Handbook of blind source separation: independent component analysis and applications
HAL (Le Centre pour la Communication Scientifique Directe)Published 1 January 2010
Pierre Comon, Christian Jutten
Citations1,503
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
This handbook provides the definitive reference on Blind Source Separation, giving a broad and comprehensive description of all the core principles and methods, numerical algorithms and major applications in the fields of telecommunications, biomedical engineering and audio, acoustic and speech processing.
Abstract
ISBN = 978-0-12-374726-6 http://www.elsevier.com/wps/find/bookdescription.cws_home/717222/description
Keywords
ChemistryComputer Science
Elsevier eBooksA Wavelet Tour of Signal Processing
16,401 Citations1999Stéphane Mallat
An introduction to a Transient World and an Approximation Tour of Wavelet Packet and Local Cosine Bases.
IEEE Transactions on Signal Processing$rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation
9,506 Citations2006Michal Aharon, Michael Elad +1 more
A novel algorithm for adapting dictionaries in order to achieve sparse signal representations, the K-SVD algorithm, an iterative method that alternates between sparse coding of the examples based on the current dictionary and a process of updating the dictionary atoms to better fit the data.
The Annals of StatisticsLeast angle regression
9,493 Citations2004Bradley Efron, Trevor Hastie +2 more
IEEE Transactions on Signal ProcessingMatching pursuits with time-frequency dictionaries
9,115 Citations1993Stéphane Mallat, Zhifeng Zhang
The authors introduce an algorithm, called matching pursuit, that decomposes any signal into a linear expansion of waveforms that are selected from a redundant dictionary of functions, chosen in order to best match the signal structures.
SIAM Journal on Scientific ComputingAtomic Decomposition by Basis Pursuit
6,899 Citations1998Scott Shaobing Chen, David L. Donoho +1 more
Basis Pursuit (BP) is a principle for decomposing a signal into an "optimal" superposition of dictionary elements, where optimal means having the smallest l1 norm of coefficients among all such decompositions.
IEEE Transactions on Neural NetworksSurvey of Clustering Algorithms
6,154 Citations2005Rui Xu, D. WunschII
Clustering algorithms for data sets appearing in statistics, computer science, and machine learning are surveyed, and their applications in some benchmark data sets, the traveling salesman problem, and bioinformatics, a new field attracting intensive efforts are illustrated.
NatureEmergence of simple-cell receptive field properties by learning a sparse code for natural images
5,840 Citations1996Bruno A. Olshausen, David J. Field
It is shown that a learning algorithm that attempts to find sparse linear codes for natural scenes will develop a complete family of localized, oriented, bandpass receptive fields, similar to those found in the primary visual cortex.
Communications on Pure and Applied MathematicsAn iterative thresholding algorithm for linear inverse problems with a sparsity constraint
4,957 Citations2004Ingrid Daubechies, Michel Defrise +1 more
It is proved that replacing the usual quadratic regularizing penalties by weighted 𝓁p‐penalized penalties on the coefficients of such expansions, with 1 ≤ p ≤ 2, still regularizes the problem.
Vision ResearchSparse coding with an overcomplete basis set: A strategy employed by V1?
3,720 Citations1997Bruno A. Olshausen, David J. Field
These deviations from linearity provide a potential explanation for the weak forms of non-linearity observed in the response properties of cortical simple cells, and they further make predictions about the expected interactions among units in response to naturalistic stimuli.
IEEE Transactions on Information TheoryGreed is Good: Algorithmic Results for Sparse Approximation
3,648 Citations2004Joel A. Tropp
This article presents new results on using a greedy algorithm, orthogonal matching pursuit (OMP), to solve the sparse approximation problem over redundant dictionaries and develops a sufficient condition under which OMP can identify atoms from an optimal approximation of a nonsparse signal.
SIAM Journal on ComputingSparse Approximate Solutions to Linear Systems
2,822 Citations1995B. K. Natarajan
It is shown that the problem is NP-hard, but that the well-known greedy heuristic is good in that it computes a solution with at most at most $\left\lceil 18 \mbox{ Opt} ({\bf \epsilon}/2) \|{\bf A}^+\|^2_2 \ln(\|b\|_2/{\bf
Practical Optimization
2,718 Citations2007
Pattern RecognitionDigital processing of speech signals
2,647 Citations1980
This paper presents a meta-modelling framework for digital Speech Processing for Man-Machine Communication by Voice that automates the very labor-intensive and therefore time-heavy and expensive process of encoding and decoding speech.
IEEE Transactions on Image ProcessingThe curvelet transform for image denoising
2,216 Citations2002Jean‐Luc Starck, Emmanuel J. Candès +1 more
IEEE Transactions on Information TheoryStable recovery of sparse overcomplete representations in the presence of noise
2,209 Citations2005David L. Donoho, Michael Elad +1 more
This paper establishes the possibility of stable recovery under a combination of sufficient sparsity and favorable structure of the overcomplete system and shows that similar stability is also available using the basis and the matching pursuit algorithms.
IEEE Transactions on Information TheoryUncertainty principles and ideal atomic decomposition
1,967 Citations2001David L. Donoho, Xiaoming Huo
It is proved that if S is representable as a highly sparse superposition of atoms from this time-frequency dictionary, then there is only one such highly sparse representation of S, and it can be obtained by solving the convex optimization problem of minimizing the l/sup 1/ norm of the coefficients among all decompositions.
A New Learning Algorithm for Blind Signal Separation
1,888 Citations1995Шун-ичи Амари, Andrzej Cichocki +1 more
A new on-line learning algorithm which minimizes a statistical dependency among outputs is derived for blind separation of mixed signals and has an equivariant property and is easily implemented on a neural network like model.
Proceedings of the IEEEBlind signal separation: statistical principles
1,852 Citations1998J.-F. Cardoso
The objectives of this paper are to review some of the approaches that have been developed to address blind signal separation and independent component analysis, to illustrate how they stem from basic principles, and to show how they relate to each other.
IEEE Transactions on Signal ProcessingSparse signal reconstruction from limited data using FOCUSS: a re-weighted minimum norm algorithm
1,810 Citations1997I.F. Gorodnitsky, Bhaskar D. Rao
A view of the algorithm as a novel optimization method which combines desirable characteristics of both classical optimization and learning-based algorithms is provided and Mathematical results on conditions for uniqueness of sparse solutions are also given.
IEEE Transactions on Signal ProcessingBlind Separation of Speech Mixtures via Time-Frequency Masking
1,458 Citations2004Özgür Yılmaz, Scott Rickard
The results demonstrate that there exist ideal binary time-frequency masks that can separate several speech signals from one mixture and show that the W-disjoint orthogonality of speech can be approximate in the case where two anechoic mixtures are provided.
IEEE Transactions on Information TheoryJust relax: convex programming methods for identifying sparse signals in noise
1,427 Citations2006Joel A. Tropp
A method called convex relaxation, which attempts to recover the ideal sparse signal by solving a convex program, which can be completed in polynomial time with standard scientific software.
IEEE Transactions on Signal ProcessingSparse solutions to linear inverse problems with multiple measurement vectors
1,400 Citations2005Shane F. Cotter, Bhaskar D. Rao +2 more
This work considers in depth the extension of two classes of algorithms-Matching Pursuit and FOCal Underdetermined System Solver-to the multiple measurement case so that they may be used in applications such as neuromagnetic imaging, where multiple measurement vectors are available, and solutions with a common sparsity structure must be computed.
Signal ProcessingAlgorithms for simultaneous sparse approximation. Part I: Greedy pursuit
1,347 Citations2005Joel A. Tropp, Anna C. Gilbert +1 more
This paper proposes a greedy pursuit algorithm, called simultaneous orthogonal matching pursuit (S-OMP), for simultaneous sparse approximation, and presents some numerical experiments that demonstrate how a sparse model for the input signals can be identified more reliably given several input signals.
IEEE Transactions on Signal ProcessingEquivariant adaptive source separation
1,346 Citations1996J.-F. Cardoso, B.H. Laheld
A class of adaptive algorithms for source separation that implements an adaptive version of equivariant estimation and is henceforth called EASI, which yields algorithms with a simple structure for both real and complex mixtures.
Neural ComputationHigh-Order Contrasts for Independent Component Analysis
1,221 Citations1999J.-F. Cardoso
This article considers high-order measures of independence for the independent component analysis problem and discusses the class of Jacobi algorithms for their optimization and compares the proposed approaches with gradient-based techniques from the algorithmic point of view and also on a set of biomedical data.
IEEE Transactions on Image ProcessingAn EM algorithm for wavelet-based image restoration
1,204 Citations2003Mário A. T. Figueiredo, R.D. Nowak
An expectation-maximization (EM) algorithm for image restoration (deconvolution) based on a penalized likelihood formulated in the wavelet domain is introduced, and it is shown that under mild conditions the algorithm converges to a globally optimal restoration.
Neural ComputationLearning Overcomplete Representations
1,142 Citations2000Michael S. Lewicki, Terrence J. Sejnowski
It is shown that overcomplete bases can yield a better approximation of the underlying statistical distribution of the data and can thus lead to greater coding efficiency and provide a method for Bayesian reconstruction of signals in the presence of noise and for blind source separation when there are more sources than mixtures.
Constructive ApproximationAdaptive greedy approximations
1,141 Citations1997Geoffrey M. Davis, Stéphane Mallat +1 more
A notion of the coherence of a signal with respect to a dictionary is derived from the characterization of the approximation errors of a pursuit from their statistical properties, which can be obtained from the invariant measure of the pursuit.
Neural ComputationBlind Source Separation by Sparse Decomposition in a Signal Dictionary
754 Citations2001Michael Zibulevsky, Barak A. Pearlmutter
Signal ProcessingUnderdetermined blind source separation using sparse representations
710 Citations2001Pau Bofill, Michael Zibulevsky
This work estimates both the number of sources and the mixing matrix by the maxima of a potential function along the circle of unit length, and obtains the minimal l1 norm representation of each data point by a linear combination of the pair of basis vectors that enclose it.
Signal ProcessingAlgorithms for simultaneous sparse approximation. Part II: Convex relaxation
707 Citations2005Joel A. Tropp
This paper presents theoretical and numerical results for a greedy pursuit algorithm, called simultaneous orthogonal matching pursuit, and develops conditions under which convex relaxation computes good solutions to simultaneous sparse approximation problems.
Nature NeuroscienceEfficient coding of natural sounds
692 Citations2002Michael S. Lewicki
It is reported that several basic auditory nerve fiber tuning properties can be accounted for by adapting a population of filter shapes to encode natural sounds efficiently.
IEEE Transactions on Signal ProcessingBlind separation of mixture of independent sources through a quasi-maximum likelihood approach
464 Citations1997Dinh Tuan Pham, Philippe Garat
Two methods for separating mixture of independent sources without any precise knowledge of their probability distribution are proposed by considering a maximum likelihood (ML) solution corresponding to some given distributions of the sources and relaxing this assumption afterward.
Communications of the ACMCoSaMP
424 Citations2010Deanna Needell, Joel A. Tropp
This extended abstract describes a recent algorithm, called, CoSaMP, that accomplishes the data recovery task and was the first known method to offer near-optimal guarantees on resource usage.
IEEE Signal Processing LettersBlind source separation of more sources than mixtures using overcomplete representations
404 Citations1999Te-Won Lee, Michael S. Lewicki +2 more
It is demonstrated that three speech signals can be separated with good fidelity given only two mixtures of the three signals.
Blind separation of disjoint orthogonal signals: demixing N sources from 2 mixtures
402 Citations2002Alexander Jourjine, Scott Rickard +1 more
A novel method for blind separation of any number of sources using only two mixtures when sources are (W-)disjoint orthogonal, that is, when the supports of the (windowed) Fourier transform of any two signals in the mixture are disjoint sets.
ALGORITHMS FOR SIMULTANEOUS SPARSE APPROXIMATION
359 Citations2006Joel A. Tropp
Journal of the Optical Society of America AProbabilistic framework for the adaptation and comparison of image codes
312 Citations1999Michael S. Lewicki, Bruno A. Olshausen
The learned bases are shown to have better coding efficiency than traditional Fourier and wavelet bases and to provide a Bayesian solution to the problems of image denoising and filling in of missing pixels.
IEEE Transactions on Image ProcessingMorphological Component Analysis: An Adaptive Thresholding Strategy
310 Citations2007J. Bobin, Jean‐Luc Starck +3 more
This paper shows how the MCA convergence can be drastically improved using the mutual incoherence of the dictionaries associated to the different components.
IEEE Transactions on Information TheoryWhy Simple Shrinkage Is Still Relevant for Redundant Representations?
284 Citations2006Michael Elad
This work develops a simple iterative procedure for the BPDN minimization that amounts to stepwise shrinkage, and demonstrates how the simple shrinkage emerges as the first iteration of this novel algorithm.
Signal ProcessingA time–frequency blind signal separation method applicable to underdetermined mixtures of dependent sources
277 Citations2005Frédéric Abrard, Yannick Deville
A new blind source separation (BSS) method called Time-Frequency Ratio Of Mixtures (TIFROM) which uses time-frequency information to cancel source signal contributions from a set of linear instantaneous mixtures of these sources.
Homotopy continuation for sparse signal representation
271 Citations2006Dmitry Malioutov, Müjdat Çetin +1 more
This work describes a homotopy continuation-based algorithm to find and trace efficiently all solutions of basis pursuit as a function of the regularization parameter, and shows the effectiveness of this algorithm in accurately and efficiently generating entire solution paths for basis pursuit.
Mathematical ProgrammingModified barrier functions (theory and methods)
254 Citations1992Roman A. Polyak
The excellent MBF properties allow us to discover that for any nondegenerate constrained optimization problem, there exists a “hot” start, from which the NMBM has a better rate of convergence, a better complexity bound, and is more stable than the interior point methods, which are based on the classical barrier functions.
Journal of Fourier Analysis and ApplicationsAtoms of All Channels, Unite! Average Case Analysis of Multi-Channel Sparse Recovery Using Greedy Algorithms
236 Citations2008Rémi Gribonval, Holger Rauhut +2 more
This paper provides new results on computing simultaneous sparse approximations of multichannel signals over redundant dictionaries using two greedy algorithms, p-thresholding and p-SOMP, and shows that, if the dictionary satisfies a uniform uncertainty principle, the probability that simultaneous OMP fails to recover any sufficiently sparse set of atoms gets increasingly smaller as the number of channels increases.
SIAM Journal on Numerical AnalysisRecovery Algorithms for Vector-Valued Data with Joint Sparsity Constraints
223 Citations2008Massimo Fornasier, Holger Rauhut
This work shows how to compute solutions of linear inverse problems with such joint sparsity regularization constraints by fast thresholded Landweber algorithms by discussing the adaptive choice of suitable weights appearing in the definition of sparsity measures.
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE<title>Blind source separation by sparse decomposition</title>
203 Citations2000Michael Zibulevsky, Barak A. Pearlmutter
This work exploits the property of the sources to have a sparse representation in a corresponding signal dictionary, which provides faster and more robust computations, when there are an equal number of sources and mixtures.
SIAM Journal on OptimizationPenalty/Barrier Multiplier Methods for Convex Programming Problems
201 Citations1997Aharon Ben‐Tal, Michael Zibulevsky
A new type of penalty/barrier function (having a logarithmic branch glued to a quadratic branch) is introduced and used to construct an efficient algorithm that is tested on large-scale quadratically constrained problems arising in structural optimization.
Applied and Computational Harmonic AnalysisCoordinate and subspace optimization methods for linear least squares with non-quadratic regularization
198 Citations2007Michael Elad, Boaz Matalon +1 more
This work provides herein a convergence analysis of the PCD algorithm, and also introduces a form of the regularization function, which permits analytical solution to the coordinate optimization, and merge them into a recently developed sequential subspace optimization technique (SESOP), with almost no additional complexity.
Linear Algebra and its ApplicationsOn the uniqueness of overcomplete dictionaries, and a practical way to retrieve them
194 Citations2005Michal Aharon, Michael Elad +1 more
The uniqueness of the dictionary A is established, depending on the quantity and nature of the set { b i }, and the sparsity of { x i }, and a recently developed algorithm is described that practically find the matrix A, in a manner similar to the K-Means algorithm.
Electronics LettersRobust learning algorithmfor blind separation of signals
194 Citations1994Andrzej Cichocki, R. Unbehauen +1 more
A novel, efficient, self-normalising, unsupervised adaptive learning algorithm for the on-line (real-time) separation of statistically independent unknown source signals from a linear mixture of them.
Applied and Computational Harmonic AnalysisHighly sparse representations from dictionaries are unique and independent of the sparseness measure
188 Citations2006Rémi Gribonval, Morten Nielsen
A large class of admissible sparseness measures is introduced, and sufficient conditions are given for having a unique sparse representation of a signal from the dictionary w.r.t. such aSparseness measure.
IEEE Transactions on Information TheoryOn the exponential convergence of matching pursuits in quasi-incoherent dictionaries
163 Citations2005Rémi Gribonval, Pierre Vandergheynst
The main contribution is a detailed analysis of the approximation and stability properties of MP with quasi-incoherent dictionaries, and a bound on the number of steps sufficient to reach an error no larger than a penalization factor times the best m-term approximation error.
IEEE Transactions on Audio Speech and Language ProcessingA Bayesian Approach for Blind Separation of Sparse Sources
154 Citations2006Cédric Févotte, Simon Godsill
The results show the improved sound quality obtained with the Student t prior and the better robustness to mixing matrices close to singularity of the Markov chain Monte Carlo approach.
Maximum Likelihood Blind Source Separation: A Context-Sensitive Generalization of ICA
144 Citations1996Barak A. Pearlmutter, Lucas C. Parra
The resulting algorithm is called cICA, after the (Bell and Sejnowski 1995) Infomax algorithm, which is able to separate in a number of situations where standard methods cannot, including sources with low kurtosis, colored Gaussian sources, and sources which have Gaussian histograms.
Mptk: Matching Pursuit Made Tractable
142 Citations2006Sacha Krstulović, Rémi Gribonval
A new architecture is proposed which exploits the structure shared by many redundant MP dictionaries, and thus decreases its complexity to O(N log N), which makes it possible, from now on, to explore and apply MP in the framework of real-life, high-dimensional data processing problems.
IEEE Transactions on Image ProcessingLow-rate and flexible image coding with redundant representations
119 Citations2006Rosa Ventura, Pierre Vandergheynst +1 more
The work proposed in this paper provides an adaptive way of representing images as a sum of two-dimensional features by presenting a low bit-rate image coding method based on a matching pursuit (MP) expansion, over a dictionary built on anisotropic refinement and rotation of contour-like atoms.
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIEMorphological component analysis
106 Citations2005Jean‐Luc Starck, Y. Moudden +3 more
MCA is extended to a multichannel MCA (MMCA) for analyzing multispectral data and a range of examples which illustrates the results are presented.
PROPOSALS FOR PERFORMANCE MEASUREMENT IN SOURCE SEPARATION
100 Citations2003Rémi Gribonval, Emmanuel Vincent +3 more
When the sources are estimated from a degenerate set of mixtures by applying a demixing matrix, it is proved that there are upper bounds on the achievable Source to Interference Ratio.
IEEE Transactions on Image ProcessingBlind deconvolution of images using optimal sparse representations
98 Citations2005Michael M. Bronstein, Alex Bronstein +2 more
A method of sparsification is proposed, which allows blind deconvolution of arbitrary sources, and how to find optimal sparsifying transformations by supervised learning is shown.
Signal ProcessingHybrid representations for audiophonic signal encoding
92 Citations2002Laurent Daudet, Bruno Torrésani
A new approach for signal models in the context of audio signal encoding based upon hybrid models featuring simultaneously transient, tonal and stochastic components in the signal is discussed.
IEEE Signal Processing LettersTwo Contributions to Blind Source Separation Using Time–Frequency Distributions
89 Citations2004Cédric Févotte, C. Doncarli
It is shown that Belouchrani and Amin's technique can be interpreted as a practical implementation of the general equations provided in the stochastic case, and a new criterion aimed at selecting more efficiently the time-frequency locations where the spatial matrices should be joint-diagonalized is introduced, introducing single autoterms selection.
Blind Source Separation via Multinode Sparse Representation
84 Citations2001Michael Zibulevsky, Pavel Kisilev +2 more
The property of multiscale transforms, such as wavelet or wavelet packets, is used to decompose signals into sets of local features with various degrees of sparsity, for selecting the best (most sparse) subsets of features for further separation.
Neural ComputationFaithful Representation of Separable Distributions
82 Citations1997Juan K. Lin, David G. Grier +1 more
By modifying the Kohonen self-organized feature maps, this work arrives at neural networks with local interactions that optimize coding while simultaneously performing source separation, which results in networks with nonlinear ICA capabilities.
Neural ComputationLinear Geometric ICA: Fundamentals and Algorithms
69 Citations2003Fabian J. Theis, Andreas Jung +2 more
A new approach to linear geometric ICA based on histograms observing a considerable improvement in separation quality of different distributions and a sizable reduction in computational cost, by a factor of 100, compared to the ordinary geometric approach.
IEEE International Conference on Acoustics Speech and Signal ProcessingSparse decomposition of stereo signals with Matching Pursuit and application to blind separation of more than two sources from a stereo mixture
63 Citations2002Rémi Gribonval
A method of sparse decomposition of stereo audio signals is developed, and its application to blind separation of more than two sources from only two linear mixtures is tested.
Advances in Computational MathematicsSimultaneous approximation by greedy algorithms
62 Citations2006D. Leviatan, Vladimir Temlyakov
Approximation of m-term approximation with regard to a redundant dictionary in a Hilbert space H is studied and convergence and rate of convergence of such expansions which are called simultaneous expansions.
Lecture notes in computer scienceComplex Nonconvex l p Norm Minimization for Underdetermined Source Separation
61 Citations2007Emmanuel Vincent
This article extends source separation methods by assuming that these coefficients follow a generalized Gaussian prior with shape parameter p to derive an efficient global optimization algorithm for complex nonconvex lp norm optimization problem.
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIEImage decomposition: separation of texture from piecewise smooth content
53 Citations2003Jean‐Luc Starck, Mikael Elad +1 more
A novel method for separating images into texture and piecewise smooth parts based on a combination of the Basis Pursuit Denoising (BPDN) algorithm and the Total-Variation (TV) regularization scheme is presented.
Mechanical Systems and Signal ProcessingTime–frequency ratio-based blind separation methods for attenuated and time-delayed sources
52 Citations2005Matthieu Puigt, Yannick Deville
Two types of time–frequency (TF) blind source separation (BSS) methods suited to attenuated and delayed (AD) mixtures, especially suited to non-stationary sources are proposed and derive their performance from many tests performed with AD mixtures of speech signals.
Blind separation of dependent sources using the "time-frequency ratio of mixtures" approach
46 Citations2003Frédéric Abrard, Yannick Deville
The principles of the TIFROM approach are recalled and it is shown that, unlike independent component analysis methods, this approach can separate dependent signals, provided there exist some areas in the time-frequency plane where only one source occurs.
UNDERDETERMINED BLIND SOURCE SEPARATION USING A PROBABILISTIC SOURCE SPARSITY MODEL
46 Citations2001Luis Vielva, Deniz Erdoğmuş +1 more
This communication presents a method that choose the “best” demixing matrix in a sample by sample basis by using some previous knowledge of the statistics of the sources to estimate the sources.
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIEPiecewise linear source separation
46 Citations2003Rémi Gribonval
A new framework, called piecewise linear separation, for blind source separation of possibly degenerate mixtures, including the extreme case of a single mixture of several sources is proposed.
Signal ProcessingA simple test to check the optimality of a sparse signal approximation
44 Citations2005Rémi Gribonval, Rosa Ventura +1 more
This paper provides a simple test to check whether the output of a sparse approximation algorithm is nearly optimal, in the sense that no significantly different linear expansion from the dictionary can provide both a smaller approximation error and a better sparsity.
BLIND SOURCE SEPARATION WITH RELATIVE NEWTON METHOD
44 Citations2003Michael Zibulevsky
A relative optimization framework for the quasimaximum likelihood blind source separation and relative Newton method as its particular instance and demonstrates the efficiency of the presented approach on example of sparse sources.
Lecture notes in computer scienceOn the Strong Uniqueness of Highly Sparse Representations from Redundant Dictionaries
43 Citations2004Rémi Gribonval, Morten Nielsen
The results should have a practical impact on source separation methods based on sparse decompositions, since they indicate that a large class of sparse priors can be efficiently replaced with a Laplacian prior without changing the resulting solution.
Signal ProcessingImage compression using an edge adapted redundant dictionary and wavelets
42 Citations2005Lorenzo Peotta, L. Granai +1 more
This paper proposes an approach based on building a sparse representation of the edge part of images in a redundant geometrically inspired library of functions, followed by suitable coding techniques.
Statistical properties of STFT ratios for two channel systems and applications to blind source separation
39 Citations2000Radu Bălan
This paper analyzes and extends a source separation method based on the use of STFT ratios of two sensor inputs, called DUET, and proves that considerably weaker assumptions about the classes of input signals are required to apply the derived techniques.
Clustering approach to square and non-square blind source separation
38 Citations2003Marc M. Van Hulle
A new heuristic is introduced that relies on the tendency of the mixture samples to cluster around the source directions in mixture space to solve BSS problems with not only square but also non-square mixing matrices.
Lecture notes in computer scienceA Robust Method to Count and Locate Audio Sources in a Stereophonic Linear Instantaneous Mixture
34 Citations2006Simon Arberet, Rémi Gribonval +1 more
A new clustering algorithm called DEMIX is proposed to estimate the number of sources and the mixing matrix in a linear instantaneous mixture, even with more sources than sensors, based on a multiscale Short Time Fourier Transform.
University of Regensburg Publication Server (University of Regensburg)Formalization of the Two-Step Approach to Overcomplete BSS
29 Citations2002Fabian J. Theis, Elmar W. Lang
It is proved that the shortest-path algorithm as proposed by Bofill and Zibulevsky indeed solves the maximum-likelihood conditions in the BSR step.
Lecture notes in computer scienceUnder-Determined Source Separation: Comparison of Two Approaches Based on Sparse Decompositions
23 Citations2006Sylvain Lesage, Sacha Krstulović +1 more
This paper focuses on under-determined source separation when the mixing parameters are known by introducing a new class of multi-channel dictionaries, where the atoms are given by a spatial direction and a waveform.
IEEE Transactions on Circuits and Systems for Video TechnologyFlexible motion-adaptive video coding with redundant expansions
20 Citations2006A. Rahmoune, Pierre Vandergheynst +1 more
The MP3D scheme is shown to provide rate-distortion performance that are comparable with state-of-the-art schemes, such as H.264, MPEG-4, at low and medium bit rate, but the use of a redundant dictionary is penalizing at high coding rate, which makes the algorithm mostly interesting for low rate applications, or as a flexible base layer in hierarchical coding schemes.
IEEE Transactions on Signal ProcessingRelative optimization for blind deconvolution
19 Citations2005Alex Bronstein, Michael M. Bronstein +1 more
A relative optimization framework for quasi-maximum likelihood (QML) blind deconvolution and the relative Newton method as its particular instance, with special Hessian structure allowing fast Newton system construction and solution, resulting in a fast-convergent algorithm with iteration complexity comparable to that of gradient methods.
University of Regensburg Publication Server (University of Regensburg)A HISTOGRAM-BASED OVERCOMPLETE ICA ALGORITHM
18 Citations2003Fabian J. Theis, Carlos G. Puntonet +1 more
A new approach based on an estimated histogram of the sensor data is presented, which searches for the points fulfilling the overcomplete Geometric Convergence Condition, which has been shown to be a limit condition of overcomplete geometric BSS.
A Simple Test to Check the Optimality of Sparse Signal Approximations
15 Citations2006Rémi Gribonval, Rosa Ventura +1 more
This paper provides a simple test to check whether the output of a sparse approximation algorithm is nearly optimal, in the sense that no significantly different linear expansion from the dictionary can provide both a smaller approximation error and a better sparsity.
Signal ProcessingBlind source separation using block-coordinate relative Newton method
9 Citations2004Alexander M. Bronstein, Michael M. Bronstein +1 more
A block-coordinate version of the relative Newton method, recently proposed for quasi-maximum likelihood blind source separation, that converges in near constant number of iterations (order of 10) independently of the problem size.
Warwick Research Archive Portal (University of Warwick)The Multiresolution Fourier Transform and its application to Polyphonic Audio Analysis
8 Citations1995E. R.S. Pearson
The area of music perception has attracted some attention over the last few decades and there is an increasing interest in the subject largely arising from the availability of suitably powerful technology.
HAL (Le Centre pour la Communication Scientifique Directe)Underdetermined blind source separation of audio sources in time-frequency domain
7 Citations2005Abdeldjalil Aïssa El Bey, Karim Abed-Meraim +1 more
HAL (Le Centre pour la Communication Scientifique Directe)Estimation de fonctions géométriques et déconvolution
4 Citations2005Charles Dossal
Signals and communication technologyRelative Newton and Smoothing Multiplier Optimization Methods for Blind Source Separation
4 Citations2007Michael Zibulevsky
An extended notion of non-quadratic augmented Lagrangian is obtained by incorporating Lagrange multiplier into a smooth approximation of max-type func- tion, and preserves the sparse structure of Hessian.
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE<title>Nonseparable two-dimensional multiwavelet transform for image coding and compression</title>
3 Citations1998D. Wajcer, D. Stanhill +1 more
A method of designing non-separable, orthogonal 2D wavelet functions and filter- banks and a different method for the coefficient coding, employing the fact that there exists similarity between the subbands, to increase the efficiency of data compression are presented.
…