Blind Separation of Sources Using Temporal Correlation of the Observed Signals

Mitsuru KAWAMOTO; Kiyotoshi MATSUOKA; Masahiro OYA

Blind Separation of Sources Using Temporal Correlation of the Observed Signals

Mitsuru KAWAMOTO, Kiyotoshi MATSUOKA, Masahiro OYA

Full Text Views

0

Share
Cite this

Summary :

This paper proposes a new method for recovering the original signals from their linear mixtures observed by the same number of sensors. It is performed by identifying the linear transform from the sources to the sensors, only using the sensor signals. The only assumption of the source signals is basically the fact that they are statistically mutually independent. In order to perform the 'blind' identification, some time-correlational information in the observed signals are utilized. The most important feature of the method is that the full information of available time-correlation data (second-order statistics) is evaluated, as opposed to the conventional methods. To this end, an information-theoretic cost function is introduced, and the unknown linear transform is found by minimizing it. The propsed method gives a more stable solution than the conventional methods.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E80-A No.4 pp.695-704

Publication Date: 1997/04/25

Publicized

Online ISSN

DOI

Type of Manuscript

Category: Digital Signal Processing

Cite this

Copy

Mitsuru KAWAMOTO, Kiyotoshi MATSUOKA, Masahiro OYA, "Blind Separation of Sources Using Temporal Correlation of the Observed Signals" in IEICE TRANSACTIONS on Fundamentals, vol. E80-A, no. 4, pp. 695-704, April 1997, doi: .
Abstract: This paper proposes a new method for recovering the original signals from their linear mixtures observed by the same number of sensors. It is performed by identifying the linear transform from the sources to the sensors, only using the sensor signals. The only assumption of the source signals is basically the fact that they are statistically mutually independent. In order to perform the 'blind' identification, some time-correlational information in the observed signals are utilized. The most important feature of the method is that the full information of available time-correlation data (second-order statistics) is evaluated, as opposed to the conventional methods. To this end, an information-theoretic cost function is introduced, and the unknown linear transform is found by minimizing it. The propsed method gives a more stable solution than the conventional methods.
URL: https://globals.ieice.org/en_transactions/fundamentals/10.1587/e80-a_4_695/_p

Copy

@ARTICLE{e80-a_4_695,
author={Mitsuru KAWAMOTO, Kiyotoshi MATSUOKA, Masahiro OYA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Blind Separation of Sources Using Temporal Correlation of the Observed Signals},
year={1997},
volume={E80-A},
number={4},
pages={695-704},
abstract={This paper proposes a new method for recovering the original signals from their linear mixtures observed by the same number of sensors. It is performed by identifying the linear transform from the sources to the sensors, only using the sensor signals. The only assumption of the source signals is basically the fact that they are statistically mutually independent. In order to perform the 'blind' identification, some time-correlational information in the observed signals are utilized. The most important feature of the method is that the full information of available time-correlation data (second-order statistics) is evaluated, as opposed to the conventional methods. To this end, an information-theoretic cost function is introduced, and the unknown linear transform is found by minimizing it. The propsed method gives a more stable solution than the conventional methods.},
keywords={},
doi={},
ISSN={},
month={April},}

Copy

TY - JOUR
TI - Blind Separation of Sources Using Temporal Correlation of the Observed Signals
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 695
EP - 704
AU - Mitsuru KAWAMOTO
AU - Kiyotoshi MATSUOKA
AU - Masahiro OYA
PY - 1997
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E80-A
IS - 4
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - April 1997
AB - This paper proposes a new method for recovering the original signals from their linear mixtures observed by the same number of sensors. It is performed by identifying the linear transform from the sources to the sensors, only using the sensor signals. The only assumption of the source signals is basically the fact that they are statistically mutually independent. In order to perform the 'blind' identification, some time-correlational information in the observed signals are utilized. The most important feature of the method is that the full information of available time-correlation data (second-order statistics) is evaluated, as opposed to the conventional methods. To this end, an information-theoretic cost function is introduced, and the unknown linear transform is found by minimizing it. The propsed method gives a more stable solution than the conventional methods.
ER -