Abstract
This chapter considers the multichannel blind deconvolution problem. Blind deconvolution refers to the problem of determining the impulse response of a system where the output is usually accessible and the system as well as the input are inaccessible. Multichannel blind deconvolution refers to the fact that multiple channels are observable and multiple sources are mixed and convolved simultaneously.
We know that this is our son, and that he was born blind. But by what means he now seeth, we know not or who hath opened his eyes, we know not . . .
John (9:20)
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Notes
Its name is due to statistics of the deconvolved signal which are approximately Bussgang (Bellini, 1994). The Bussgang statistic refers to Bussgang at Bell Labs who found that the autocorrelation and the correlation between the signal and its nonlinearly transformed signal exhibit the same characteristics.
A model that can measure the power spectrum with a pole-zero transfer function
The natural gradient is also valid in the multichannel case (Amari et al., 1997b).
i.e. microphones that can record signal sources witch may be far away from the microphone.
These audio-files are available in http://www.cnl.salk.edu/r,tewon/.
Fundamentals in speech recognition are presented by Rabiner and Juang (1993) and Deller et al. (1993).
The speech recognizer is trained with speech signals obtained from various people reading parts of the Wall Street Journal.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer Science+Business Media Dordrecht
About this chapter
Cite this chapter
Lee, TW. (1998). Blind Separation of Time-Delayed and Convolved Sources. In: Independent Component Analysis. Springer, Boston, MA. https://doi.org/10.1007/978-1-4757-2851-4_4
Download citation
DOI: https://doi.org/10.1007/978-1-4757-2851-4_4
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4419-5056-7
Online ISBN: 978-1-4757-2851-4
eBook Packages: Springer Book Archive