A spiking neural network model for sound recognition

Rong Xiao, Rui Yan, Huajin Tang, Kay Chen Tan

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

23 Citations (Scopus)

Abstract

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.

Original languageEnglish
Title of host publicationCognitive Systems and Signal Processing - 3rd International Conference, ICCSIP 2016, Revised Selected Papers
EditorsFuchun Sun, Huaping Liu, Dewen Hu
PublisherSpringer-Verlag
Pages584-594
Number of pages11
ISBN (Print)9789811052293
DOIs
Publication statusPublished - 2017
Externally publishedYes
Event3rd International Conference on Cognitive Systems and Information Processing, ICCSIP 2016 - Beijing, China
Duration: 19 Nov 201623 Nov 2016

Publication series

NameCommunications in Computer and Information Science
Volume710
ISSN (Print)1865-0929

Conference

Conference3rd International Conference on Cognitive Systems and Information Processing, ICCSIP 2016
Country/TerritoryChina
CityBeijing
Period19/11/1623/11/16

Keywords

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

ASJC Scopus subject areas

  • General Computer Science
  • General Mathematics

Fingerprint

Dive into the research topics of 'A spiking neural network model for sound recognition'. Together they form a unique fingerprint.

Cite this