Ajou University repository

Towards Proper Contrastive Self-Supervised Learning Strategies for Music Audio Representationoa mark
Citations

SCOPUS

0

Citation Export

Publication Year
2022-01-01
Journal
Proceedings - IEEE International Conference on Multimedia and Expo
Publisher
IEEE Computer Society
Citation
Proceedings - IEEE International Conference on Multimedia and Expo, Vol.2022-July
Keyword
Contrastive LearningMusic Audio RepresentationSelf-supervised Learning
Mesh Keyword
Audio representationContrastive learningDown-streamLearning schemesLearning strategyMusic audio representationMusic information retrievalMusic perceptionResearch goalsSelf-supervised learning
All Science Classification Codes (ASJC)
Computer Networks and CommunicationsComputer Science Applications
Abstract
The common research goal of self-supervised learning is to extract a general representation which an arbitrary downstream task would benefit from. In this work, we investigate music audio representation learned from different contrastive self-supervised learning schemes and empirically evaluate the embedded vectors on various music information retrieval (MIR) tasks where different levels of the music perception are concerned. We analyze the results to discuss the proper direction of contrastive learning strategies for different MIR tasks. We show that these representations convey a comprehensive information about the auditory characteristics of music in general, although each of the self-supervision strategies has its own effectiveness in certain aspect of information.
Language
eng
URI
https://aurora.ajou.ac.kr/handle/2018.oak/36808
https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85137677423&origin=inward
DOI
https://doi.org/10.1109/icme52920.2022.9859799
Journal URL
http://ieeexplore.ieee.org/xpl/conferences.jsp
Type
Conference
Show full item record

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Cho, Hyunsouk Image
Cho, Hyunsouk조현석
Department of Software and Computer Engineering
Read More

Total Views & Downloads

File Download

  • There are no files associated with this item.