Isolated word recognition with the liquid state machine: a case study

Authors:
D. Verstraten;B. Schrauwen;D. Stroobandt;J. Van Campenhout
Affiliations:
Department of Electronics and Information Systems, Ghent University, Sint-Pietersnieuwstraat, Gent, Belgium;Department of Electronics and Information Systems, Ghent University, Sint-Pietersnieuwstraat, Gent, Belgium;Department of Electronics and Information Systems, Ghent University, Sint-Pietersnieuwstraat, Gent, Belgium;Department of Electronics and Information Systems, Ghent University, Sint-Pietersnieuwstraat, Gent, Belgium
Venue:
Information Processing Letters - Special issue on applications of spiking neural networks
Year:
2005

Citing 4
Cited 10

The nature of statistical learning theory

The nature of statistical learning theory
Real-time computing without stable states: a new framework for neural computation based on perturbations

Neural Computation
Reducing Communication for Distributed Learning in Neural Networks

ICANN '02 Proceedings of the International Conference on Artificial Neural Networks
Sphinx-4: a flexible open source framework for speech recognition

Sphinx-4: a flexible open source framework for speech recognition

Linking non-binned spike train kernels to several existing spike train metrics

Neurocomputing
2007 Special Issue: Online reservoir adaptation by intrinsic plasticity for backpropagation-decorrelation and echo state learning

Neural Networks
2007 Special Issue: An experimental unification of reservoir computing methods

Neural Networks
2008 Special Issue: Compact hardware liquid state machines on FPGA for real-time speech recognition

Neural Networks
Improving reservoirs using intrinsic plasticity

Neurocomputing
Continuous speech recognition with sparse coding

Computer Speech and Language
Pruning and regularization in reservoir computing

Neurocomputing
Improving the separability of a reservoir facilitates learning transfer

IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Accelerating event-driven simulation of spiking neurons with multiple synaptic time constants

Neural Computation
Connectivity, dynamics, and memory in reservoir computing with binary and analog neurons

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.