TECHNOLOGY MEL FREQUENCY CEPSTRAL COEFFICIENTS (MFCC) BASED SPEAKER IDENTIFICATION IN NOISY ENVIRONMENT USING LBG VECTOR QUANTIZATION
Arun Choudhary, Jitendra K. Mishra · 2016
Recognizing A speaker can simplify task of translating speech in systems that have been trained on specific person's voices or it can be used to the authenticate or verify the identity of a speaker as part of a security process. This work discusses Implementation of an Enhanced Speaker Recognition system using MFCC and the LBG Algorithm. The MFCC has been used the extensively for purposes of Speaker Recognition. This work has augmented the existing work by using Vector Quantization and Classification using a Linde Buzo Gray Algorithm. A complete test system has been developed using MATLAB which it can be used for real time testing as it can take the inputs directly from the Microphone. Therefore, the design can be translated into the Hardware having the necessary real time processing Prerequisites. The system has been tested using VID TIMIT Database and using the Performance metrics of False Acceptance Rate(FAR), True Acceptance Rate(TAR) and False Rejection Rate(FRR). A system has been found to perform better than the existing systems under moderately noisy conditions.