Speech Enhancement Based on Noise Eigenspace Projection

Dongwen YING
Masashi UNOKI
Xugang LU
Jianwu DANG

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E92-D    No.5    pp.1137-1145
Publication Date: 2009/05/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.E92.D.1137
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Speech and Hearing
Keyword: 
speech enhancement,  noise eigenspace,  dimension reduction (DR),  Karhunen-Loeve transform (KLT),  

Full Text: PDF(385.7KB)>>
Buy this Article



Summary: 
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.


open access publishing via