Abstract
Source separation consists of recovering a set of independent signals when only mixtures with unknown coefficients are observed. This paper introduces a class of adaptive algorithms for source separation that implements an adaptive version of equivariant estimation and is henceforth called equivariant adaptive separation via independence (EASI). The EASI algorithms are based on the idea of serial updating. This specific form of matrix updates systematically yields algorithms with a simple structure for both real and complex mixtures. Most importantly, the performance of an EASI algorithm does not depend on the mixing matrix. In particular, convergence rates, stability conditions, and interference rejection levels depend only on the (normalized) distributions of the source signals. Closed-form expressions of these quantities are given via an asymptotic performance analysis. The theme of equivariance is stressed throughout the paper. The source separation problem has an underlying multiplicative structure. The parameter space forms a (matrix) multiplicative group. We explore the (favorable) consequences of this fact on implementation, performance, and optimization of EASI algorithms.
Keywords
Equivariant mapBlind signal separationMultiplicative functionSource separationIndependence (probability theory)Matrix (chemical analysis)AlgorithmStability (learning theory)Computer scienceIndependent component analysisMathematicsArtificial intelligenceStatisticsPure mathematics
Affiliated Institutions
Related Publications
Independent Component Analysis
A tutorial-style introduction to a class of methods for extracting independent signals from a mixture of signals originating from different physical sources; includes MatLab com...
Robust neural networks with on-line learning for blind identification and blind separation of sources
Two unsupervised, self-normalizing, adaptive learning algorithms are developed for robust blind identification and/or blind separation of independent source signals from a linea...
A class of neural networks for independent component analysis
Independent component analysis (ICA) is a recently developed, useful extension of standard principal component analysis (PCA). The ICA model is utilized mainly in blind separati...
Analog CMOS integration and experimentation with an autoadaptive independent component analyzer
In this paper we explore a combination of above-and-subthreshold CMOS circuit techniques for the implementation of analog neuromorphic network processing. The implemented networ...
Separation of a mixture of independent signals using time delayed correlations
The problem of separating n linearly superimposed uncorrelated signals and determining their mixing coefficients is reduced to an eigenvalue problem which involves the simultane...
Publication Info
- Year
- 1996
- Type
- article
- Volume
- 44
- Issue
- 12
- Pages
- 3017-3030
- Citations
- 1345
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
1345
OpenAlex
Cite This
J.-F. Cardoso,
B.H. Laheld
(1996).
Equivariant adaptive source separation.
IEEE Transactions on Signal Processing
, 44
(12)
, 3017-3030.
https://doi.org/10.1109/78.553476
Identifiers
- DOI
- 10.1109/78.553476