MusPy: A Toolkit for Symbolic Music Generation
Abstract
In this paper, we present MusPy, an open source Python library for symbolic music generation. MusPy provides easy-to-use tools for essential components in a music generation system, including dataset management, data I/O, data preprocessing and model evaluation. In order to showcase its potential, we present statistical analysis of the eleven datasets currently supported by MusPy. Moreover, we conduct a cross-dataset generalizability experiment by training an autoregressive model on each dataset and measuring held-out likelihood on the others---a process which is made easier by MusPy's dataset management system. The results provide a map of domain overlap between various commonly used datasets and show that some datasets contain more representative cross-genre samples than others. Along with the dataset analysis, these results might serve as a guide for choosing datasets in future research. Source code and documentation are available at https://github.com/salu133445/muspy .
Cite
@article{arxiv.2008.01951,
title = {MusPy: A Toolkit for Symbolic Music Generation},
author = {Hao-Wen Dong and Ke Chen and Julian McAuley and Taylor Berg-Kirkpatrick},
journal= {arXiv preprint arXiv:2008.01951},
year = {2020}
}
Comments
Accepted by International Society for Music Information Retrieval Conference (ISMIR), 2020