High Impact Factor : 4.396 icon | Submit Manuscript Online icon |

Feature Extraction and Classification Techniques in Speaker Recognition

Author(s):

Neelam Nehra , Maharaja Surajmal Institute of Technology; Pardeep Sangwan, Maharaja Surajmal Institute of Technology; Divya Kumar, IFTM University, Moradabad, Uttar-Pradesh

Keywords:

Speaker recognition, MFCC, GMM, VQ

Abstract

Speech is one of the natural form to express emotion. Every person has different voice production organ like vocal tract shape, vocal fold, larynx size etc. Moreover to these differences every speaker has unique accent, fundamental frequency, rhythm, choice of vocabulary, speaking style etc. Speaker recognition is the process of verifying/identifying the speaker based on their speech sample. Feature extraction and matching algorithm are the two main process of speaker recognition .In this paper feature extraction technique Mel Frequency Cepstrum Coefficients (MFCC), Linear Predictive Coefficients (LPC) and classifiers Vector Quantization(VQ), Gaussian Mixture Model (GMM) and Hidden Markov Model (HMM) are explained.

Other Details

Paper ID: IJSRDV7I100211
Published in: Volume : 7, Issue : 10
Publication Date: 01/01/2020
Page(s): 383-384

Article Preview

Download Article