
There is a more recent version of this eprint available. Click here to view it.
Ma, Y., Yuan, R., Li, Y. et al. (12 more authors) (Submitted: 2023) On the effectiveness of speech self-supervised learning for music. [Preprint - arXiv] (Submitted)
Abstract
Self-supervised learning (SSL) has shown promising results in various speech and natural language processing applications. However, its efficacy in music information retrieval (MIR) still remains largely unexplored. While previous SSL models pre-trained on music recordings may have been mostly closed-sourced, recent speech models such as wav2vec2.0 have shown promise in music modelling. Nevertheless, research exploring the effectiveness of applying speech SSL models to music recordings has been limited. We explore the music adaption of SSL with two distinctive speech-related models, data2vec1.0 and Hubert, and refer to them as music2vec and musicHuBERT, respectively. We train 12 SSL models with 95M parameters under various pre-training configurations and systematically evaluate the MIR task performances with 13 different MIR tasks. Our findings suggest that training with music data can generally improve performance on MIR tasks, even when models are trained using paradigms designed for speech. However, we identify the limitations of such existing speech-oriented designs, especially in modelling polyphonic information. Based on the experimental results, empirical suggestions are also given for designing future musical SSL strategies and paradigms.
Metadata
Item Type: | Preprint |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2023 The Author(s). This preprint is made available under a Creative Commons Attribution 4.0 International License. (https://creativecommons.org/licenses/by/4.0/) |
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: | 06 Jun 2024 16:25 |
Last Modified: | 28 Jun 2024 04:20 |
Status: | Submitted |
Identification Number: | 10.48550/arXiv.2307.05161 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:213151 |
Available Versions of this Item
- On the effectiveness of speech self-supervised learning for music. (deposited 06 Jun 2024 16:25) [Currently Displayed]