Abstract
Methods based on one-channel audio source separation are more practical than multi-channel ones in the real world applications. In this paper we proposed a new method to separate audio signals from single convolutive mixture. This method is based on subband domain to blindly segregate this mixture and it is composed of three stages. In the first stage, the observed mixture is divided into a finite number of subbands through filtering with a parallel bank of FIR band-pass filters. The second stage employed empirical mode decomposition (EMD) to extract intrinsic mode functions (IMFs) in the each subband. Then we obtain independent basis vectors by applying principle component analysis (PCA) and independent component analysis (ICA) to the vectors of IMFs in the each subband. In the third stage we perform subband synthesis process to reconstruct fullband separated signals. We have produced experimental results using the proposed separation technique. The results showed that the proposed method truly performs separation of speech and interfering sound from a single mixture.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
D.E. Dudgeon, and R.M. Mersereau, Multidimensional Digital Signal Processing, Prentice Hall, Englewood Cliffs, USA, 1984.
K. Torkkola, Blind separation of delayed and convolved sources, John Wiley & Sons, 2000.
G.J. Jang, and T.W. Lee,, “A maximum likelihood approach to single channel source separation,” Journal of Machine Learning Research, vol.4, pp. 1365-1392, 2003.
G.J. Jang, T.W. Lee, and Y.H. Oh,, “Single channel signal separation using time-domain basis functions,” IEEE Signal Process. Lett., vol.10, pp. 168-171, 2003.
L. Parra, and C. Spence,, “Convolutive blind separation of non-stationary sources,” IEEE Trans. Speech and Audio Process., vol. 8, pp. 320-327, 2000.
P. Smaragdis,, “Blind separation of convolved mixtures in the frequency domain,” Neurocomp., vol. 22, pp.21-34, 1998.
K. Kokkinakis, and P.C. Loizou,, “Subband-based blind signal processing for source separation in convolutive mixtures of speech,” IEEE International Conf. on Acoustic, Speech and Signal Processing, Honolulu, HI, pp. 917-920, 2007.
N. Grbic, X.J. Tao, S.E. Nordholm, and I. Claesson,, “Blind signal separation using overcomplete subband representation,” IEEE Trans. Speech and Audio Process., vol. 9, pp. 524-533, 2001.
S. Araki, S. Makino, T. Nishikawa, and H. Saruwatari,, “Fundamental limitation of frequency domain blind source separation for convolutive mixture of speech,” IEEE Trans. Speech and Audio Process., pp. 2737-2740, 2001.
N.E. Huang, Z. Shen, S.R. Long, M.C. Wu, H.H. Shih, Q. Zheng, N.C. Yen, C.C. Tung, and H.H. Liu,, “The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis,” Journal of Proceedings the Royal of Society, pp. 903-995, 1998.
K.I. Molla, K. Hirose, and N. Minematsu,, “Separation of mixed audio signals by decomposing Hilbert spectrum with modified EMD,” IEICE Trans. on Fundamentals of Electronics, Communications and Computer Sciences, pp. 727-734, 2006.
S. Araki1, S. Makino, R. Aichner, T.Nishikawa, and H. Saruwatari,, “Subband-Based blind separation for convolutive mixtures of speech,” IEICE Trans. on Fundamentals of Electronics, Communications and Computer Sciences, pp. 3593-3603, 2005.
M.E. Wall, A. Rechtsteiner, and L.M. Rocha1,, “Singular value decomposition and principle component analysis,” Modeling, Algorithms, and Informatics Group (CCS-3), Los Alamos, New Mexico 87545, USA, 2003.
Z. Koldovský, P. Tichavský, and E. Oja,, “Efficient variant of algorithm FastICA for independent component analysis attaining the CramÉr-Rao lower bound,” IEEE Trans. on Neural Networks, vol. 17, pp. 1265-1277, 2006.
E. Vincent, R. Gribonval, and C. Fevotte,, “Performance measurement in blind audio source separation,” IEEE Trans. on Speech Audio Process., vol. 14, pp. 1462-1469, 2005.
K. Nayebi, T.P. Barnwell, and M.J.T. Smith,, “Time-domain filter bank analysis: A new design theory,” IEEE Trans. Signal Process., vol. 40, pp. 1412-1429, 1992.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer Science+Business Media B.V.
About this paper
Cite this paper
Taghia, J., Taghia, J. (2008). One-Channel Audio Source Separation of Convolutive Mixture. In: Sobh, T. (eds) Advances in Computer and Information Sciences and Engineering. Springer, Dordrecht. https://doi.org/10.1007/978-1-4020-8741-7_36
Download citation
DOI: https://doi.org/10.1007/978-1-4020-8741-7_36
Publisher Name: Springer, Dordrecht
Print ISBN: 978-1-4020-8740-0
Online ISBN: 978-1-4020-8741-7
eBook Packages: Computer ScienceComputer Science (R0)