A Frequency Grouping Approach for Blind Deconvolution of Fairly Motionless Sources
A frequency grouping approach for multi-channel
instantaneous blind source separation (I-BSS) of convolutive
mixtures is proposed for a lower net residual inter-symbol
interference (ISI) and inter-channel interference (ICI) than the
conventional short-time Fourier transform (STFT) approach. Starting
in the time domain, STFTs are taken with overlapping windows to
convert the convolutive mixing problem into frequency domain
instantaneous mixing. Mixture samples at the same frequency but
from different STFT windows are grouped together forming unique
frequency groups.
The individual frequency group vectors are input to the I-BSS
algorithm of choice, from which the output samples are dispersed
back to their respective STFT windows. After applying the inverse
STFT, the resulting time domain signals are used to construct the
complete source estimates via the weighted overlap-add method
(WOLA). The proposed algorithm is tested for source deconvolution
given two mixtures, and simulated along with the STFT approach to
illustrate its superiority for fairly motionless sources.
[1] J. F. Cardosso and A. Souloumiac, "Blind Beamforming for Non-
Gaussian Signals, " IEE Proceedings Part F, VOl. 140, No. 6, pp 362-
370, 1993.
[2] E. G. L. Miller and J. W. Fisher III, "ICA using Spacing Estimates of
Entropy, "Journal of Machine Learning Research, vol. 4, pp. 1271-
1295, 2003.
[3] A. Hyvarinen, "Fast and Robust Fixed-Point Algorithms for Independent
Component Analysis, " IEEE Transactions on Neural Networks, vol. 10,
no. 2, pp. 626-634, 1999.
[4] S. Amari, A. Cichocki and H. H. Yang, "A new Learning Algorithm for
Blind Signal Separation, "Advances in Neural Information Processing
Systems, vol. 8, pp. 752-763, 1996.
[5] S. Ikeda and N. Murata, "A Method of ICA in Time-Frequency Domain,
" In Proc. ICA, pp. 365-371, 1999.
[6] K. Rahbar and J. P. Reilly, "A frequency Domain Method for Blind
Source Separation f Convolutive Audio Mixtures, " IEEE Transactions
on Speech and Audio Processing, vol. 13, no. 5, September 2005.
[7] S. Sanei, W. Wenwu and J. A. Chambers, "A Coupled HMM for Solving
the Permutation Problem in Frequency Domain BSS, " IEEE
International Conference on Acoustics, Speech and Signal Processing,
vol. 5, pp. 565-568, May 2004.
[8] C. Mejuto, A. Dapena and L. Castedo, "Frequency Domain Informax for
Blind Separation of Convolutive Mixtures, " Proceedings of ICA, pp.
315-320, Hensinki, Finland, June 2000.
[9] A. Dapena and C. Serviere, " A Simplified Frequency-Domain Approach
for Blind Separation of Convolutive Mixtures, " Proceedings of ICA,
San Diego, USA, pp. 569-574, 2001.
[10] R. Crochiere, "A Weighted Overlapp-add Method for Short Time
Fourier Transform Analysis/Synthesis, " IEEE Transactions on
Acoustics, Speech and Signal Processing, vol. 28, no. 1, pp. 99-102,
January 2003.
[1] J. F. Cardosso and A. Souloumiac, "Blind Beamforming for Non-
Gaussian Signals, " IEE Proceedings Part F, VOl. 140, No. 6, pp 362-
370, 1993.
[2] E. G. L. Miller and J. W. Fisher III, "ICA using Spacing Estimates of
Entropy, "Journal of Machine Learning Research, vol. 4, pp. 1271-
1295, 2003.
[3] A. Hyvarinen, "Fast and Robust Fixed-Point Algorithms for Independent
Component Analysis, " IEEE Transactions on Neural Networks, vol. 10,
no. 2, pp. 626-634, 1999.
[4] S. Amari, A. Cichocki and H. H. Yang, "A new Learning Algorithm for
Blind Signal Separation, "Advances in Neural Information Processing
Systems, vol. 8, pp. 752-763, 1996.
[5] S. Ikeda and N. Murata, "A Method of ICA in Time-Frequency Domain,
" In Proc. ICA, pp. 365-371, 1999.
[6] K. Rahbar and J. P. Reilly, "A frequency Domain Method for Blind
Source Separation f Convolutive Audio Mixtures, " IEEE Transactions
on Speech and Audio Processing, vol. 13, no. 5, September 2005.
[7] S. Sanei, W. Wenwu and J. A. Chambers, "A Coupled HMM for Solving
the Permutation Problem in Frequency Domain BSS, " IEEE
International Conference on Acoustics, Speech and Signal Processing,
vol. 5, pp. 565-568, May 2004.
[8] C. Mejuto, A. Dapena and L. Castedo, "Frequency Domain Informax for
Blind Separation of Convolutive Mixtures, " Proceedings of ICA, pp.
315-320, Hensinki, Finland, June 2000.
[9] A. Dapena and C. Serviere, " A Simplified Frequency-Domain Approach
for Blind Separation of Convolutive Mixtures, " Proceedings of ICA,
San Diego, USA, pp. 569-574, 2001.
[10] R. Crochiere, "A Weighted Overlapp-add Method for Short Time
Fourier Transform Analysis/Synthesis, " IEEE Transactions on
Acoustics, Speech and Signal Processing, vol. 28, no. 1, pp. 99-102,
January 2003.
@article{"International Journal of Electrical, Electronic and Communication Sciences:53474", author = "E. S. Gower and T. Tsalaile and E. Rakgati and M. O. J. Hawksford", title = "A Frequency Grouping Approach for Blind Deconvolution of Fairly Motionless Sources", abstract = "A frequency grouping approach for multi-channel
instantaneous blind source separation (I-BSS) of convolutive
mixtures is proposed for a lower net residual inter-symbol
interference (ISI) and inter-channel interference (ICI) than the
conventional short-time Fourier transform (STFT) approach. Starting
in the time domain, STFTs are taken with overlapping windows to
convert the convolutive mixing problem into frequency domain
instantaneous mixing. Mixture samples at the same frequency but
from different STFT windows are grouped together forming unique
frequency groups.
The individual frequency group vectors are input to the I-BSS
algorithm of choice, from which the output samples are dispersed
back to their respective STFT windows. After applying the inverse
STFT, the resulting time domain signals are used to construct the
complete source estimates via the weighted overlap-add method
(WOLA). The proposed algorithm is tested for source deconvolution
given two mixtures, and simulated along with the STFT approach to
illustrate its superiority for fairly motionless sources.", keywords = "Blind source separation, short-time Fouriertransform, weighted overlap-add method", volume = "5", number = "8", pages = "960-6", }