Play It Back: Iterative Attention For Audio Recognition

Alexandros G Stergiou, Dima Damen

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

Abstract

A key function of auditory cognition is the association of characteristic sounds with their corresponding semantics over time. Humans attempting to discriminate between fine grained audio categories, often replay the same discriminative sounds to increase their prediction confidence. We propose an end-to-end attention-based architecture that through selective repetition attends over the most discriminative sounds across the audio sequence. Our model initially uses the full audio sequence and iteratively refines the temporal segments replayed based on slot attention. At each playback, the selected segments are replayed using a smaller hop length which represents higher resolution features within these segments. We show that our method can consistently achieve state-of-the art performance across three audio-classification benchmarks: Audio Set, VGG-Sound, and EPIC-KITCHENS-100.
Original languageEnglish
Title of host publicationICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages5
ISBN (Electronic)9781728163277
ISBN (Print)9781728163284
DOIs
Publication statusPublished - 5 May 2023
EventIEEE International Conference on Acoustics, Speech and Signal Processing - Rhodes, Greece
Duration: 2 Jun 2023 → …
https://2023.ieeeicassp.org/

Publication series

NameIEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
PublisherIEEE
ISSN (Print)1520-6149
ISSN (Electronic)2379-190X

Conference

ConferenceIEEE International Conference on Acoustics, Speech and Signal Processing
Abbreviated titleICASSP
Country/TerritoryGreece
CityRhodes
Period2/06/23 → …
Internet address

Fingerprint

Dive into the research topics of 'Play It Back: Iterative Attention For Audio Recognition'. Together they form a unique fingerprint.

Cite this