# Learning Jazz Pianist Style with Cross-Attention Conditioning

arXiv: https://arxiv.org/abs/2610.02918 · HTML: https://mlsanity.com/paper/2610.02918/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 25 references that are in the map.
- First posted on arXiv 2 Oct 2026.

## Builds on (most cited first, 12 of 12)

- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2308.06721/) (2023)
- [Generating Sentences from a Continuous Space](https://mlsanity.com/paper/1511.06349/) (2015)
- [Music Transformer](https://mlsanity.com/paper/1809.04281/) (2018)
- [Classification Accuracy Score for Conditional Generative Models](https://mlsanity.com/paper/1905.10887/) (2019)
- [This Time with Feeling: Learning Expressive Musical Performance](https://mlsanity.com/paper/1808.03715/) (2018)
- [MuseMorphose: Full-Song and Fine-Grained Piano Music Style Transfer with One Transformer VAE](https://mlsanity.com/paper/2105.04090/) (2021)
- [Composer Style-specific Symbolic Music Generation Using Vector Quantized Discrete Diffusion Models](https://mlsanity.com/paper/2310.14044/) (2023)
- [Scaling Self-Supervised Representation Learning for Symbolic Piano Performance](https://mlsanity.com/paper/2506.23869/) (2025)
- [Reconstructing Human Expressiveness in Piano Performances with a Transformer Network](https://mlsanity.com/paper/2306.06040/) (2023)
- [Training Discriminative Models to Evaluate Generative Ones](https://mlsanity.com/paper/1806.10840/) (2018)

## Abstract (arXiv)

Jazz pianists develop distinctive traits that experienced listeners can often identify within seconds, yet the features underlying this recognition resist formal description. We study jazz pianist style through the lens of a pretrained symbolic music transformer, showing that its learned representations already encode pianist identity well enough for highly accurate classification across two benchmarks. We then augment the transformer with cross-attention over learned pianist identity embeddings, enabling it to generate music conditioned on a specific artist's style. Two evaluation protocols confirm that the generator captures meaningful stylistic structure: a sliding-window classifier consistently attributes conditioned continuations to the correct artist, far above unconditioned baselines; and a classifier trained entirely on synthetic generations identifies real pianists across 12 classes with 87% chunk-level and 95% song-level accuracy. Finally, we repurpose the classifier to locate the most characteristic moments within a performance, surfacing the specific musical gestures that distinguish each pianist's voice.