A new version of dynamic synapse neural network (DSNN) has been applied to recognize noisy raw waveforms of words spoken by multiple speakers. The new architecture of DSNN is based on the original DSNN and a wavelet filter bank, which decomposes speech signals in multiresolution frequency bands. In this study we applied a genetic algorithm (GA) learning method to optimize the neural network. The advantage of the GA method is that it facilitates finding of a semi-optimal parameter set in the search space domain. In order to speed up the training time of the network, a new discrete time implementation of the DSNN was introduced based on the impulse invariant transformation. The network was tested for difficult discrimination conditions.
[1]
J S Liaw,et al.
Dynamic synapse: A new concept of neural representation and computation
,
1996,
Hippocampus.
[2]
D. E. Goldberg,et al.
Genetic Algorithms in Search
,
1989
.
[3]
Theodore W. Berger,et al.
Dynamic synapse: Harnessing the computing power of synaptic dynamics
,
1999,
Neurocomputing.
[4]
Stéphane Mallat,et al.
A Theory for Multiresolution Signal Decomposition: The Wavelet Representation
,
1989,
IEEE Trans. Pattern Anal. Mach. Intell..
[5]
David E. Goldberg,et al.
Genetic Algorithms in Search Optimization and Machine Learning
,
1988
.