Abstract
A new algorithm is presented for efficient implementation of multiple FIR filters in real-time applications. We introduce an analogy between the multiple FIR filters and linear feed-forward networks, and show how the FIR filters with any frequency characteristics may be designed by a learning algorithm of the network with proper choice of training patterns. Starting from a fully-connected feed-forward architecture, more efficient network architectures may be obtainable by pruning connection weights with minor contributions. For demonstration we design feed-forward networks for 16 bandpass cochlear filters with much less connection weights and moderate performance degradation.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
D.S. Kim, S.Y. Lee, R.M. Kil and X. Zhu, “Feature extraction based on auditory representations for robust speech recognition,” Electronics Letters, Vol. 33, pp. 15–16, 1997.
O. Ghitza, “Auditory models and human performances in tasks related to speech coding and speech recognition,” IEEE Transactions on Speech and Audio Processing, Vol. 2, pp. 115–132, 1994.
N. Maeda, “Transversal filters with non-uniform tap spacing,” IEEE Transactions on Circuits and Systems, Vol. CAS-27, pp. 1–11, 1980.
Y.C. Lim and S.R. Parker, “FIR filter design over a discrete power-of-two coefficient space,” IEEE Transactions on Acoust., Speech and Signal Processing, Vol. 31, pp. 583–591, 1983.
P.J. Werbos, “Backpropagation through time: What it does and how to do it,” Proceedings of the IEEE, Vol. 78, pp. 1550–1560, 1990.
Reed, “Pruning algorithms - A survey,” IEEE Transactions on Neural Networks, Vol. 4, pp. 740–747, 1993.
E.D. Karnin, “A simple procedure for pruning backpropagation trained neural networks,” IEEE Trans. Neural Networks, Vol. 1, pp. 239–242, 1990.
J.M. Kates, “A time-domain digital cochlear model,” IEEE Trans. Signal Processing, Vol. 39, pp. 2593–2597, 1991.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Ahn, KH., Choi, Y.K. & Lee, SY. Pruned Feed-forward Networks for Efficient Implementation of Multiple FIR Filters with Arbitrary Frequency Responses. Neural Processing Letters 8, 221–227 (1998). https://doi.org/10.1023/A:1009625700734
Issue Date:
DOI: https://doi.org/10.1023/A:1009625700734