Skip to main navigation Skip to search Skip to main content

Large-Scale Pretrained Model for Self-Supervised Music Audio Representation Learning

  • Yizhi Li
  • , Ruibin Yuan
  • , Ge Zhang
  • , Yinghao Ma
  • , Chenghua Lin
  • , Xingran Chen
  • , Anton Ragni
  • , Hanzhi Yin
  • , Zhijie Hu
  • , Haoyu He
  • , Emmanouil Benetos
  • , Norbert Gyenge
  • , Ruibo Liu
  • , Jie Fu

Research output: Other contributionpeer-review

Abstract

Self-supervised learning technique is an under-explored topic for music audio due to the challenge of designing an appropriate training paradigm. We hence propose MAP-MERT, a large-scale music audio pre-trained model for general music understanding. We achieve performance that is comparable to the state-of-the-art pre-trained model Jukebox using less than 2% of parameters.
Original languageEnglish
PublisherDigital Music Research Network
Number of pages1
Publication statusPublished - 22 Dec 2022

Publication series

NameDigital Music Research Network

Keywords

  • Self-supervised learning
  • Music representation learning
  • Music information retrieval

Fingerprint

Dive into the research topics of 'Large-Scale Pretrained Model for Self-Supervised Music Audio Representation Learning'. Together they form a unique fingerprint.

Cite this