# Etude: Piano Cover Generation with a Three-Stage Approach -- Extract, strucTUralize, and DEcode

arXiv: https://arxiv.org/abs/2509.16522 · HTML: https://mlsanity.com/paper/2509.16522/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 26 references that are in the map.
- First posted on arXiv 20 Sep 2025.

## Builds on (most cited first, 18 of 18)

- [GPT-NeoX-20B: An Open-Source Autoregressive Language Model](https://mlsanity.com/paper/2204.06745/) (2022)
- [MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment](https://mlsanity.com/paper/1709.06298/) (2017)
- [Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphs](https://mlsanity.com/paper/2101.02402/) (2021)
- [DeepBach: a Steerable Model for Bach Chorales Generation](https://mlsanity.com/paper/1612.01010/) (2016)
- [MidiNet: A Convolutional Generative Adversarial Network for Symbolic-domain Music Generation](https://mlsanity.com/paper/1703.10847/) (2017)
- [Music FaderNets: Controllable Music Generation Based On High-Level Features via Low-Level Feature Modelling](https://mlsanity.com/paper/2007.15474/) (2020)
- [MuseMorphose: Full-Song and Fine-Grained Piano Music Style Transfer with One Transformer VAE](https://mlsanity.com/paper/2105.04090/) (2021)
- [MIDI-VAE: Modeling Dynamics and Instrumentation of Music with Applications to Style Transfer](https://mlsanity.com/paper/1809.07600/) (2018)
- [Symbolic Music Genre Transfer with CycleGAN](https://mlsanity.com/paper/1809.07575/) (2018)
- [Melody transcription via generative pre-training](https://mlsanity.com/paper/2212.01884/) (2022)
- [Automatic Piano Transcription with Hierarchical Frequency-Time Transformer](https://mlsanity.com/paper/2307.04305/) (2023)
- [Compose & Embellish: Well-Structured Piano Performance Generation via A Two-Stage Approach](https://mlsanity.com/paper/2209.08212/) (2022)
- [Beat Transformer: Demixed Beat and Downbeat Tracking with Dilated Self-Attention](https://mlsanity.com/paper/2209.07140/) (2022)
- [Pop2Piano : Pop Audio-based Piano Cover Generation](https://mlsanity.com/paper/2211.00895/) (2022)
- [Lead Sheet Generation and Arrangement by Conditional Generative Adversarial Network](https://mlsanity.com/paper/1807.11161/) (2018)
- [PiCoGen: Generate Piano Covers with a Two-stage Approach](https://mlsanity.com/paper/2407.20883/) (2024)
- [PiCoGen2: Piano cover generation with transfer learning approach and weakly aligned data](https://mlsanity.com/paper/2408.01551/) (2024)
- [AMT-APC: Automatic Piano Cover by Fine-Tuning an Automatic Music Transcription Model](https://mlsanity.com/paper/2409.14086/) (2024)

## Built on by (most cited first, 1 of 1)

- [MPEcho: A Melody and Phoneme-Aware Generative Framework for Controllable Cover Song Generation](https://mlsanity.com/paper/2607.26698/) (2026)

## Abstract (arXiv)

Piano cover generation aims to automatically transform a pop song into a piano arrangement. While numerous deep learning approaches have been proposed, existing models often fail to maintain structural consistency with the original song, likely due to the absence of beat-aware mechanisms or the difficulty of modeling complex rhythmic patterns. Rhythmic information is crucial, as it defines structural similarity (e.g., tempo, BPM) and directly impacts the overall quality of the generated music. In this paper, we introduce Etude, a three-stage architecture consisting of Extract, strucTUralize, and DEcode stages. By pre-extracting rhythmic information and applying a novel, simplified REMI-based tokenization, our model produces covers that preserve proper song structure, enhance fluency and musical dynamics, and support highly controllable generation through style injection. Subjective evaluations with human listeners show that Etude substantially outperforms prior models, achieving a quality level comparable to that of human composers.