Environment Sound Classification (ESC) with Choquet Integral Fusion

Yilin Wang, Timothy C. Havens, Andrew Barnard

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

The Choquet integral (ChI) plays an important role in the area of aggregating sensors and information. One of the defining advantages of the ChI, compared to other types of aggregations, is that it takes into account how variables interact with one another, which it does by means of what is called a capacity or fuzzy measure. The fuzzy measure captures the relative value, or worth, of different subsets of information sources taken together to make an inference. For data-driven problems, i.e., machine learning, the fuzzy measure comprises the parameters learned for using the ChI. In this work, we apply data-driven ChI decision-level fusion to the problem of classifying sound events from clips of audio. Three benchmark sound classification data sets are utilized: ESC-10, ESC-50, and UrbanSound8K. Six leading classification algorithms-deep networks and transformers-are used as the decision sources. The ChI fusion shows significant gains in accuracy for all three benchmarks.

Original languageEnglish (US)
Title of host publication2021 IEEE Symposium Series on Computational Intelligence, SSCI 2021 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728190488
DOIs
StatePublished - 2021
Event2021 IEEE Symposium Series on Computational Intelligence, SSCI 2021 - Orlando, United States
Duration: Dec 5 2021Dec 7 2021

Publication series

Name2021 IEEE Symposium Series on Computational Intelligence, SSCI 2021 - Proceedings

Conference

Conference2021 IEEE Symposium Series on Computational Intelligence, SSCI 2021
Country/TerritoryUnited States
CityOrlando
Period12/5/2112/7/21

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Science Applications
  • Decision Sciences (miscellaneous)
  • Safety, Risk, Reliability and Quality
  • Control and Optimization

Fingerprint

Dive into the research topics of 'Environment Sound Classification (ESC) with Choquet Integral Fusion'. Together they form a unique fingerprint.

Cite this