Frequency domain blind source separation has the great advantage that the complicated convolution in time domain becomes multiple efficient multiplications in frequency domain. However, the inherent ambiguity of permutation of ICA becomes an important problem that the separated signals at different frequencies may be permuted in order. Mapping the separated signal at each frequency to a target source remains to be a difficult problem. In this paper, we first discuss the inter-frequency correlation based method, and propose a new method using the continuity in power between adjacent frequency components of same source. The proposed method also implicitly utilizes the information of inter-frequency correlation, as such has better performance than the previous method.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Xuebin HU, Hidefumi KOBATAKE, "A New Method for Solving the Permutation Problem of Frequency-Domain Blind Source Separation" in IEICE TRANSACTIONS on Fundamentals,
vol. E88-A, no. 6, pp. 1543-1548, June 2005, doi: 10.1093/ietfec/e88-a.6.1543.
Abstract: Frequency domain blind source separation has the great advantage that the complicated convolution in time domain becomes multiple efficient multiplications in frequency domain. However, the inherent ambiguity of permutation of ICA becomes an important problem that the separated signals at different frequencies may be permuted in order. Mapping the separated signal at each frequency to a target source remains to be a difficult problem. In this paper, we first discuss the inter-frequency correlation based method, and propose a new method using the continuity in power between adjacent frequency components of same source. The proposed method also implicitly utilizes the information of inter-frequency correlation, as such has better performance than the previous method.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1093/ietfec/e88-a.6.1543/_p
Copy
@ARTICLE{e88-a_6_1543,
author={Xuebin HU, Hidefumi KOBATAKE, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={A New Method for Solving the Permutation Problem of Frequency-Domain Blind Source Separation},
year={2005},
volume={E88-A},
number={6},
pages={1543-1548},
abstract={Frequency domain blind source separation has the great advantage that the complicated convolution in time domain becomes multiple efficient multiplications in frequency domain. However, the inherent ambiguity of permutation of ICA becomes an important problem that the separated signals at different frequencies may be permuted in order. Mapping the separated signal at each frequency to a target source remains to be a difficult problem. In this paper, we first discuss the inter-frequency correlation based method, and propose a new method using the continuity in power between adjacent frequency components of same source. The proposed method also implicitly utilizes the information of inter-frequency correlation, as such has better performance than the previous method.},
keywords={},
doi={10.1093/ietfec/e88-a.6.1543},
ISSN={},
month={June},}
Copy
TY - JOUR
TI - A New Method for Solving the Permutation Problem of Frequency-Domain Blind Source Separation
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1543
EP - 1548
AU - Xuebin HU
AU - Hidefumi KOBATAKE
PY - 2005
DO - 10.1093/ietfec/e88-a.6.1543
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E88-A
IS - 6
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - June 2005
AB - Frequency domain blind source separation has the great advantage that the complicated convolution in time domain becomes multiple efficient multiplications in frequency domain. However, the inherent ambiguity of permutation of ICA becomes an important problem that the separated signals at different frequencies may be permuted in order. Mapping the separated signal at each frequency to a target source remains to be a difficult problem. In this paper, we first discuss the inter-frequency correlation based method, and propose a new method using the continuity in power between adjacent frequency components of same source. The proposed method also implicitly utilizes the information of inter-frequency correlation, as such has better performance than the previous method.
ER -