A New Denoising Approach for Sound Signals Based on Non-negative Sparse Coding of Power Spectra

Authors:
Li Shang;Fengwen Cao;Jinfeng Zhang
Affiliations:
Department of Electronic Information Engineering, Suzhou Vocational University, Suzhou, China 215104;Department of Electronic Information Engineering, Suzhou Vocational University, Suzhou, China 215104;Department of Electronic Information Engineering, Suzhou Vocational University, Suzhou, China 215104
Venue:
ISNN '08 Proceedings of the 5th international symposium on Neural Networks: Advances in Neural Networks, Part II
Year:
2008

Citing 2
Cited 0

Sparse code shrinkage: denoising of nongaussian data by maximum likelihood estimation

Neural Computation
Sparse spectrotemporal coding of sounds

EURASIP Journal on Applied Signal Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a novel sound denoising approach based on a statistical model of the power spectrogram of a sound signal is proposed by using an extended non-negative sparse coding (NNSC) algorithm for power spectra. This approach is self-adaptive to the statistic property of spectrograms of sounds. The basic idea for denoising is to exploit a shrinkage function to reduce noises in spectrogram patches. Experimental results show that our approach is indeed effective and efficient in spectrogram denoising. Compared with other denoising methods, the simulation results show that the NNSC shrinkage technique is indeed effective and efficient.