者的语料库中进行了评估，主要有两个目标：研究不同音素组在 PD 检测中的影响，并提出更准确的基于语音的检测方案。所提出的方法使用 GMM-UBM 分类器结合本文提出的一种称为音素分组的技术，该技术可以观察到不同发音方式的准确性差异。交叉验证结果的准确率在 85%到 94%之间，AUC 在 0.91 到 0.98 之间，而跨语料库试验的准确率在 75%到 82%之间，AUC 在 0.84 到 0.95 之间，具体取决于语料库。这是首次使用跨语料库试验分析所提出方法的泛化性质并达到高准确率的工作。在不同的音素组中，结果表明，爆破音、元音和摩擦音是使用所提出的方案检测 PD 时最相关的声学片段。此外，使用与文本相关的话语可以得到更一致和准确的模型。
