The Gamma MLP for Speech Phoneme Recognition

[Steve Lawrence]

The following NIPS 95 paper presents a network with multiple
independent Gamma filters which is able to find multiple time
resolutions that are optimized for prediction or classification of a
given signal. We show large improvements over traditional FIR or
TDNN(*) networks.

The paper is available from 

http://www.elec.uq.edu.au/~lawrence		- Australia
http://www.neci.nj.nec.com/homepages/lawrence	- USA

We welcome your comments


	The Gamma MLP for Speech Phoneme Recognition

	 Steve Lawrence, Ah Chung Tsoi, Andrew Back

	     Electrical and Computer Engineering
     University of Queensland, St. Lucia 4072, Australia

 		         ABSTRACT

We define a Gamma multi-layer perceptron (MLP) as an MLP with the
usual synaptic weights replaced by gamma filters (as proposed by de
Vries and Principe) and associated gain terms throughout all layers. We
derive gradient descent update equations and apply the model to the
recognition of speech phonemes. We find that both the inclusion of
gamma filters in all layers, and the inclusion of synaptic gains,
improves the performance of the Gamma MLP. We compare the Gamma MLP
with TDNN, Back-Tsoi FIR MLP, and Back-Tsoi IIR MLP architectures, and
a local approximation scheme. We find that the Gamma MLP results in a
substantial reduction in error rates.


(*) We use the term TDNN to describe an MLP with a window of delayed
inputs, not the shared weight architecture of Lang, et al.


---
Steve Lawrence +61 41 113 6686  http://www.neci.nj.nec.com/homepages/lawrence