Speaker verification using Gaussian Mixture Model

Author

Jagtap, Shilpa S. ; Bhalke, D.G.

Author_Institution

Dept. of Electron. & Telecommun. Eng., Savitribai Phule Pune Univ., Pune, India

fYear

2015

fDate

8-10 Jan. 2015

Firstpage

1

Lastpage

5

Abstract

In this paper, speaker verification system using Gaussian Mixture Model (GMM) is proposed. The proposed system consists of pre-processing, feature extraction, modelling and classification stage. The pre-processing is used to remove silent part of signal to reduce computational complexity. Pitch frequency and Mel Frequency Cepstral Coefficients(MFCC)are used as a feature vector for speaker verification system. Modelling is done using different combination of Gaussian mixture models. Simple distance measures are used for the classification between reference and the test signal.

Keywords

Gaussian processes; cepstral analysis; computational complexity; mixture models; speaker recognition; vectors; GMM; Gaussian mixture model; MFCC; Mel frequency cepstral coefficients; classification stage; computational complexity reduction; distance measures; feature extraction; feature vector; modelling; pitch frequency; preprocessing; reference signal; speaker verification; test signal; Accuracy; Feature extraction; Gaussian mixture model; Mel frequency cepstral coefficient; Speech; System performance; EER; GMM; MFCC; feature extraction; pitch;

fLanguage

English

Publisher

ieee

Conference_Titel

Pervasive Computing (ICPC), 2015 International Conference on

Conference_Location

Pune

Type

conf

DOI

10.1109/PERVASIVE.2015.7087080

Filename

7087080