Abstract
In this paper, a new frequency-domain normalized MBD algorithm is presented for separating convolutive mixtures of acoustical sources. The proposed algorithm uses unidirectional unmixing filters to avoid backward filtering in gradient terms. The gradient terms are then normalized in the frequency domain. As a result, separation and convergence performances are improved, while whitening effect is relieved greatly. Simulation results with real world recordings demonstrate superior performances of the proposed algorithm.
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
Amari, S.I., Douglas, S.C., Cichocki, A., Yang, H.H.: Novel on-line adaptive learning algorithms for blind deconvolution using the natural gradient approach. In: Proc. IEEE 11th IFAC Symposium on System Identification, SYSID 1997, Kitakyushu, Japan, pp. 1057–1062 (1997)
Lee, T.W., Bell, A., Orglmeister, R.: Blind source separation of real world signals. In: Proc. IEEE Int. Conf. Neural Networks, Houston, June 1997, pp. 2129–2135 (1997)
Amari, S.I., Chen, T.P., Cichocki, A.: Nonholonomic orthogonal learning algorithms for blind source separation. Neural Computation 12, 1463–1484 (2000)
Sun, X., Douglas, S.: A natural gradient convolutive blind source separation algorithm for speech mixtures. In: Proc. Int. Workshop on Independent Component Analysis and Signal Separation (ICA 2001), San Diego, California, pp. 59–64 (2001)
Ferrara, E.R.: Fast implmentation of LMS adaptive filters. IEEE Trans. on Acoustics Speech and Signal Processing ASSP–28, 474–475 (1980)
Haykin, S.: Adaptive Filter Theory, 4th edn. Prentice-Hall, Englewood Cliffs (2002)
Na, K., Kang, S., K.L., Chae, S.: Frequency-domain implementation of block adaptive filters for ica-based multichannel blind deconvolution. In: Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, ICASSP 1999 (1999)
Joho, M., Schniter, P.: Frequency domain realization of a multichannel blind deconvolution algorithm based on the natural gradient. In: Proc. Int. Workshop on Independent Component Analysis and Signal Separation, ICA 2003 (2003)
Douglas, S., Amari, A.C., Quasi-newton, S.: filtered-regressor algorithms for adaptive equalization and deconvolution. In: Proc. IEEEWorkshop on Signal Processing Advances in Wireless Communications, Paris, France, pp. 109–112 (1997)
Zhang, L., Cichocki, A., Amari, S.: Geometrical structures of FIR manifold and their application to multichannel blind deconvoluution. In: Proc. IEEE Workshop on Neural Networks for Signal Processing (NNSP 1999), Madison, Wisconsin, pp. 303–312 (1999)
Cichocki, A., Amari, S.I.: Adaptive Blind Signal and Image Processing: Learning algorithms and applications. Wiley, Chichester (2002)
Fancourt, C., Parra, L.: Coherence function as a criterion for blind source separation. In: IEEE International Workshop on Neural Networks and Signal Processing 2001, pp. 303–312 (2001)
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
Nam, S.H., Beack, S. (2004). A Frequency-Domain Normalized Multichannel Blind Deconvolution Algorithm for Acoustical Signals. 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_67
Download citation
DOI: https://doi.org/10.1007/978-3-540-30110-3_67
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