Speaker Recognition Using MFCC Front End Analysis and VQ Modeling Technique for Hindi Words using MATLAB

Automatic Speaker Recognition technology has recently been implemented in large number of commercial areas successfully. Speaker recognition is being used in voice based biometrics; voice controlled appliances, security control for confidential information, remote access to computers and many more interesting areas. This paper introduces text dependent systems that have been trained for a particular user. All speaker recognition systems contain two main modules: feature extraction and feature matching. Here, we have used MFCC technique for feature extraction and Vector Quantization model for feature vectors modeling. There are mainly two important tasks to be performed in speaker recognition process: one is training phase and other is testing phase. During the training phase, the input speech features are extracted and the corresponding feature vectors are modeled using modeling techniques. These feature vectors are stored as reference templates. They are then compared with the entered speech signals during the testing phase and thus how helps in identification of voice. [13] General Terms This Document contain following keywords: Automatic speaker recognition MFCC: Mel-Frequency Cepstrum Coefficients VQ: Vector Quantization Feature Extraction Feature Recognition

[1]  Oliver Chiu-sing Choy,et al.  An efficient MFCC extraction method in speech recognition , 2006, 2006 IEEE International Symposium on Circuits and Systems.

[2]  Jonathan Allen,et al.  Speech recognition and synthesis , 2003 .

[3]  I. Mahmood,et al.  Speech Recognition using Dynamic Time Warping , 2008, 2008 2nd International Conference on Advances in Space Technologies.

[4]  M.S. Haleem.  Voice controlled automation system , 2008, 2008 IEEE International Multitopic Conference.

[5]  O.O. Khalifa,et al.  Human computer interaction using isolated-words speech recognition technology , 2007, 2007 International Conference on Intelligent and Advanced Systems.

[6]  Lie Lu,et al.  Improve audio representation by using feature structure patterns , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[7]  Robert M. Gray,et al.  An Algorithm for Vector Quantizer Design , 1980, IEEE Trans. Commun..

[8]  Douglas Beeks.  Speech Recognition and Synthesis , 2000 .

[9]  Finn Dag Buø,et al.  JANUS 93: towards spontaneous speech translation , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

[10]  Aslam Muhammad,et al.  A Speaker Identification System Using MFCC Features with VQ Technique , 2009, 2009 Third International Symposium on Intelligent Information Technology Application.

[11]  M Hossan,et al.  Automatic speaker recognition dynamic feature identification and classification using distributed discrete cosine transform based mel frequency cepstral coefficients and fuzzy vector quantization , 2011 .

[12]  M.S. Awan,et al.  Recognizing spoken Urdu numbers using fourier descriptor and neural networks with Matlab , 2008, 2008 Second International Conference on Electrical Engineering.