MEL FREQUENCY CEPSTRAL COEFFICIENTS (MFCC) BASED SPEAKER IDENTIFICATION IN NOISY ENVIRONMENT USING LBG VECTOR QUANTIZATION
Journal Title: International Journal of Engineering Sciences & Research Technology - Year 0, Vol 5, Issue 2
Abstract
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.
Authors and Affiliations
Arun Kumar Choudhary,
Keywords
Related Articles
- EP ID EP148954
- DOI 10.5281/zenodo.46499
- Views 64
- Downloads 0
FPGA BASED CONTROLLER FOR FUEL CELL
This thesis primarily focuses on reduction and the complexity of a fuel cell controller and research carried out in the modeling of a renewable energy sources like fuel cell. A fuel cell, one of the recently identified...
A Study and Future of 3D Internet
The Internet is a living, dynamic “wizard” who is constantly and rapidly evolving, reshaping and transforming and consequently .The world wide web which has started as a document bank is rapidly transforming to f...
DATA MINING: A TECHNIQUE WITH WIDENING APPLICATIONS AND HAVING SOME ISSUES
Data mining, the extraction of hidden predictive information from large databases, invented as a powerful new technology with great potential to help companies and organizations to focus on the most important info...
MHD Flow Past a Parabolic Started Isothermal Vertical Plate with Variable Mass Diffusion in the Presence of Chemical Reaction of First Order
Laplace transform solution of MHD flow past a parabolic starting motion of the infinite isothermal vertical plate with variable mass diffusion, in the presence of homogeneous chemical reaction of first order has b...
PROPOSED ARCHITECTURAL MODEL FOR ATM SERVICES ON CLOUDS
Today, one of the biggest problems that gripped the banking sphere, the high cost of implementing advanced technologies and the efficient use of the hardware. Cloud computing is the use of shared services on the In...