5Rudasi L, Zahorian SA. Text-independent talker identification with neural networks [C].ICAS SP91,1991:389-392.
6Do CT,Pastor D,Goalic A.On the recognition of cochlearimplant-like spectrally reduced speech with MFCC andHMM-based ASR.IEEE Trans.on Audio,Speech,andLanguage Processing,2010,18(5):1065-1068.
7Zhen B,Wu X,Liu Z.On the importance of components ofthe MFCC in speech and speaker recognition.ActaScicentiarum Naturalum Universitis Pekinesis,2001,37(3):371-378.
8Ferras M,Leung CC,Barras C,et al.Comparison of speakeradaptation methods as feature extraction for SVM-basedspeaker recognition.IEEE Trans.on Audio,Speech,andLanguage Processing,2010,18(6):1366-1378.
9Manikandan J,Venkataramani B.Design of a modified one-against-all SVM classifier.Proc.of the 2009 IEEEInternational Conference on Systems,Man,and Cybernetics.San Autonio,2009:1869-1874.