Convolutive blind source separation using relative optimization

Details Convolutive blind source separation using relative optimization Convolutive blind source separation using relative optimization

2006-06-29

2010-06-15

Lugo, David B (Department: 2611)

Pulse or digital communications

Systems using alternating or pulsating current

Plural channels for transmission of a single pulse train

C375S350000

Reexamination Certificate

active

07738574

ABSTRACT:
A method and apparatus for separating a multi-channel mixed signal are provided. The method includes the steps of: a) transforming a temporal domain to a frequency domain by performing a discrete Fourier transform onto at least one of mixed signals inputted from an external device through multi-channel; b) estimating multi-decorrelation by calculating a plurality of cross power spectra for the mixed signal in the transformed frequency domain; c) estimating a separation coefficient of the mixed signal based on relative optimization in order to decorrelate the calculated cross power spectra, where the separation coefficient is serially updated; d) transforming the frequency domain to the temporal domain by performing an inverse discrete Fourier transform on the estimated separation coefficient in the temporal domain; and e) separating an original signal from the mixed signal by filtering the mixed signal using the separation coefficient of the transformed temporal domain.

REFERENCES:
patent: 2005/0240642 (2005-10-01), Parra et al.
patent: 2006/0067541 (2006-03-01), Yamada et al.
patent: 2001-0042537 (2001-05-01), None
Bronstein et al., “Relative Optimization for Blind Deconvolution,” Jun. 2005, IEEE Transactions on Signal Processing, vol. 53, Issue 6, 2018-2026.
Ziehe et al., “A Fast Algorithm for Joint Diagonalization with Application to Blind Source Separation,” Sep. 23, 2003, Bliss Technical Report, 1-14.
‘Convolutive Blind Separation of Non-Stationary Sources’ Parra et al., IEEE Transactions on Speech and Audio Processing, vol. 8, No. 3, May 2000, pp. 320-327.
Algorithms for Approximate Joint Diagonalization of Hermitian Matrices: Relative Gradient, Relative Newton and Relative Trust-Region, Seungjin Choi, Department of Computer Science & Engineering, Pohang University of Science and Technology, Korea.

Affiliated with

Also associated with

Rating

Convolutive blind source separation using relative optimization does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Convolutive blind source separation using relative optimization, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Convolutive blind source separation using relative optimization will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-4236051