Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Computer Engineering and Applications》 2011-25
Add to Favorite Get Latest Update

Natural sounds recognition using GMM distribution

YU Qingqing,LI Ying,LI Yong College of Mathematics and Computer Science,Fuzhou University,Fuzhou 350108,China  
A recognition method for natural sounds based on Gaussian Mixture Model(GMM) distribution is proposed.Mel-Frequency Cepstral Coefficients(MFCCs) are used to analyze natural sounds for their feature extraction.The expectation maximization algorithm is used to learn a Gaussian mixture model distribution of MFCCs for the set of audio feature vectors that describe each sound.Minimum classification error criterion and vote rule are used to yield higher recognition accuracy for natural sounds.Experimentally,compared with K-Nearest Neighbo(rKNN)method,GMM is able to achieve a higher accuracy rate for discriminating 36 classes of natural sounds.The classified accuracy rate of GMM reaches to 95.83%.
【Fund】: 国家自然科学基金(No.61075022);; 福建省教育厅A类科技项目(No.JA09021)~~
【CateGory Index】: TN912.34
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