Impact of multiple sound types on environmental sound classification

Etto L. Salomons, Henk Van Leeuwen, Paul J.M. Havinga

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

3 Citations (Scopus)
33 Downloads (Pure)

Abstract

A wireless sensor network equipped with microphones can be used for context awareness by classifying sound events in the target environment. This classification will become less accurate when more than one sound can be heard at the same time. We conduct a series of experiments in which we mix different sound types in order to see how high this influence is. We conclude, that in most cases, the classifier will become unreliable if other sounds with the same loudness are audible within a range of less than five times the distance of the main sound from the microphone.

Original languageEnglish
Title of host publication2016 IEEE Sensors - Proceedings
Place of PublicationPiscataway, NJ
PublisherIEEE
ISBN (Electronic)978-1-4799-8287-5
ISBN (Print)978-1-4799-8288-2
DOIs
Publication statusPublished - 5 Jan 2017
Event15th IEEE Sensors Conference, SENSORS 2016 - Caribe Royale, Orlando, United States
Duration: 30 Oct 20162 Nov 2016

Publication series

NameProceedings of IEEE Sensors
PublisherIEEE
Volume2016
ISSN (Print)1930-0395
ISSN (Electronic)2168-9229

Conference

Conference15th IEEE Sensors Conference, SENSORS 2016
Country/TerritoryUnited States
CityOrlando
Period30/10/162/11/16

Keywords

  • Noise
  • Sound classification
  • Wireless Sensor Networks (WSN)
  • 2023 OA procedure

Fingerprint

Dive into the research topics of 'Impact of multiple sound types on environmental sound classification'. Together they form a unique fingerprint.

Cite this