| Pathological Voice Classification Based on Features Dimension Opti mization |
| |
| 作者姓名： | 彭策 徐秋晶 万柏坤 陈文西 |
| |
| 作者单位： | School of Precision Instrument and Opto-Electronics Engineering Tianjin University，School of Precision Instrument and Opto-Electronics Engineering，Tianjin University，School of Precision Instrument and Opto-Electronics Engineering，Tianjin University，Graduate Department of Information Systems，University of Aizu，Tianjin 300072，China，Tianjin 300072，China，Tianjin 300072，China，Aizu-Wakamatsu 965-8580，Japan |
| |
| 摘 要： | The classification of pathological voice from healthy voice was studied based upon 27 acoustic features derived from a single sound signal of vowel /a:/. First, the feature space was transferred to reduce the data dimension by principle component analysis (PCA). Then the voice samples were classified according to the reduced PCA parameters by support vector machine (SVM) using radial basis function (RBF) as a kernel function. Meanwhile, by changing the ratio of opposite class samples, the accuracy under different features combinations was tested. Experimental data were provided by the voice database of Massachusetts Eye and Ear Infirmary (MEEI) in which 216 vowel /a:/ samples were collected from subjects of healthy and pathological cases, and tested with 5 fold cross-validation method. The result shows the positive rate of pathological voices was improved from 92% to 98% through the PCA method. STD, Fatr, Tasm, NHR, SEG, and PER are pathology sensitive features in illness detection. Using these sensitive features the accuracy of detection of pathological voice from healthy voice can reach 97%.
|
| 关 键 词： | 支持向量机 病理敏感特征 声音 病变 |
Pathological Voice Classification Based on Features Dimension Optimization |
| |
| PENG Ce,XU Qiujing,WAN Baikun,CHEN Wenxi.Pathological Voice Classification Based on Features Dimension Opti mization[J].Transactions of Tianjin University,2007,13(6):456-461. |
| |
| Authors: | PENG Ce XU Qiujing WAN Baikun CHEN Wenxi |
| |
| Institution: | 1. School of Precision Instrument and Opto-Electronics Engineering, Tianjin University, Tianjin 300072, China
2. Graduate Department of Information Systems, University of Aizu, Aizu-Wakamatsu 965-8580, Japan |
| |
| Abstract: | The classification of pathological voice from healthy voice was studied based upon 27 acoustic features derived from a single sound signal of vowel /a:/. First, the feature space was transferred to reduce the data dimension by principle component analysis (PCA). Then the voice samples were classified according to the reduced PCA parameters by support vector machine (SVM) using radial basis function (RBF) as a kernel function. Meanwhile, by changing the ratio of opposite class samples, the accuracy under different features combinations was tested. Experimental data were provided by the voice database of Massachusetts Eye and Ear Infirmary (MEEI) in which 216 vowel /a:/ samples were collected from subjects of healthy and pathological cases, and tested with 5 fold cross-validation method. The result shows the positive rate of pathological voices was improved from 92% to 98% through the PCA method. STD, Fatr, Tasm, NHR, SEG, and PER are pathology sensitive features in illness detection. Using these sensitive features the accuracy of detection of pathological voice from healthy voice can reach 97%. |
| |
| Keywords: | pathological voice classification support vector machine radial basis function principle component analysis pathology sensitive features |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
