On the Effectiveness of Speech Self-supervised Learning for Music

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 close...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-07
Main Authors: Ma, Yinghao, Yuan, Ruibin, Li, Yizhi, Zhang, Ge, Chen, Xingran, Yin, Hanzhi, Lin, Chenghua, Benetos, Emmanouil, Ragni, Anton, Gyenge, Norbert, Liu, Ruibo, Xia, Gus, Dannenberg, Roger, Guo, Yike, Fu, Jie
Format: Article
Language:English
Subjects:
Effectiveness
Information retrieval
Modelling
Music
Natural language processing
Self-supervised learning
Speech
Training
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!