Speaker Identification using Mel-frequency Cepstrum Coefficient

Lalit G. Patil

Abstract


Now a days, Speaker identification is most popular technology and there is a much little research on it for practical application. When a human speaks any word, it contains certain frequency and amplitude. Speaker identification is the technology in which developed algorithm recognizes a word spoken by user, and it deals with identification of a person. Its applications are device control like laptop, door opening, Voice based dialing, and other security purpose also. This technology deals with signal processing. Different features are extracted from spoken words and this is the most important stage with which a programmer have to deal.

Keywords


Speaker identification, Signal Processing, DCT, FFT, MFCC

Full Text:

PDF




Copyright (c) 2014 Lalit G. Patil

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

 

All published Articles are Open Access at  https://journals.pen2print.org/index.php/ijr/ 


Paper submission: ijr@pen2print.org