Signal separation of nonlinear time-delayed mixture: Time domain approach

W. L. Woo, S. S. Dlay, J. E. Hudson

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this paper, a novel algorithm is proposed to solve blind signal separation of nonlinear time-delayed mixtures of statistically independent sources. Both mixing and nonlinear distortion are included in the proposed model. Maximum Likelihood (ML) approach is developed to estimate the parameters in the model and this is formulated within the framework of the generalized Expectation-Maximization (EM) algorithm. Adaptive polynomial basis expansion is used to estimate the nonlinearity of the mixing model. In the E-step, the sufficient statistics associated with the source signals are estimated while in the M-step, the parameters are optimized by using these statistics. Generally, the nonlinear distortion renders the statistics intractable and difficult to be formulated in a closed form. However, in this paper it is proved that with the use of Extended Kalman Smoother (EKS) around a linearized point, the M-step is made tractable and can be solved by linear equations.

Original languageEnglish
Title of host publication2009 International Conference on Signal Acquisition and Processing, ICSAP 2009
PublisherIEEE
Pages203-207
Number of pages5
ISBN (Print)9780769535944
DOIs
Publication statusPublished - 14 Jul 2009
Event2009 International Conference on Signal Acquisition and Processing, ICSAP 2009 - Kuala Lumpur, Malaysia
Duration: 3 Apr 20095 Apr 2009

Conference

Conference2009 International Conference on Signal Acquisition and Processing, ICSAP 2009
CountryMalaysia
CityKuala Lumpur
Period3/04/095/04/09

Fingerprint

Dive into the research topics of 'Signal separation of nonlinear time-delayed mixture: Time domain approach'. Together they form a unique fingerprint.

Cite this