Abstract
In this paper we address the problem of overcomplete BSS for convolutive mixtures following a two-step approach. In the first step the mixing matrix is estimated, which is then used to separate the signals in the second step. For estimating the mixing matrix we propose an algorithm based on hierarchical clustering, assuming that the source signals are sufficiently sparse. It has the advantage of working directly on the complex valued sample data in the frequency-domain. It also shows better convergence than algorithms based on self-organizing maps. The results are improved by reducing the variance of direction of arrival. Experiments show accurate estimations of the mixing matrix and very low musical tone noise.
This is a preview of subscription content, log in via an institution to check access.
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
Winter, S., Sawada, H., Makino, S.: Geometrical interpretation of the PCA subspace method for overdetermined blind source separation. In: Proc. ICA 2003, pp. 775–780 (2003)
Matsuoka, K.: Independent component analysis and its applications to sound signal separation. In: Proc. IWAENC 2003, Kyoto, pp. 15–18 (2003)
Sawada, H., Mukai, R., Araki, S., Makino, S.: A robust and precise method for solving the permutation problem of frequency-domain blind source separation. In: Proc. ICA 2003, pp. 505–510 (2003)
Yilmaz, O., Rickard, S.: Blind separation of speech mixtures via time-frequency masking. IEEE Transactions on Signal Processing (2004) (to appear)
Rickard, S., Yilmaz, O.: On the approximate W-disjoint orthogonality of speech. In: Proc. ICASSP 2002, pp. 529–532 (2002)
Vielva, L., Santamaria, I., Pantaleon, C., Ibanez, J., Erdogmus, D.: Estimation of the mixing matrix for underdetermined blind source separation using spectral estimation techniques. In: Proc. EUSIPCO 2002, vol. 1, pp. 557–560 (2002)
Bofill, P., Zibulevsky, M.: Blind separation of more sources than mixtures using sparsity of their short-time fourier transform. In: Proc. ICA 2000, pp. 87–92 (2000)
Bofill, P.: Underdetermined blind separation of delayed sound sources in the frequency domain. Neurocomputing 55, 627–641 (2003)
Araki, S., Makino, S., Blin, A., Mukai, R., Sawada, H.: Blind separation of more speech than sensors with less distortion by combining spareseness and ica. In: Proc. IWAENC 2003, pp. 271–274 (2003)
Blin, A., Araki, S., Makino, S.: Blind source separation when speech signals outnumber sensors using a sparseness - mixing matrix estimation (SMME). In: Proc. IWAENC 2003, pp. 211–214 (2003)
Waheed, K., Salem, F.M.: Algebraic overcomplete independent component analysis. In: Proc. ICA 2003, pp. 1077–1082 (2003)
Theis, F.: Mathematics in independent component analysis. PhD thesis, University of Regensburg (2002)
Hastie, T., Tibshirani, R., Friedman, J.: The elements of statistical learning: data mining, inference, and prediction. Springer Series in Statistics. Springer, Heidelberg (2002)
Vielva, L., Erdogmus, D., Principe, J.C.: Underdetermined blind source separation using a probabilistic source sparsity model. In: Proc. ICA 2001, pp. 675–679 (2001)
Sawada, H., Mukai, R., de la Kethulle de Ryhove, S., Araki, S., Makino, S.: Spectral smoothing for frequency-domain blind source separation. In: Proc. IWAENC 2003, pp. 311–314 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Winter, S., Sawada, H., Araki, S., Makino, S. (2004). Overcomplete BSS for Convolutive Mixtures Based on Hierarchical Clustering. In: Puntonet, C.G., Prieto, A. (eds) Independent Component Analysis and Blind Signal Separation. ICA 2004. Lecture Notes in Computer Science, vol 3195. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30110-3_83
Download citation
DOI: https://doi.org/10.1007/978-3-540-30110-3_83
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23056-4
Online ISBN: 978-3-540-30110-3
eBook Packages: Springer Book Archive