Isolated word recognition with the Liquid State Machine: a case study

The Liquid State Machine (LSM) is a recently developed computational model with interesting properties. It can be used for pattern classification, function approximation and other complex tasks. Contrary to most common computational models, the LSM does not require information to be stored in some stable state of the system: the inherent dynamics of the system are used by a memoryless readout function to compute the output. In this paper we present a case study of the performance of the Liquid State Machine based on a recurrent spiking neural network by applying it to a well known and well studied problem: speech recognition of isolated digits. We evaluate different ways of coding the speech into spike trains. In its optimal configuration, the performance of the LSM approximates that of a state-of-the-art recognition system. Another interesting conclusion is the fact that the biologically most realistic encoding performs far better than more conventional methods.

[1]  Robert A. Legenstein,et al.  At the Edge of Chaos: Real-time Computations and Self-Organized Criticality in Recurrent Neural Networks , 2004, NIPS.

[2]  Henry Markram,et al.  Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations , 2002, Neural Computation.

[3]  J J Hopfield,et al.  What is a moment? "Cortical" sensory integration over a brief interval. , 2000, Proceedings of the National Academy of Sciences of the United States of America.

[4]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[5]  Henry Markram,et al.  On the Computational Power of Recurrent Circuits of Spiking Neurons , 2002, Electron. Colloquium Comput. Complex..

[6]  Jürgen Schmidhuber,et al.  Biologically Plausible Speech Recognition with LSTM Neural Nets , 2004, BioADIT.

[7]  D. B. Davis,et al.  Sun Microsystems Inc. , 1993 .

[8]  Henry Markram,et al.  On the computational power of circuits of spiking neurons , 2004, J. Comput. Syst. Sci..

[9]  J.J. Steil,et al.  Backpropagation-decorrelation: online recurrent learning with O(N) complexity , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[10]  Richard F. Lyon,et al.  A computational model of filtering, detection, and compression in the cochlea , 1982, ICASSP.

[11]  Malcolm Slaney,et al.  Lyon's Cochlear Model , 1997 .

[12]  Henry Markram,et al.  A Model for Real-Time Computation in Generic Neural Microcircuits , 2002, NIPS.

[13]  S. Chakrabartty,et al.  Analog auditory perception model for robust speech recognition , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[14]  Peter Auer,et al.  Reducing Communication for Distributed Learning in Neural Networks , 2002, ICANN.

[15]  Paul Lamere,et al.  Sphinx-4: a flexible open source framework for speech recognition , 2004 .

[16]  J P Martens,et al.  Pitch and voiced/unvoiced determination with an auditory model. , 1992, The Journal of the Acoustical Society of America.

[17]  Henry Markram,et al.  Computer models and analysis tools for neural microcircuits , 2003 .

[18]  Herbert Jaeger,et al.  The''echo state''approach to analysing and training recurrent neural networks , 2001 .

[19]  Chrisantha Fernando,et al.  Pattern Recognition in a Bucket , 2003, ECAL.