Anomaly Localization in Audio via Feature Pyramid Matching

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

Abstract

Sound anomaly detection is a specific task that aims
at identifying unusual or abnormal sounds within audio data.
These sounds could be caused by different factors, such as
background noise, equipment malfunctions, or unexpected events.
Anomaly detection in sound is a well-studied topic, with a lot of
research being done in the field. Anomaly localization refers to
the process of identifying the specific location or region within
a sample where an anomaly (or outlier) occurs. When applied
to audio signals, anomaly localization can involve analyzing the
spectral content of the sound to detect regions that deviate from
the typical or expected pattern.
In this study, we present a simple yet effective model based
on the Student-Teacher Feature Pyramid Matching Method for
locating anomalies in audio data. Utilizing the MIMII dataset by
augmenting it with synthetic anomalies, we evaluate the method’s
accuracy. Our results demonstrate that the proposed model
can accurately locate artificially created anomalies within the
spectrograms, both in terms of time and frequency. This approach
offers a promising solution for identifying and determining the
precise location of anomalies in various audio applications.
Original languageEnglish
Title of host publication2023 IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC)
Number of pages6
PublisherIEEE
Publication dateAug 2023
Pages286-291
ISBN (Electronic)979-8-3503-2697-0
DOIs
Publication statusPublished - Aug 2023
MoE publication typeA4 Article in conference proceedings
EventAnnual Computers, Software, and Applications Conference - Torino, Italy
Duration: 26 Jun 202330 Jun 2023
Conference number: 47

Fields of Science

  • 113 Computer and information sciences
  • Anomaly detection (AD)
  • Anomaly localization (AL)
  • Audio processing
  • Deep learning
  • Machine learning

Cite this