MEL FREQUENCY CEPSTRAL COEFFICIENTS (MFCC) BASED SPEAKER IDENTIFICATION IN NOISY ENVIRONMENT USING LBG VECTOR QUANTIZATION

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

 Basic Ideas of Making E-Mail Library Newsletters

 Newsletter is a regularly distributed publication that is generally something like one guideline subject of excitement to its endorsers. Email newsletter is the electronic configuration of traditional newsletter c...

PERFORMANCE ENHANCEMENT OF MOBILE AIR CONDITIONING SYSTEM USING VARIABLE GEOMETRY MICRO CHANNEL HEAT EXCHANGER (MCHX)

Due to stiff competition among the Original Equipment Manufacturer (OEM’s), the Comfort, Fuel efficiency & Safety are the key factors that drive the vehicle business; in that context A/c plays an important part for...

 IMPLEMENTATION OF VLSI ARCHITECTURE FOR RECONFIGURABLE RRC FIR FILTER USING GRAPH BASED METHOD

 The essential factors which contributes for designing the architecture of reconfigurable pulse shaping FIR filter are low complexity and power consumption. Although several low complexity architectures have been u...

 MECHANICAL PROPERTIES OF BAMBOO REINFORCED EPOXY COMPOSITES WITH DIFFERENT SIZES OF BAMBOO POWDER

 Uses of natural fibres as reinforcement have gained the importance in the recent years due to the eco-friendly nature. These natural fibres offer a number of advantages over traditional synthetic fibres. This pape...

 Analysis and Simulation of Asymmetrical Current Source Multilevel Inverter

 This paper presents asymmetrical current source multilevel inverter approach for high power output applications. The topology used here is derived from the multilevel voltage-source inverter (MVSI) by dual conver...

Download PDF file
  • EP ID EP148954
  • DOI 10.5281/zenodo.46499
  • Views 56
  • Downloads 0

How To Cite

Arun Kumar Choudhary, (0). MEL FREQUENCY CEPSTRAL COEFFICIENTS (MFCC) BASED SPEAKER IDENTIFICATION IN NOISY ENVIRONMENT USING LBG VECTOR QUANTIZATION. International Journal of Engineering Sciences & Research Technology, 5(2), 721-731. https://europub.co.uk/articles/-A-148954