TY  - JOUR
T1  - Speaker Identification Using MFCC-Domain Support Vector Machine
AU - , S.M. Kamruzzaman AU - , A.N.M. Rezaul Karim AU - , Saiful Islam AU - , Emdadul Haque 
JO  - International Journal of Electrical and Power Engineering
VL  - 1
IS  - 3
SP  - 274
EP  - 278
PY  - 2007
DA  - 2001/08/19
SN  - 1990-7958
DO  - ijepe.2007.274.278
UR  - https://makhillpublications.co/view-article.php?doi=ijepe.2007.274.278
KW  - Speech recognition
KW  -speaker identification
KW  -MFCC
KW  -support vector machine
KW  -neural networks
KW  -chunking
KW  -osuna
KW  -discrete cosine transform
AB  - Speech recognition and speaker identification are important for authentication and verification in security purpose, but they are difficult to achieve. Speaker identification methods can be divided into text-independent and text-dependent. This study presents a technique of text-dependent speaker identification using MFCC-domain Support Vector Machine (SVM). In this research, Mel-Frequency Cepstrum Coefficients (MFCCs) and their statistical distribution properties are used as features, which will be inputs to the neural network. This research firstly used Sequential Minimum Optimization (SMO) learning technique for SVM that improve performance over traditional techniques Chunking, Osuna. The cepstrum coefficients representing the speaker characteristics of a speech segment are computed by nonlinear filter bank analysis and discrete cosine transform. The speaker identification ability and convergence speed of the SVMs are investigated for different combinations of features. Extensive experimental results on several samples show the effectiveness of the proposed approach.
ER  -