Information-theoretic approach to blind separation of sources in non-linear mixture
Signal Processing - Special issue on neural networks
Spoken Language Processing: A Guide to Theory, Algorithm, and System Development
Spoken Language Processing: A Guide to Theory, Algorithm, and System Development
Using Signal Invariants to Perform Nonlinear Blind Source Separation
ICA '09 Proceedings of the 8th International Conference on Independent Component Analysis and Signal Separation
Riemannian optimization method on the flag manifold for independent subspace analysis
ICA'06 Proceedings of the 6th international conference on Independent Component Analysis and Blind Signal Separation
Source separation in post-nonlinear mixtures
IEEE Transactions on Signal Processing
| Hi-index | 35.68 |
Given a time series of multicomponent measurements x(t), the usual objective of nonlinear blind source separation (BSS) is to find a "source" time series s(t), comprised of statistically independent combinations of the measured components. In this paper, the source time series is required to have a density function in (s, s)-space that is equal to the product of density functions of individual components. This formulation of the BSS problem has a solution that is unique, up to permutations and componentwise transformations. Separability is shown to impose constraints on certain locally invariant (scalar) functions of x, which are derived from local higher-order correlations of the data's velocity x. The data are separable if and only if they satisfy these constraints, and, if the constraints are satisfied, the sources can be explicitly constructed from the data. The method is illustrated by using it to recover the contents of two simultaneous speech-like sounds recorded with a single microphone.