IEICE TRANSACTIONS on Fundamentals
Stable Learning Algorithm for Blind Separation of Temporally Correlated Acoustic Signals Combining Multistage ICA and Linear Prediction
Summary :
We newly propose a stable algorithm for blind source separation (BSS) combining multistage ICA (MSICA) and linear prediction. The MSICA is the method previously proposed by the authors, in which frequency-domain ICA (FDICA) for a rough separation is followed by time-domain ICA (TDICA) to remove residual crosstalk. For temporally correlated signals, we must use TDICA with a nonholonomic constraint to avoid the decorrelation effect from the holonomic constraint. However, the stability cannot be guaranteed in the nonholonomic case. To solve the problem, the linear predictors estimated from the roughly separated signals by FDICA are inserted before the holonomic TDICA as a prewhitening processing, and the dewhitening is performed after TDICA. The stability of the proposed algorithm can be guaranteed by the holonomic constraint, and the pre/dewhitening processing prevents the decorrelation. The experiments in a reverberant room reveal that the algorithm results in higher stability and separation performance.
- Publication
- IEICE TRANSACTIONS on Fundamentals Vol.E86-A No.8 pp.2028-2036
- Publication Date
- 2003/08/01
- Publicized
- Online ISSN
- DOI
- Type of Manuscript
- Special Section PAPER (Special Section on Digital Signal Processing)
- Category
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
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.
Cite this
Copy
Tsuyoki NISHIKAWA, Hiroshi SARUWATARI, Kiyohiro SHIKANO, "Stable Learning Algorithm for Blind Separation of Temporally Correlated Acoustic Signals Combining Multistage ICA and Linear Prediction" in IEICE TRANSACTIONS on Fundamentals,
vol. E86-A, no. 8, pp. 2028-2036, August 2003, doi: .
Abstract: We newly propose a stable algorithm for blind source separation (BSS) combining multistage ICA (MSICA) and linear prediction. The MSICA is the method previously proposed by the authors, in which frequency-domain ICA (FDICA) for a rough separation is followed by time-domain ICA (TDICA) to remove residual crosstalk. For temporally correlated signals, we must use TDICA with a nonholonomic constraint to avoid the decorrelation effect from the holonomic constraint. However, the stability cannot be guaranteed in the nonholonomic case. To solve the problem, the linear predictors estimated from the roughly separated signals by FDICA are inserted before the holonomic TDICA as a prewhitening processing, and the dewhitening is performed after TDICA. The stability of the proposed algorithm can be guaranteed by the holonomic constraint, and the pre/dewhitening processing prevents the decorrelation. The experiments in a reverberant room reveal that the algorithm results in higher stability and separation performance.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e86-a_8_2028/_p
Copy
@ARTICLE{e86-a_8_2028,
author={Tsuyoki NISHIKAWA, Hiroshi SARUWATARI, Kiyohiro SHIKANO, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Stable Learning Algorithm for Blind Separation of Temporally Correlated Acoustic Signals Combining Multistage ICA and Linear Prediction},
year={2003},
volume={E86-A},
number={8},
pages={2028-2036},
abstract={We newly propose a stable algorithm for blind source separation (BSS) combining multistage ICA (MSICA) and linear prediction. The MSICA is the method previously proposed by the authors, in which frequency-domain ICA (FDICA) for a rough separation is followed by time-domain ICA (TDICA) to remove residual crosstalk. For temporally correlated signals, we must use TDICA with a nonholonomic constraint to avoid the decorrelation effect from the holonomic constraint. However, the stability cannot be guaranteed in the nonholonomic case. To solve the problem, the linear predictors estimated from the roughly separated signals by FDICA are inserted before the holonomic TDICA as a prewhitening processing, and the dewhitening is performed after TDICA. The stability of the proposed algorithm can be guaranteed by the holonomic constraint, and the pre/dewhitening processing prevents the decorrelation. The experiments in a reverberant room reveal that the algorithm results in higher stability and separation performance.},
keywords={},
doi={},
ISSN={},
month={August},}
Copy
TY - JOUR
TI - Stable Learning Algorithm for Blind Separation of Temporally Correlated Acoustic Signals Combining Multistage ICA and Linear Prediction
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 2028
EP - 2036
AU - Tsuyoki NISHIKAWA
AU - Hiroshi SARUWATARI
AU - Kiyohiro SHIKANO
PY - 2003
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E86-A
IS - 8
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - August 2003
AB - We newly propose a stable algorithm for blind source separation (BSS) combining multistage ICA (MSICA) and linear prediction. The MSICA is the method previously proposed by the authors, in which frequency-domain ICA (FDICA) for a rough separation is followed by time-domain ICA (TDICA) to remove residual crosstalk. For temporally correlated signals, we must use TDICA with a nonholonomic constraint to avoid the decorrelation effect from the holonomic constraint. However, the stability cannot be guaranteed in the nonholonomic case. To solve the problem, the linear predictors estimated from the roughly separated signals by FDICA are inserted before the holonomic TDICA as a prewhitening processing, and the dewhitening is performed after TDICA. The stability of the proposed algorithm can be guaranteed by the holonomic constraint, and the pre/dewhitening processing prevents the decorrelation. The experiments in a reverberant room reveal that the algorithm results in higher stability and separation performance.
ER -
English
