An extension of the ICA model using latent variables

Abstract : The Independent Component Analysis (ICA) model is extended to the case where the components are not necessarily independent: depending on the value a hidden latent process at the same time, the unknown components of the linear mixture are assumed either mutually independent or dependent. We propose for this model a separation method which combines: (i) a classical ICA separation performed using the set of samples whose components are conditionally independent, and (ii) a method for estimation of the latent process. The latter task is performed by Iterative Conditional Estimation (ICE). It is an estimation technique in the case of incomplete data, which is particularly appealing because it requires only weak conditions. Finally, simulations validate our method and show that the separation quality is improved for sources generated according to our model
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [11 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01302411
Contributor : Médiathèque Télécom Sudparis & Institut Mines-Télécom Business School <>
Submitted on : Thursday, April 14, 2016 - 11:24:15 AM
Last modification on : Thursday, February 7, 2019 - 3:08:24 PM
Document(s) archivé(s) le : Tuesday, November 15, 2016 - 3:05:23 AM

File

icassp11.pdf
Files produced by the author(s)

Identifiers

Citation

Selwa Rafi, Marc Castella, Wojciech Pieczynski. An extension of the ICA model using latent variables. ICASSP 2011 : 36th International Conference on Acoustics, Speech and Signal Processing, May 2011, Prague, Czech Republic. IEEE, Proceedings ICASSP 2011 : 36th International Conference on Acoustics, Speech and Signal Processing, pp.3712 - 3715, 2011, 〈10.1109/ICASSP.2011.5947157 〉. 〈hal-01302411〉

Share

Metrics

Record views

162

Files downloads

29