A Spiking Network that Learns to Extract Spike Signatures from Speech Signals
Preprint
Abstract
Spiking neural networks (SNNs) with adaptive synapses reflect core properties of biological neural networks. Speech recognition, as an application involving audio coding and dynamic learning, provides a good test problem to study SNN functionality. We present a novel and efficient method that learns to convert a speech signal into a spike train signature. The signature is distinguishable from signatures for other speech signals, representing different words, thereby enabling digit recognition and discrimination in devices that use only spiking neurons. The method uses a small SNN consisting of Izhikevich neurons equipped with spike timing dependent plasticity (STDP) and biologically realistic synapses. This approach introduces an efficient, fast, and multi-speaker strategy without error-feedback training, although it does require supervised training. The new simulation results produce discriminative spike train patterns for spoken digits in which highly correlated spike trains belong to the same category and low correlated patterns belong to different categories. The signatures can be used as a set of feature maps for classification. Our experiments compare two simple classifiers for spoken digit recognition in both clean and noisy environments.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- An online supervised learning method for spiking neural networks with adaptive structureNeurocomputing, 2014
- Dynamic evolving spiking neural networks for on-line spatio- and spectro-temporal pattern recognitionNeural Networks, 2013
- Evolving spiking neural networks for audiovisual information processingNeural Networks, 2010
- Reservoir computing approaches to recurrent neural network trainingComputer Science Review, 2009
- Fast and adaptive network of spiking neurons for multi-view visual pattern recognitionNeurocomputing, 2008
- Automatic speech recognition using a predictive echo state network classifierNeural Networks, 2007
- Isolated word recognition with the Liquid State Machine: a case studyInformation Processing Letters, 2005
- Simple model of spiking neuronsIEEE Transactions on Neural Networks, 2003
- Speech recognition with spiking neurons and dynamic synapses: a model motivated by the human auditory pathwayNeurocomputing, 2002
- Temporal clustering with spiking neurons and dynamic synapses: towards technological applicationsNeural Networks, 2001