MARBLE: Music Audio Representation Benchmark for Universal Evaluation
Abstract
In the era of extensive intersection between art and Artificial Intelligence (AI), such as image generation and fiction co-creation, AI for music remains relatively nascent, particularly in music understanding. This is evident in the limited work on deep music representations, the scarcity of large-scale datasets, and the absence of a universal and community-driven benchmark. To address this issue, we introduce the Music Audio Representation Benchmark for universaL Evaluation, termed MARBLE. It aims to provide a benchmark for various Music Information Retrieval (MIR) tasks by defining a comprehensive taxonomy with four hierarchy levels, including acoustic, performance, score, and high-level description. We then establish a unified protocol based on 14 tasks on 8 public-available datasets, providing a fair and standard assessment of representations of all open-sourced pre-trained models developed on music recordings as baselines. Besides, MARBLE offers an easy-to-use, extendable, and reproducible suite for the community, with a clear statement on copyright issues on datasets. Results suggest recently proposed large-scale pre-trained musical language models perform the best in most tasks, with room for further improvement. The leaderboard and toolkit repository are published at https://marble-bm.shef.ac.uk to promote future music AI research.
Cite
@article{arxiv.2306.10548,
title = {MARBLE: Music Audio Representation Benchmark for Universal Evaluation},
author = {Ruibin Yuan and Yinghao Ma and Yizhi Li and Ge Zhang and Xingran Chen and Hanzhi Yin and Le Zhuo and Yiqi Liu and Jiawen Huang and Zeyue Tian and Binyue Deng and Ningzhi Wang and Chenghua Lin and Emmanouil Benetos and Anton Ragni and Norbert Gyenge and Roger Dannenberg and Wenhu Chen and Gus Xia and Wei Xue and Si Liu and Shi Wang and Ruibo Liu and Yike Guo and Jie Fu},
journal= {arXiv preprint arXiv:2306.10548},
year = {2023}
}
Comments
camera-ready version for NeurIPS 2023