Metraipolis › archive › dc_2aee3d46cbe3
Learning Jazz Pianist Style with Cross-Attention Conditioning — arXiv:2610.02918
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.02918
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-05T23:10:42.517Z
- SHA-256 of the archived text
9e4ec1c07b4ecdb4e24db3cb0d91ddcd7e1cb726e00d255ab16c5ea37d47bc75- Stable URL of this page
https://metraipolis.com/documento/dc_2aee3d46cbe3
How to cite
Learning Jazz Pianist Style with Cross-Attention Conditioning — arXiv:2610.02918 — arXiv, https://arxiv.org/abs/2610.02918 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2aee3d46cbe3 (Metraipolis archive dc_2aee3d46cbe3, sha256 9e4ec1c07b4ecdb4e24db3cb0d91ddcd7e1cb726e00d255ab16c5ea37d47bc75)
BibTeX
@misc{dc2aee3d46cbe3,
title = {Learning Jazz Pianist Style with Cross-Attention Conditioning — arXiv:2610.02918},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.02918},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2aee3d46cbe3; sha256 9e4ec1c07b4ecdb4e24db3cb0d91ddcd7e1cb726e00d255ab16c5ea37d47bc75},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02918. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Sound (cs.SD) ; Machine Learning (cs.LG); Audio and Speech Processing (eess.AS). Pagina del lavoro: https://arxiv.org/abs/2610.02918 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-05T23:01:38.754Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).