A novel approach for MFCC feature extraction

Author

Hossan, Md Afzal ; Memon, Sheeraz ; Gregory, Mark A.

Author_Institution

Sch. Electr. & Comput. Eng., RMIT Univ., Melbourne, VIC, Australia

fYear

2010

fDate

13-15 Dec. 2010

Firstpage

1

Lastpage

5

Abstract

The Mel-Frequency Cepstral Coefficients (MFCC) feature extraction method is a leading approach for speech feature extraction and current research aims to identify performance enhancements. One of the recent MFCC implementations is the Delta-Delta MFCC, which improves speaker verification. In this paper, a new MFCC feature extraction method based on distributed Discrete Cosine Transform (DCT-II) is presented. Speaker verification tests are proposed based on three different feature extraction methods including: conventional MFCC, Delta-Delta MFCC and distributed DCT-II based Delta-Delta MFCC with a Gaussian Mixture Model (GMM) classifier.

Keywords

cepstral analysis; discrete cosine transforms; feature extraction; speaker recognition; Gaussian mixture model classifier; delta-delta MFCC; distributed discrete cosine transform; mel-frequency cepstral coefficient feature extraction method; speaker verification; speech feature extraction; Discrete cosine transforms; Feature extraction; Filter bank; Mel frequency cepstral coefficient; Speaker recognition; Speech; Delta MFCC (DMFCC); Delta-Delta MFCC (DDMFCC); Discrete Cosine Transform (DCT-II); Gaussian Mixture Model (GMM); Mel Frequency Cepstral Coefficients (MFCC); Speech Feature Extraction;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing and Communication Systems (ICSPCS), 2010 4th International Conference on

Conference_Location

Gold Coast, QLD

Print_ISBN

978-1-4244-7908-5

Electronic_ISBN

978-1-4244-7906-1

Type

conf

DOI

10.1109/ICSPCS.2010.5709752

Filename

5709752