A spiking neural network model for sound recognition

Research output: Research - peer-review32_Refereed conference paper (with ISBN/ISSN)

View graph of relations


Related Research Unit(s)


Original languageEnglish
Title of host publicationCognitive Systems and Signal Processing
PublisherSpringer, Singapore
ISBN (Electronic)978-981-10-5230-9
ISBN (Print)978-981-10-5229-3
StateE-pub ahead of print - 11 Jul 2017

Publication series

NameCommunications in Computer and Information Science
ISSN (Print)1865-0929


TitleThird International Conference on Cognitive Systems and Information Processing ( ICCSIP 2016)
Period19 - 23 November 2016


This paper presents a spiking neural network (SNN) model of leaky integrate-and-fire (LIF) neurons for sound recognition, which provides a way to simulate the brain processes. Neural coding and learning by processing external stimulus and recognizing different patterns are important parts in SNN model. Based on features extracted from the time-frequency representation of sound, we present a time-frequency encoding method which can retain the adequate information of original sound and generate spikes from represented features. The generated spikes are further used to train the SNN model with plausible supervised synaptic learning rule to efficiently perform various classification tasks. By testing the encoding and learning methods in RWCP database, experiments demonstrate that the proposed SNN model can achieve the robust performance for sound recognition across a variety of noise conditions.

Research Area(s)

  • Time-frequency Information, Sound recognition, Spiking neural network, Temporal coding, Temporal network

Citation Format(s)

A spiking neural network model for sound recognition. / Xiao, Rong; Yan, Rui; Tang, Huajin; Tan, Kay Chen.

Cognitive Systems and Signal Processing. Vol. 710 Springer, Singapore, 2017. p. 584-594 (Communications in Computer and Information Science; Vol. 710).

Research output: Research - peer-review32_Refereed conference paper (with ISBN/ISSN)