Detecting Parkinson's disease with sustained phonation and speech signals using machine learning techniques
Detecting Parkinson's disease with sustained phonation and speech signals using machine learning techniques
复制标题
DOI：
10.1016/j.patrec.2019.04.005
复制
发表时间：
2019-07-01
影响因子：
5.1
通讯作者：
de Albuquerque, Victor Hugo C.
中科院分区：
文献类型：
--
作者：
Almeida, Jefferson S.;Reboucas Filho, Pedro R.;de Albuquerque, Victor Hugo C.
这项研究调查了用于检测帕金森病的语音信号的处理。这种疾病是世界上影响最严重的神经系统疾病之一。该方法评估了十八种特征提取技术和四种机器学习方法的使用，以对从持续发声和语音任务中获得的数据进行分类。发声涉及元音/a/ 发声任务，而语音涉及立陶宛语中短句的发音。音频任务是使用声学心形 (AC) 和智能手机 (SP) 的两个麦克风通道录制的，从而可以评估不同类型麦克风的性能。采用五个指标来分析分类性能：来自检测误差权衡 (DET) 的等错误率 (EER) 和曲线下面积 (AUC) 测量以及接收器操作特征曲线、准确性、特异性和灵敏度。我们将此方法与使用相同数据集的其他方法进行比较。我们证明，在疾病检测方面，发声任务比语音任务更有效。 AC 通道的最佳性能达到了 94.55% 的准确率、AUC 0.87 和 EER 19.01%。当使用SP通道时，我们取得了92.94%的准确率、AUC 0.92和EER 14.15%。 (C) 2019 Elsevier B.V. 保留所有权利。
This study investigates the processing of voice signals for detecting Parkinson's disease. This disease is one of the neurological disorders that affect people in the world most. The approach evaluates the use of eighteen feature extraction techniques and four machine learning methods to classify data obtained from sustained phonation and speech tasks. Phonation relates to the vowel /a/ voicing task and speech to the pronunciation of a short sentence in Lithuanian language. The audio tasks were recorded using two microphone channels from acoustic cardioid (AC) and a smartphone (SP), thus allowing to evaluate the performance for different types of microphones. Five metrics were employed to analyze the classification performance: Equal Error Rate (EER) and Area Under Curve (AUC) measures from Detection Error Tradeoff(DET) and Receiver Operating Characteristic curves, Accuracy, Specificity, and Sensitivity. We compare this approach with other approaches that use the same data set. We show that the task of phonation was more efficient than speech tasks in the detection of disease. The best performance for the AC channel achieved an accuracy of 94.55%, AUC 0.87, and EER 19.01%. When using the SP channel, we have achieved an accuracy of 92.94%, AUC 0.92, and EER 14.15%. (C) 2019 Elsevier B.V. All rights reserved.