© The Institution of Engineering and Technology
Subband-based blind source separation has great potential in solving the complicated convolutive mixing problem. However, its performance is largely affected by the permutation ambiguity problem during the synthesis stage. Researchers have suggested methods to correct the permutation by exploiting the correlation information between adjacent frequencies/subbands. An improved solution to this permutation problem is proposed based on a novel filter banks design method, which is based on a model that includes inter-subband correlation as part of the optimisation criterion. Simulation results show that a better subband permutation alignment result has been achieved, leading to improved separation performance.
References
-
-
1)
-
N. Murata ,
S. Ikeda ,
A. Ziehe
.
An approach to blind sources separation based on temporal structure of speech signals.
Neurocomputing
,
1 -
24
-
2)
-
Douglas, S.C., Gupta, M.: `Scaled natural gradient algorithms for instantaneous and convolutive blind source separation', Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, April 2007, 2, p. II-637–II-640.
-
3)
-
Toyama, K., Plumbley, M.D.: `Using phase linearity in frequency-domain ICA to tackle the permutation problem', Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, April 2009, p. 3165–3168.
-
4)
-
Liu, W., Mandic, D.P., Cichocki, A.: `Blind source separation based on generalised canonical correlation analysis and its adaptive realization', Proc. Int. Congress on Image and Signal Processing, May 2008, Hainan, China, 5, p. 417–421.
-
5)
-
S. Araki ,
R. Mukai ,
S. Makino ,
T. Nishikawa ,
H. Saruwatari
.
The fundamental limitation of frequency domain blind source separation for convolutive mixture of speech.
IEEE Trans. Speech Audio Process.
,
2 ,
109 -
116
-
6)
-
K. Kokkinakis ,
A.K. Nandi
.
Multichannel blind deconvolution for source separation in convolutive mixtures of speech.
IEEE Trans. Audio Speech Lang. Process.
,
1 ,
200 -
212
-
7)
-
S.C. Douglas ,
Y.H. Hu ,
J.N. Hwang
.
(2002)
Blind signal separation and blind deconvolution, Handbook of neural network signal processing.
-
8)
-
W. Liu ,
D.P. Mandic ,
A. Cichocki
.
Analysis and online realization of the CCA approach for blind source separation.
IEEE Trans. Neural Netw.
,
5 ,
1505 -
1510
-
9)
-
N. Grbic ,
X.-J. Tao ,
S.E. Nordholm ,
I. Claesson
.
Blind signal separation using overcomplete subband representation.
IEEE Trans. Speech Audio Process.
,
5 ,
524 -
533
-
10)
-
S.Y. Low ,
S. Nordholm ,
R. Togneri
.
Convolutive blind signal separation with post-processing.
IEEE Trans. Speech Audio Process.
,
5 ,
539 -
548
-
11)
-
Nguyen, T.Q., Heller, P.N.: `Biorthogonal cosine-modulated filter bank', Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, May 1996, Atlanta, GA, 3, p. 1471–1474.
-
12)
-
P.P. Vaidyanathan
.
Orthonormal and biorthonormal filter banks as convolvers, and convolutional coding gain.
IEEE Trans. Signal Process.
,
6 ,
2110 -
2130
-
13)
-
R.D. Koilpillai ,
P.P. Vaidyanathan
.
Cosine-modulated FIR filter banks satisfying perfect reconstruction.
IEEE Trans. Signal Process.
,
4 ,
770 -
783
-
14)
-
H.-M. Park ,
C.S. Dhir ,
S.-H. Oh ,
S.-Y. Lee
.
A filter bank approach to independent component analysis for convolved mixtures.
Neurocomputing
,
2065 -
2077
-
15)
-
A.J. Bell ,
T.J. Sejnowski
.
An information-maximisation approach to blind separation and blind deconvolution.
Neural Comput.
,
1129 -
1159
-
16)
-
S.-I. Amari ,
A. Cichocki ,
H.H. Yang
.
A new learning algorithm for blind signal separation.
Adv. Neural Inf. Process. Syst.
,
757 -
763
-
17)
-
Araki, S., Makino, S., Aichner, R., Nishikawa, T., Saruwatari, H.: `Subband based blind source separation for convolutive mixtures of speech', Proc. IEEE Int. Conf. Acoustics, Speech, and Signal Processing, April 2003, 5, p. 509–512.
-
18)
-
A. Cichocki ,
R. Unbehauen ,
E. Rummert
.
Robust learning algorithm for blind separation of signals.
Electron. Lett.
,
17 ,
1386 -
1387
-
19)
-
W. Liu ,
D.P. Mandic ,
A. Cichocki
.
Blind source extraction based on a linear predictor.
IET Signal Process.
,
1 ,
29 -
34
-
20)
-
J. Kliewer ,
A. Mertins
.
Oversampled cosine-modulated filter banks with arbitrary system delay.
IEEE Trans. Signal Process.
,
4 ,
941 -
955
-
21)
-
K.A. Lee ,
W.S. Gan
.
On the subband orthogonality of cosine-modulated filter banks.
IEEE Trans. Circuits Syst. II: Express Briefs
,
8 ,
677 -
681
-
22)
-
Y.O. Li ,
T. Adal ,
W. Wang ,
V.D. Calhoun
.
Joint blind source separation by multi-set canonical correlation analysis.
IEEE Trans. Signal Process.
,
10
-
23)
-
Ikram, M.Z., Morgan, D.R.: `Exploring permutation inconsistency in blind separation of speech signals in a reverberant environment', Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, June 2000, Istanbul, Turkey, 2, p. 1041–1044.
-
24)
-
A. Hyv̈arinen ,
J. Harhunen ,
E. Oja
.
(2001)
Independent component analysis.
-
25)
-
Kurita, S., Saruwatari, H., Kajita, S., Takeda, K., Itakura, F.: `Evaluation of blind signal separation method using directivity pattern under reverberant conditions', Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, June 2000, Istanbul, Turkey, 5, p. 3140–3143.
-
26)
-
Russell, I., Xi, J., Mertins, A., Chichaw, J.: `Integration of DFT and cosine-modulated filter banks with blind separation of convolutively mixed non-stationary sources', Sensor Array and Multichannel Signal Proc. Workshop Proc., July 2004, p. 441–445.
-
27)
-
Liu, W., Mandic, D.P., Cichocki, A.: `A dual-linear predictor approach to blind source extraction for noisy mixtures', Proc. IEEE Workshop on Sensor Array and Multichannel Signal Processing, July 2008, Darmstadt, Germany, p. 515–519.
-
28)
-
A. Cichocki ,
S.I. Amari
.
(2001)
Adaptive blind signal and image processing.
-
29)
-
P. Smaragdis
.
Blind separation of convolved mixtures in the frequency domain.
Neurocomputing
,
21 -
34
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-spr.2011.0015
Related content
content/journals/10.1049/iet-spr.2011.0015
pub_keyword,iet_inspecKeyword,pub_concept
6
6