Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Journal of Guangxi Normal University(Natural Science Edition)》 2018-04
Add to Favorite Get Latest Update

Identification of Pathological Voice of Different Levels Based on Random Forest

XU Yuanjing;HU Weiping;College of Electronic Engineering,Guangxi Normal University;  
In order to identify the different degrees of pathological voice recognition,a method based on random forest recognition is proposed in this paper.The normal,moderate,and severe pathological voices are identified separately and compared with the recognition results of GMM.The experimental results show that compared with GMM,random forest method has higher classification accuracy,robustness,and better recognition results.The highest recognition rates of normal,moderate,and severe voices are 98.04%,86.84%,and 83.33%,respectively.It provides a reference for further research on the classification of pathological voice.
【Fund】: 国家自然科学基金(61362003);; 广西多源信息挖掘与安全重点实验室基金(13-A-03-02);; 广西壮族自治区高等学校科学研究项目(KY2015YB034)
【CateGory Index】: TN912.34;TP18
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved