This is the latest version of this eprint.
Li, Y., Yuan, R., Zhang, G. et al. (11 more authors) (2022) LV-49: MAP-Music2Vec: A Simple and Effective Baseline for Self-Supervised Music Audio Representation Learning. In: 23rd International Society for Music Information Retrieval Conference (ISMIR 2022). 23rd International Society for Music Information Retrieval Conference (ISMIR 2022), 04-08 Dec 2022, Bengaluru, India. International Society for Music Information Retrieval (ISMIR)
Abstract
The deep learning community has witnessed an exponentially growing interest in self-supervised learning (SSL). However, it still remains unexplored how to build a framework for learning useful representations of raw music waveforms in a self-supervised manner. In this work, we design MAP-Music2Vec, a framework exploring different self-supervised learning algorithmic components and tricks for music audios. Our model achieves comparable results to the state-of-the-art (SOTA) music SSL model Jukebox, despite being significantly lightweight with less than 2% of parameters of the latter. The model will be released on Huggingface.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © F. Author, S. Author, and T. Author. Licensed under a Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/). Attribution: F. Author, S. Author, and T. Author, “MAP-Music2Vec: A Simple and Effective Baseline for Self-Supervised Music Audio Representation Learning”, in Extended Abstracts for the Late-Breaking Demo Session of the 23rd Int. Society for Music Information Retrieval Conf., Bengaluru, India, 2022. |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 07 Jun 2024 16:48 |
Last Modified: | 07 Jun 2024 16:48 |
Published Version: | https://ismir2022program.ismir.net/lbd_410.html |
Status: | Published |
Publisher: | International Society for Music Information Retrieval (ISMIR) |
Refereed: | Yes |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:213233 |
Available Versions of this Item
-
MAP-Music2Vec: a simple and effective baseline for self-supervised music audio representation learning. (deposited 07 Jun 2024 16:21)
- LV-49: MAP-Music2Vec: A Simple and Effective Baseline for Self-Supervised Music Audio Representation Learning. (deposited 07 Jun 2024 16:48) [Currently Displayed]