MFCC and its Application in Speaker Identification

A. Rajendra More, R. V. Babar, M. S. Gaikwad

Abstract


Various fields for research in speech processing arespeech recognition, speaker recognition, speech synthesis, speechcoding etc. The objective of automatic speaker identification is toextract, characterize and recognize the information aboutspeakeridentity. The biometric information in general and one's voice inparticular are of such means; therefore a text-independent speakeridentification system was built for this concern. Thispaperis itsimplementation using LabVIEW on National InstrumentsCompactRIO, a control and acquisition system powered byreconfigurable I/O field-programmable gate array (FPGA)technology. The Mel-Frequency Cepstral Coefficients (MFCC)technique is used for feature extraction from the voice, VectorQuantization (VQ) technique for feature modeling, and theminimum distance classifier for the feature matching. Thus thissystem identifies the user in runtime with high accuracy.

Full Text:

PDF

References


Vibha Tiwari

MFCC and its applicat

ions in speaker recognition”

Deptt

of

Electronics Engg., Gyan Ganga Institute of Technology and Management,

Bhopal, (MP) INDIA

(Received 5 Nov., 2009, Accepted 10 Feb., 2010)

.

speaker identification using MFCC coefficients”

-

Mohd Rasheedur Hassan,

Mu

stafa Zamil, Mohd Bolam Khabsani, Mohd Saifur Rehman.

r d

i n t e r n a t i o n a l

c o n f e r e n c e o n e l e c t r i c a l a n d c o m p u t e r

e n g i n e e r i n g

(ICECE), (2004).

“Text independent speaker recognition using L

BG Vector Quantization”

Danko Kolen,

Tomi

slav Lombarovi, Mario O

grizek.

University of Zagreb

,Faculty of Electrical Electrical Engineering and Computing ,Unska 3, 100

Zagreb ,Republic of Croatia.

MIPRO 2011 May 23

-

,2011,

Opatija,Croatia.

“An overview of text

-

independent speaker recognition: From features to

s

uper vectors” Tomi Kinnunen, Haizhou Li Department of Computer Science

and Statistics, Speech and Image Process

ing Unit, University of Joensuu.

Voice

Command Recognit

ion System Based on MFCC and VQ

Algorithms”

Mahdi Shaneb,and Azizollah Taheri ,Wo

rd academy of Science, Engineering

& Technology 2009.




 

Copyright © IJETT, International Journal on Emerging Trends in Technology