MusicScore: A Dataset for Music Score Modeling and Generation
Yuheng Lin, Zheqi Dai, Qiuqiang Kong

TL;DR
MusicScore is a large-scale dataset of music score images with rich metadata, designed to facilitate research in music score modeling and generation, and includes a diffusion-based score generation system as a benchmark.
Contribution
The paper introduces MusicScore, a comprehensive large-scale dataset for music score modeling and generation, filling a gap in existing resources and enabling new research directions.
Findings
MusicScore includes 400, 14k, and 200k image-text pairs at different scales.
A diffusion-based score generation system is developed and benchmarked using the dataset.
MusicScore is publicly available for research use.
Abstract
Music scores are written representations of music and contain rich information about musical components. The visual information on music scores includes notes, rests, staff lines, clefs, dynamics, and articulations. This visual information in music scores contains more semantic information than audio and symbolic representations of music. Previous music score datasets have limited sizes and are mainly designed for optical music recognition (OMR). There is a lack of research on creating a large-scale benchmark dataset for music modeling and generation. In this work, we propose MusicScore, a large-scale music score dataset collected and processed from the International Music Score Library Project (IMSLP). MusicScore consists of image-text pairs, where the image is a page of a music score and the text is the metadata of the music. The metadata of MusicScore is extracted from the general…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMusic and Audio Processing · Music Technology and Sound Studies · Diverse Musicological Studies
