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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Klein, D.J., Peter, K., Körding, K.P.: Sparse Spectrotemporal Coding of Sounds. EURASIP Journal on Applied Signal Processing 7, 659–667 (2003)
Hanuch, L.A., Yariv, E.: Extension of the Signal Subspace Speech Enhancement Approach to Colored Noise. IEEE Signal Processing Letters 10, 104–106 (2003)
Mahmoudi, D., Drygajlo, A.: Combined Wiener and Coherence Filtering Array Speech Enhancement. In: International Conference on Acoustics, Speech, and Signal Processing (ICASSP 1998), pp. 385–388. Seattle Press, Washington (1998)
Wan, E., Vander, M.R.: Noise-regularized Adaptive Filtering for Speech Enhancement. In: 6th European Conference on Speech Communication and Technology (EUROSPEECH 1999), pp. 156–163. Budapest Press, Hungary (1999)
Hyvärinen, A.: Sparse Coding Shrinkage: Denoising of Nongaussian Data by Maximum Likelihood Estimation. Neural Computation 11, 1739–1768 (1997)
Gazor, S., Zhang, W.: Speech Enhancement Employing Laplacian-Gaussian Mixture. IEEE Transactions on Speech Audio processing 13(5), 896–904 (2005)
Hanssen, Ø.T.A.: The Normal Inverse Gaussian Distributions as A Flexible Model for Heavy Tailed Processes. In: Proc. IEEE-EURASIP Workshop on Nonlinear Signal and Image Processing. Baltimore Press, Maryland (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Shang, L., Cao, F., Zhang, J. (2008). A New Denoising Approach for Sound Signals Based on Non-negative Sparse Coding of Power Spectra. In: Sun, F., Zhang, J., Tan, Y., Cao, J., Yu, W. (eds) Advances in Neural Networks - ISNN 2008. ISNN 2008. Lecture Notes in Computer Science, vol 5264. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-87734-9_41
Download citation
DOI: https://doi.org/10.1007/978-3-540-87734-9_41
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-87733-2
Online ISBN: 978-3-540-87734-9
eBook Packages: Computer ScienceComputer Science (R0)