Presentation 2007-12-11
Impact Noise Suppression for Speech Signals by Using a Morphological Component Analysis with DFT
Hiroaki HAYASHI, Makoto NAKASHIZUKA, Youji IIGUNI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Morphological component analysis (MCA) is a signal separation method using sparse signal representations. For separation by the MCA, the set of bases are defined. Each source is assumed to be represented by one of the bases sparsely. In this paper, we propose an impact noise suppression by using the MCA. In our approach, the DFT bases and the set of shifted impluses are employed for representation of speeches and noises, respectively. To perform the separation, the sparsity measure is imposed on the distributions of DFT spectrum. In experiments, we demonstrate that noise reduction capability of the proposed method for various impact noises.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Noise Supression / Sparse Signal Separation / Impact Noises / DFT Bases / Speech Processing
Paper # SIS2007-66
Date of Issue

Conference Information
Committee SIS
Conference Date 2007/12/4(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Smart Info-Media Systems (SIS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Impact Noise Suppression for Speech Signals by Using a Morphological Component Analysis with DFT
Sub Title (in English)
Keyword(1) Noise Supression
Keyword(2) Sparse Signal Separation
Keyword(3) Impact Noises
Keyword(4) DFT Bases
Keyword(5) Speech Processing
1st Author's Name Hiroaki HAYASHI
1st Author's Affiliation Graduate School of Engineering Science, Osaka University()
2nd Author's Name Makoto NAKASHIZUKA
2nd Author's Affiliation Graduate School of Engineering Science, Osaka University
3rd Author's Name Youji IIGUNI
3rd Author's Affiliation Graduate School of Engineering Science, Osaka University
Date 2007-12-11
Paper # SIS2007-66
Volume (vol) vol.107
Number (no) 374
Page pp.pp.-
#Pages 6
Date of Issue