arrow
Volume 28, Issue 3
A Time Domain Blind Decorrelation Method of Convolutive Mixtures Based on an IIR Model

Jie Liu, Jack Xin & Yingyong Qi

J. Comp. Math., 28 (2010), pp. 371-385.

Published online: 2010-06

Export citation
  • Abstract

We study a time domain decorrelation method of source signal separation from convolutive sound mixtures based on an infinite impulse response (IIR) model. The IIR model uses fewer parameters to capture the physical mixing process and is useful for finding low dimensional separating solutions. We present inversion formulas to decorrelate the mixture signals and derive filter equations involving second order time lagged statistics of mixtures. We then formulate an $l_1$ constrained minimization problem and solve it by an iterative method. Numerical experiments on recorded sound mixtures show that our method is capable of sound separation in low dimensional parameter spaces with good perceptual quality and low correlation coefficient comparable to the known infomax method.

  • AMS Subject Headings

94A12, 65H10, 65C60.

  • Copyright

COPYRIGHT: © Global Science Press

  • Email address
  • BibTex
  • RIS
  • TXT
@Article{JCM-28-371, author = {}, title = {A Time Domain Blind Decorrelation Method of Convolutive Mixtures Based on an IIR Model}, journal = {Journal of Computational Mathematics}, year = {2010}, volume = {28}, number = {3}, pages = {371--385}, abstract = {

We study a time domain decorrelation method of source signal separation from convolutive sound mixtures based on an infinite impulse response (IIR) model. The IIR model uses fewer parameters to capture the physical mixing process and is useful for finding low dimensional separating solutions. We present inversion formulas to decorrelate the mixture signals and derive filter equations involving second order time lagged statistics of mixtures. We then formulate an $l_1$ constrained minimization problem and solve it by an iterative method. Numerical experiments on recorded sound mixtures show that our method is capable of sound separation in low dimensional parameter spaces with good perceptual quality and low correlation coefficient comparable to the known infomax method.

}, issn = {1991-7139}, doi = {https://doi.org/10.4208/jcm.2009.10-m2900}, url = {http://global-sci.org/intro/article_detail/jcm/8525.html} }
TY - JOUR T1 - A Time Domain Blind Decorrelation Method of Convolutive Mixtures Based on an IIR Model JO - Journal of Computational Mathematics VL - 3 SP - 371 EP - 385 PY - 2010 DA - 2010/06 SN - 28 DO - http://doi.org/10.4208/jcm.2009.10-m2900 UR - https://global-sci.org/intro/article_detail/jcm/8525.html KW - Blind Decorrelation, Convolutive Mixtures, IIR Modeling, $l_1$ Constrained Minimization. AB -

We study a time domain decorrelation method of source signal separation from convolutive sound mixtures based on an infinite impulse response (IIR) model. The IIR model uses fewer parameters to capture the physical mixing process and is useful for finding low dimensional separating solutions. We present inversion formulas to decorrelate the mixture signals and derive filter equations involving second order time lagged statistics of mixtures. We then formulate an $l_1$ constrained minimization problem and solve it by an iterative method. Numerical experiments on recorded sound mixtures show that our method is capable of sound separation in low dimensional parameter spaces with good perceptual quality and low correlation coefficient comparable to the known infomax method.

Jie Liu, Jack Xin & Yingyong Qi. (2019). A Time Domain Blind Decorrelation Method of Convolutive Mixtures Based on an IIR Model. Journal of Computational Mathematics. 28 (3). 371-385. doi:10.4208/jcm.2009.10-m2900
Copy to clipboard
The citation has been copied to your clipboard