Neuro-inspired speech recognition with recurrent spiking neurons

Arfan Ghani, T. M. McGinnity, Liam Maguire, Jim Harkin

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

20 Citations (Scopus)


This paper investigates the potential of recurrent spiking neurons for classification problems. It presents a hybrid approach based on the paradigm of Reservoir Computing. The practical applications based on recurrent spiking neurons are limited due to their non-trivial learning algorithms. In the paradigm of Reservoir Computing, instead of training the whole recurrent network only the output layer (known as readout neurons) are trained. These recurrent neural networks are termed as microcircuits which are viewed as basic computational units in cortical computation. These microcircuits are connected as columns which are linked with other neighboring columns in cortical areas. These columns read out information from each other and can serve both as reservoir and readout. The design space for this paradigm is split into three domains; front end, reservoir, and back end. This work contributes to the identification of suitable front and back end processing techniques along with stable and compact reservoir dynamics, which provides a reliable framework for classification related problems.
Original languageEnglish
Title of host publicationNeuro-inspired speech recognition with recurrent spiking neurons
PublisherSpringer Verlag
Number of pages10
ISBN (Electronic)978-3-540-87536-9
ISBN (Print)978-3-540-87535-2
Publication statusPublished - 2008
Event18th International Conference on Artificial Neural Networks - Prague, Czech Republic
Duration: 3 Sep 20086 Sep 2008

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743


Conference18th International Conference on Artificial Neural Networks
Abbreviated titleICANN 2008
Country/TerritoryCzech Republic


  • Reservoir computing
  • liquid state machine
  • hybrid neuro inspired computing
  • speech recognition


Dive into the research topics of 'Neuro-inspired speech recognition with recurrent spiking neurons'. Together they form a unique fingerprint.

Cite this