Abstract
We propose a new ANC system that selectively cancels only the noise signal in the mixture at a specific local position. The BSS separates the desired sound signal from the unwanted noise signal and is used as a preprocessor of the proposed ANC system. In order to enhance the performance of noise separation, we propose a teacher-forced BSS learning algorithm. The teacher signal is obtained form a loudspeaker of the ANC system. Computer simulation and experimental results show that the proposed ANC system effectively cancels only the noise signals from the mixtures with human voice.
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
Kuo, S.M., Morgan, D.R.: Active noise control systems; Algorithm and DSP Implementations. John Wiley & Sons (1996) 1–51
Yang, H.H., Amari, S.I.: Adaptive on-line learning algorithms for blind separation: Maximum entropy and minimum mutual information. Neural Computation, Vol. 9. (1997)
Lee, T.W., Bell, A., Orglmeister, R.: Blind source separation of real world signals. International Conference on Neural Network, Vol. 4. (1997) 129–2134
Comon, P. Independent component analysis, A new concept?. Signal Processing, Vol. 36. (1994) 287–314
Sohn, J.I., Lee, M. Selective attention system using active noise controller. Neurocomputing, Vol. 31. (2000) 197–204
Choi, S., Cichocki, A.: Adaptive blind separation of speech signals: Cocktail party problem. International Conference on Speech Processing (1997) 617–622
Pearlmetter, B.A., Parra, L.C.: Maximum likelihood blind source separation: A context-sensitive generalization of ICA, Neural Information Processing System (1996) 613–619
Taleb, A., Jutten, C.: Entropy optimization-application to source separation, International Conference on Artificial Neural Networks (1997) 529–534
Fiori, S.: Blind signal processing by the adaptive activation function neurons. Neural Networks, Vol. 13. (1996) 597–611
Welling, M., Weber, M.: A Constrainsed E.M. Algorithm for independent component analysis. Neural Computation, Vol. 13. (2001)
Choi, S., Cichock, A.I., Amari, S.I.: Flexible independent component analysis. The Journal of VLSI Signal Processing, Vol. 26. (2000) 25–38
Lee, T.W., Lewicki, M.S., Girolami, M., Sejnowski, T.J.: Blind source separation of more sources than mixtures using overcomplete representations. IEEE Signal Processing Letters, Vol. 4. (1999)
Bae U.M., Lee, S.Y.: Combining ICA and top-down attention for robust speech recognition. Neural Information Processing Systems, Vol. 13. (2000)
Williams, R.J., Zipser, D.: A learning algorithm for continually running fully recurrent neural network, Neural Computation, Vol. 1. (1989) 270–280
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sohn, JI., Lee, M. (2003). Selective Noise Cancellation Using Independent Component Analysis. In: Kaynak, O., Alpaydin, E., Oja, E., Xu, L. (eds) Artificial Neural Networks and Neural Information Processing — ICANN/ICONIP 2003. ICANN ICONIP 2003 2003. Lecture Notes in Computer Science, vol 2714. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44989-2_63
Download citation
DOI: https://doi.org/10.1007/3-540-44989-2_63
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40408-8
Online ISBN: 978-3-540-44989-8
eBook Packages: Springer Book Archive