Speaker recognition using Vector Quantization by MFCC and KMCG clustering algorithm

Author

Kekre, H.B. ; Bharadi, V.A. ; Sawant, A.R. ; Kadam, Onkar ; Lanke, Pushkar ; Lodhiya, Rohit

Author_Institution

Comput. Eng. Dept., NMIMS Univ., Mumbai, India

fYear

2012

fDate

19-20 Oct. 2012

Firstpage

1

Lastpage

5

Abstract

Speaker identification system is one of the applications of biometric using voice signal. In this paper we have implemented a speaker recognition system using a combination of Mel Frequency Capestral Coefficients (MFCC) & Kekre´s Median Codebook Generation Algorithm (KMCG). The MFCC algorithm is used for feature extraction while the KMCG algorithm plays important role in code book generation and feature matching. For implementation simplicity the system is built as a text dependent system, i.e. common text used by all users. KMCG algorithm provides implementation simplicity along with high level of accuracy.

Keywords

biometrics (access control); feature extraction; pattern clustering; speaker recognition; text analysis; vector quantisation; KMCG clustering algorithm; Kekre´s median codebook generation clustering algorithm; MFCC clustering algorithm; Mel frequency capestral coefficients; biometrics; code book generation; feature extraction; feature matching; speaker identification system; speaker recognition system; text dependent system; vector quantization; voice signal; Accuracy; Cepstrum; Educational institutions; FCC; Fingerprint recognition; Mel frequency cepstral coefficient; Random access memory; Biometrics; Code Book; Code Vectors; Euclidean Distance; KMCG; Speaker Identification;

fLanguage

English

Publisher

ieee

Conference_Titel

Communication, Information & Computing Technology (ICCICT), 2012 International Conference on

Conference_Location

Mumbai

Print_ISBN

978-1-4577-2077-2

Type

conf

DOI

10.1109/ICCICT.2012.6398146

Filename

6398146