Speaker Recognition Using MFCC Front End Analysis and VQ Modeling Technique for Hindi Words using MATLAB
Nitisha, Ashu Bansal · International Journal of Computer Applications · 2012
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