Catching the Specific Fusion Features for a Speaker Based on Contourlets

Author

Jinfang, Wang ; Jinbao, Wang

Author_Institution

Commun. Eng. Coll., Jilin Univ., Changchun

fYear

2006

fDate

25-28 June 2006

Firstpage

2393

Lastpage

2398

Abstract

This paper presents the fusion features resulting from contourlet transform on the geometry structure in the time-frequency representation for the one-dimensional speech. In the experiments, after extracting the separate features including main diagonal of the inner lowpass subband (MDL), main anti-diagonal of the inner lowpass subband (MADL), main diagonal of bandpass subband (MDB) and ordinal binary tree difference of main diagonal of bandpass subband(BTDB), the combination features such as MDL-MDB, MDL-MADL-MDB and MDL-MADL-BTDB achieve the remarkable performance with the recognition veracity up to 86.88% enough to match the classical MFCC parameters though the high dimension of the fusion features is still a disadvantage

Keywords

geometry; speaker recognition; time-frequency analysis; bandpass subband; contourlet transform; geometry structure; inner lowpass subband; one-dimensional speech; specific fusion features; time-frequency representation; Automation; Cepstral analysis; Feature extraction; Geometry; Mechatronics; Mel frequency cepstral coefficient; Pattern recognition; Speaker recognition; Speech; Time frequency analysis; Speaker recognition; contourlets; fusion feature;

fLanguage

English

Publisher

ieee

Conference_Titel

Mechatronics and Automation, Proceedings of the 2006 IEEE International Conference on

Conference_Location

Luoyang, Henan

Print_ISBN

1-4244-0465-7

Electronic_ISBN

1-4244-0466-5

Type

conf

DOI

10.1109/ICMA.2006.257707

Filename

4026474