Continuous wavelet transform based source separation

Author

Belley, Lee-Pierre ; Gabrea, Marcel ; Gargour, Christian

Author_Institution

Ecole de Technol. Super., Montreal

fYear

2007

fDate

5-8 Aug. 2007

Firstpage

365

Lastpage

368

Abstract

Separation of convolutive mixtures of speech sources is considered in this paper. Several approaches have been reported in the literature using statistical methods as well as transforms such as the short time Fourier transform (STFT) and the Paquet wavelet transform (PWT). In this paper we propose a new source separation method based on the independent component analysis (ICA) and utilizing the continuous wavelet transform (CWT). The experimental results obtained by our method have been investigated and compared with those generated by other approaches.

Keywords

Fourier transforms; independent component analysis; speech processing; wavelet transforms; Paquet wavelet transform; continuous wavelet transform; independent component analysis; short time Fourier transform; source separation; speech source convolutive mixtures; statistical methods; Continuous wavelet transforms; Finite impulse response filter; Fourier transforms; Frequency; Independent component analysis; Iterative algorithms; Source separation; Speech; Statistical analysis; Wavelet transforms;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 2007. MWSCAS 2007. 50th Midwest Symposium on

Conference_Location

Montreal, Que.

ISSN

1548-3746

Print_ISBN

978-1-4244-1175-7

Electronic_ISBN

1548-3746

Type

conf

DOI

10.1109/MWSCAS.2007.4488607

Filename

4488607