A Traditional Approach to Symbolic Piano Continuation
Sound
2025-09-17 v1 Machine Learning
Multimedia
Audio and Speech Processing
Abstract
We present a traditional approach to symbolic piano music continuation for the MIREX 2025 Symbolic Music Generation challenge. While computational music generation has recently focused on developing large foundation models with sophisticated architectural modifications, we argue that simpler approaches remain more effective for constrained, single-instrument tasks. We thus return to a simple, unaugmented next-token-prediction objective on tokenized raw MIDI, aiming to outperform large foundation models by using better data and better fundamentals. We release model weights and code at https://github.com/christianazinn/mirex2025.
Cite
@article{arxiv.2509.12267,
title = {A Traditional Approach to Symbolic Piano Continuation},
author = {Christian Zhou-Zheng and John Backsund and Dun Li Chan and Alex Coventry and Avid Eslami and Jyotin Goel and Xingwen Han and Danysh Soomro and Galen Wei},
journal= {arXiv preprint arXiv:2509.12267},
year = {2025}
}
Comments
3 pages, extended abstract, MIREX session at ISMIR 2025 LBD