Abstract
In this work, we work on the problem of sound source separation in convolutive mixtures. Particularly, we propose a method for reducing the number of filter taps while guaranteeing adequate separation performance. We recorded the mixed signals using directional microphones placed close to each other. As a result, we demonstrate that the proposed method successfully separates sources with fewer taps and better separation than conventional methods. In order to enhance the performance, we consider three main factors to prevent the reduction of number of taps: Echoes; frequency property of a directional microphone; and size of sound source. In experimental results, we found that echoes have little influence in preventing the reduction of the number of taps, but the other two factors affect the number of taps.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Lee, T.W.: Independent Component Analysis. Kuluwer Academic Publishers, Dordrecht (1998)
Mansour, A., Barros, A.K., Ohnishi, N.: Blind Separation of Sources: Methods, Assumptions and Applications. IEICE Trans. Fundamentals E83–A(8), 1498–1511 (2000)
Katayama, Y., Takeuchi, Y., Matsumoto, T., Kudo, H., Ohnishi, N., Mukai, T.: Reduction of the Number of Taps for Blind Source Separation in the Real Environment. In: Proceeding of General Conference of IEICE, p. 157 (2002) (in Japanese)
Kawamoto, M., Matsuoka, K., Ohnishi, N.: A method of blind separation for convolved non stationary signals. Neurocomputing 22, 157–171 (1998)
Matsuoka, K., Ohya, M., Kawamoto, M.: A Neural Net for Blind Separation of Nonstationary Signals. Neural Networks 8(3), 411–419 (1995)
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
Katayama, Y. et al. (2004). Closely Arranged Directional Microphone for Source Separation. 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_17
Download citation
DOI: https://doi.org/10.1007/978-3-540-30110-3_17
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