Audio declipping with social sparsity
Authors:
- 1 May 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 1577-1581
Abstract
We consider the audio declipping problem by using iterative thresholding algorithms and the principle of social sparsity. This recently introduced approach features thresholding/shrinkage operators which allow to model dependencies between neighboring coefficients in expansions with time-frequency dictionaries. A new unconstrained convex formulation of the audio declipping problem is introduced. The chosen structured thresholding operators are the so called windowed group-Lasso and the persistent empirical Wiener. The usage of these operators significantly improves the quality of the reconstruction, compared to simple soft-thresholding. The resulting algorithm is fast, simple to implement, and it outperforms the state of the art in terms of signal to noise ratio.Keywords
This publication has 25 references indexed in Scilit:
- Declipping of Audio Signals Using Perceptual Compressed SensingIEEE Transactions on Audio, Speech, and Language Processing, 2013
- Consistent iterative hard thresholding for signal declipping2013
- Social Sparsity! Neighborhood Systems Enrich Structured Shrinkage OperatorsIEEE Transactions on Signal Processing, 2013
- Mixed norms with overlapping groups as signal priors2011
- Convex Analysis and Monotone Operator Theory in Hilbert Spaces2011
- Group lasso with overlap and graph lasso2009
- Multiple indefinite kernel learning with mixed norm regularization2009
- A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse ProblemsSIAM Journal on Imaging Sciences, 2009
- Nested Iterative Algorithms for Convex Constrained Image Recovery ProblemsSIAM Journal on Imaging Sciences, 2009
- Model Selection and Estimation in Regression with Grouped VariablesJournal of the Royal Statistical Society Series B: Statistical Methodology, 2005