JAIST Repository >
School of Information Science >
Articles >
Journal Articles >
Please use this identifier to cite or link to this item:
http://hdl.handle.net/10119/9181
|
Title: | Speech Enhancement based on Noise Eigenspace Projection |
Authors: | Ying, Dongwen Unoki, Masashi Lu, Xugang Dang, Jianwu |
Keywords: | speech enhancement noise eigenspace dimension reduction (DR) Karhunen-Loeve transform (KLT) |
Issue Date: | 2009-05-01 |
Publisher: | 電子情報通信学会 |
Magazine name: | IEICE Transactions on Information and Systems |
Volume: | E92-D |
Number: | 5 |
Start page: | 1137 |
End page: | 1145 |
DOI: | 10.1587/transinf.E92.D.1137 |
Abstract: | How to reduce noise with less speech distortion is a challenging issue for speech enhancement. We propose a novel approach for reducing noise with the cost of less speech distortion. A noise signal can generally be considered to consist of two components, a "white-like" component with a uniform energy distribution and a "color" component with a concentrated energy distribution in some frequency bands. An approach based on noise eigenspace projections is proposed to pack the color component into a subspace, named "noise subspace". This subspace is then removed from the eigenspace to reduce the color component. For the white-like component, a conventional enhancement algorithm is adopted as a complementary processor. We tested our algorithm on a speech enhancement task using speech data from the Texas Instruments and Massachusetts Institute of Technology (TIMIT) dataset and noise data from NOISEX-92. The experimental results show that the proposed algorithm efficiently reduces noise with little speech distortion. Objective and subjective evaluations confirmed that the proposed algorithm outperformed conventional enhancement algorithms. |
Rights: | Copyright (C)2009 IEICE. Dongwen Ying, Masashi Unoki, Xugang Lu, and Jianwu Dang, IEICE Transactions on Information and Systems, E92-D(5), 2009, 1137-1145. http://www.ieice.org/jpn/trans_online/ |
URI: | http://hdl.handle.net/10119/9181 |
Material Type: | publisher |
Appears in Collections: | b10-1. 雑誌掲載論文 (Journal Articles)
|
Files in This Item:
File |
Description |
Size | Format |
14617.pdf | | 384Kb | Adobe PDF | View/Open |
|
All items in DSpace are protected by copyright, with all rights reserved.
|