# Disentangling Score Content and Performance Style for Joint Piano Rendering and Transcription

arXiv: https://arxiv.org/abs/2509.23878 · HTML: https://mlsanity.com/paper/2509.23878/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 38 of its 69 references that are in the map.
- First posted on arXiv 28 Sep 2025.

## Builds on (most cited first, 30 of 38)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets](https://mlsanity.com/paper/1606.03657/) (2016)
- [Disentangled Representation Learning](https://mlsanity.com/paper/2211.11695/) (2022)
- [Onsets and Frames: Dual-Objective Piano Transcription](https://mlsanity.com/paper/1710.11153/) (2017)
- [Learning Disentangled Joint Continuous and Discrete Representations](https://mlsanity.com/paper/1804.00104/) (2018)
- [High-resolution Piano Transcription with Pedals by Regressing Onset and Offset Times](https://mlsanity.com/paper/2010.01815/) (2020)
- [Generating Sentences from Disentangled Syntactic and Semantic Spaces](https://mlsanity.com/paper/1907.05789/) (2019)
- [Posterior Collapse and Latent Variable Non-identifiability](https://mlsanity.com/paper/2301.00537/) (2023)
- [Improving Disentangled Text Representation Learning with Information-Theoretic Guidance](https://mlsanity.com/paper/2006.00693/) (2020)
- [Sequence-to-Sequence Piano Transcription with Transformers](https://mlsanity.com/paper/2107.09142/) (2021)
- [Music FaderNets: Controllable Music Generation Based On High-Level Features via Low-Level Feature Modelling](https://mlsanity.com/paper/2007.15474/) (2020)
- [Almost Unsupervised Text to Speech and Automatic Speech Recognition](https://mlsanity.com/paper/1905.06791/) (2019)
- [Learning Interpretable Representation for Controllable Polyphonic Music Generation](https://mlsanity.com/paper/2008.07122/) (2020)
- [Deep Music Analogy Via Latent Representation Disentanglement](https://mlsanity.com/paper/1906.03626/) (2019)
- [miditok: A Python package for MIDI file tokenization](https://mlsanity.com/paper/2310.17202/) (2023)
- [Automatic Piano Transcription with Hierarchical Frequency-Time Transformer](https://mlsanity.com/paper/2307.04305/) (2023)
- [Partitura: A Python Package for Symbolic Music Processing](https://mlsanity.com/paper/2206.01071/) (2022)
- [Adversarial Learning for Improved Onsets and Frames Music Transcription](https://mlsanity.com/paper/1906.08512/) (2019)
- [A holistic approach to polyphonic music transcription with neural networks](https://mlsanity.com/paper/1910.12086/) (2019)
- [Non-Local Musical Statistics as Guides for Audio-to-Score Piano Transcription](https://mlsanity.com/paper/2008.12710/) (2020)
- [DExter: Learning and Controlling Performance Expression with Diffusion Models](https://mlsanity.com/paper/2406.14850/) (2024)
- [Structured Multi-Track Accompaniment Arrangement via Style Prior Modelling](https://mlsanity.com/paper/2310.16334/) (2023)

## Abstract (arXiv)

Expressive performance rendering (EPR) and automatic piano transcription (APT) are fundamental yet inverse tasks in music information retrieval: EPR generates expressive performances from symbolic scores, while APT recovers scores from performances. Despite their dual nature, prior work has addressed them independently. In this paper we propose a unified framework that jointly models EPR and APT by disentangling note-level score content and global performance style representations from both paired and unpaired data. Our framework is built on a transformer-based sequence-to-sequence architecture and is trained using only sequence-aligned data, without requiring fine-grained note-level alignment. To automate the rendering process while ensuring stylistic compatibility with the score, we introduce an independent diffusion-based performance style recommendation module that generates style embeddings directly from score content. This modular component supports both style transfer and flexible rendering across a range of expressive styles. Experimental results from both objective and subjective evaluations demonstrate that our framework achieves competitive performance on EPR and APT tasks, while enabling effective content-style disentanglement, reliable style transfer, and stylistically appropriate rendering. Demos are available at https://jointpianist.github.io/epr-apt/