Pipeline
Three stages, end-to-end
Each stage has a focused responsibility, and together they turn a raw audio track into a stylized, expressive piano cover.
Audio → Symbolic
Lift musical content out of the source recording into a symbolic representation we can reason about.
Impose structure
Organize content into a structured form that captures phrasing, density, and rhythmic hierarchy.
Render a performance
Decode a stylized piano performance, steerable via high-level attributes like polyphony and rhythm intensity.
Demo 01
Model Comparison
Listen side-by-side: Etude variants against baselines (Music2Midi, PiCoGen2, AMT-APC) across 100 songs in four genres.
Open demoDemo 02
Interactive Style Control
Move the sliders — polyphony, rhythm intensity, note sustain — and hear how Etude's output bends to your taste in real time.
Try it liveBibTeX
@article{chen2025etude,
title = {Etude: Piano Cover Generation with a Three-Stage Approach-Extract, strucTUralize, and DEcode},
author = {Chen, Tse-Yang and Joung, Yuh-Jzer},
journal = {arXiv preprint arXiv:2509.16522},
year = {2025}
}