Optimizing Correlation Algorithms for Hardware-Based Transient Classification

The perfonnance of dedicated VLSI neural processing hardware depends critically on the design of the implemented algorithms. We have previously proposed an algorithm for acoustic transient classification [1]. Having implemented and demonstrated this algorithm in a mixed-mode architecture, we now investigate variants on the algorithm, using time and frequency channel differencing, input and output nonnalization, and schemes to binarize and train the template values, with the goal of achieving optimal classification perfonnance for the chosen hardware.

[1]  John J. Hopfield,et al.  Connected-digit speaker-dependent speech recognition using a neural network with time-delayed connections , 1991, IEEE Trans. Signal Process..

[2]  Gert Cauwenberghs,et al.  A mixed-signal correlator for acoustic transient classification , 1997, Proceedings of 1997 IEEE International Symposium on Circuits and Systems. Circuits and Systems in the Information Age ISCAS '97.

[3]  Kuansan Wang,et al.  Spectral shape analysis in the central auditory system , 1995, IEEE Trans. Speech Audio Process..

[4]  Gert Cauwenberghs,et al.  Bangs, Clicks, Snaps, Thuds and Whacks: An Architecture for Acoustic Transient Processing , 1996, NIPS.

[5]  Gert Cauwenberghs,et al.  A second-order log-domain bandpass filter for audio frequency applications , 1998, ISCAS '98. Proceedings of the 1998 IEEE International Symposium on Circuits and Systems (Cat. No.98CH36187).