Paper Title
Recognition Of Speaker Using Vector Quantization By Kekre’s Fast Codebook Generation Algorithm

Abstract
Abstract— Speaker Recognition has been developed for wide range of applications. Still there are certain limitations. Vector Quantization (VQ) has been very popular in fields of Speaker Recognition. We will try to identify the person who is speaking by characteristics of his/her voice by using classical quantization technique from signal processing, VQ. We will use VQ for feature extraction in both the training and testing phases. For speaker identification, the codebook is generated using Kekre's Fast Codebook Generation (KFCG) algorithm. KFCG algorithm is simple and faster as only comparisons is required. The codebook of test sample is generated using similar method and compared with the codebooks of the reference samples stored in the database. Thus using KFCG algorithm, we will be able to recognize the person who is speaking.