Sciweavers

Share
ICASSP
2009
IEEE

Robust speech dereverberation based on non-negativity and sparse nature of speech spectrograms

10 years 4 months ago
Robust speech dereverberation based on non-negativity and sparse nature of speech spectrograms
This paper presents a blind dereverberation method designed to recover the subband envelope of an original speech signal from its reverberant version. The problem is formulated as a blind deconvolution problem with non-negative constraints, regularized by the sparse nature of speech spectrograms. We derive an iterative algorithm for its optimization, which can be seen as a special case of the non-negative matrix factor deconvolution. We confirmed through experiments that the algorithm is fast and robust to speaker movement.
Hirokazu Kameoka, Tomohiro Nakatani, Takuya Yoshio
Added 21 May 2010
Updated 21 May 2010
Type Conference
Year 2009
Where ICASSP
Authors Hirokazu Kameoka, Tomohiro Nakatani, Takuya Yoshioka
Comments (0)
books