Underdetermined blind source separation using sparse representations

By Pau Bofill, Michael Zibulevsky. Signal Processing, 2001

792 citations recorded by the source corpus.

Subfields: Computational Mechanics, Signal Processing

View Paper: https://www.semanticscholar.org/paper/f19de552bbb7a9f3e7af169390769b2406b50948

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Signal Processing

Citations in the corpus

Zero-Shot Learning with Generative Latent Prototype Model (2017, methodology): “First, we estimate w i by means of textual representation K , by the following function: where Ω is the regularizer of w i , common choice is (cid:96) 2 or (cid:96) 1 norm [27]–[29].”
Fourth-Order Cumulant-Based Blind Identification of Underdetermined Mixtures (2007, methodology): “In a preprocessing step a linear transform may be applied such that the new representation of the data is sparser (e.g., short-time Fourier transform in the case of audio signals) [ 5 ].”
Handbook of Blind Source Separation: Independent Component Analysis and Applications (2010, background): “Some ten years elapsed before these techniques began to be fully exploited for blind source separation [72, 106, 66, 70, 116, 61, 15, 111].”
Random projection-based multiplicative data perturbation for privacy preserving distributed data mining (2006, background): “Several other similar solutions to the separation of independent components from their overcomplete mixtures have been proposed for super-Gaussian sources [61]–[63].”
Underdetermined blind source separation based on sparse representation (2006, background): “A two-stage cluster-then- -optimization approach has been proposed for underdetermined BSS in which the mixing matrix and the sources are estimated separately [ 8 ].”
Blind Haze Separation (2006, methodology): “This prior of image statistics can be exploited for the entropy estimation needed in the optimization [1, 35].”
A Fast Approach for Overcomplete Sparse Decomposition Based on Smoothed $\ell ^{0}$ Norm (2008, methodology): “, not a totally blind situation), then the problem can be solved in two steps [1], [2]: £rst estimating the mixing matrix, and then estimating the sources assuming A being known.”
Analysis of Sparse Representation and Blind Source Separation (2004, methodology): “…only a single channel observation c t. m Furthermore, a two-step approach was proposed for underdetermined BSS in which the mixing matrix and the sources are estimated separately (Boﬁll & Zibulevsky, 2001). ne c o a r t i c Boﬁll and Zibulevsky (2001) performed the BSS in the transformed domain.”