Text dependent speaker recognition using shifted MFCC

Author

Mukherjee, Rohan ; Islam, Tarikul ; Sankar, Ravi

Author_Institution

Dept. of Electr. Eng., Univ. of South Florida, Tampa, FL, USA

fYear

2013

fDate

4-7 April 2013

Firstpage

1

Lastpage

4

Abstract

In the past decade, interest in using biometric technologies for person authentication in security systems has grown rapidly. Voice is one of the most promising and mature biometric modalities for secured access control. In this paper, we present a novel approach to recognize/identify speakers by including a new set of features and using Gaussian mixture models (GMMs). In this research, the concept of shifted MFCC is introduced so as to incorporate accent information in the recognition algorithm. The algorithm was evaluated using TIDIGIT dataset and the results showed improvements over the performance of our previous work [1].

Keywords

Gaussian processes; speaker recognition; speech synthesis; GMM; Gaussian mixture models; Mel-frequency cepstral coefficients; TIDIGIT dataset; biometric modalities; biometric technology; person authentication; secured access control; security systems; shifted MFCC; text dependent speaker recognition algorithm; Mathematical model; Mel frequency cepstral coefficient; Security; Speaker recognition; Speech; Speech recognition; Gaussian Mixture Model (GMM); MFCC (Mel Frequency Cepstral Components); Speaker Recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Southeastcon, 2013 Proceedings of IEEE

Conference_Location

Jacksonville, FL

ISSN

1091-0050

Print_ISBN

978-1-4799-0052-7

Type

conf

DOI

10.1109/SECON.2013.6567398

Filename

6567398