Selective attention system using new active noise controller

Abstract A new active noise control system is proposed that can selectively cancel a particular noise signal from a mixture. Blind source separation of the desired signal from the other noise signals is performed by a dynamic recurrent neutral network that is used as a preprocessor of this active noise control system. The proposed active noise control system then adaptively generates an anti-noise signal to specifically remove only the separated noise signal. Computer experimental results show that the proposed scheme can be effective in the construction of a selective attention system.

[1]  Dirk Van Compernolle,et al.  On the use of decorrelation in scalar signal separation , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

[2]  Sen M. Kuo,et al.  Active Noise Control Systems: Algorithms and DSP Implementations , 1996 .

[3]  Shun-ichi Amari,et al.  Adaptive Online Learning Algorithms for Blind Separation: Maximum Entropy and Minimum Mutual Information , 1997, Neural Computation.

[4]  Terrence J. Sejnowski,et al.  An Information-Maximization Approach to Blind Separation and Blind Deconvolution , 1995, Neural Computation.

[5]  Reinhold Orglmeister,et al.  Blind source separation of real world signals , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[6]  Seungjin Choi,et al.  Adaptive Blind Separation of Speech Signals: Cocktail Party Problem , 1997 .

[7]  Stephen J. Elliott,et al.  The behavior of a multiple channel active control system , 1992, IEEE Trans. Signal Process..

[8]  Kari Torkkola,et al.  Blind separation of delayed sources based on information maximization , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

[9]  Yannick Deville,et al.  Optimization of the asymptotic performance of time-domain convolutive source separation algorithms , 1997, ESANN.

[10]  Stephen J. Elliott,et al.  A multiple error LMS algorithm and its application to the active control of sound and vibration , 1987, IEEE Trans. Acoust. Speech Signal Process..