Metraipolis › archive › dc_db67f92732c8
How Close to the Theme? Similarity-Label Conditioning for Game Music Generation — arXiv:2611.01047
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.01047
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:40:24.148Z
- SHA-256 of the archived text
6aa2cf33dac128b10236f346bd4215bbb5a6c4e51c2c6a5f54db070a5c230f95- Stable URL of this page
https://metraipolis.com/documento/dc_db67f92732c8
How to cite
How Close to the Theme? Similarity-Label Conditioning for Game Music Generation — arXiv:2611.01047 — arXiv (en), https://arxiv.org/abs/2611.01047 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_db67f92732c8 (Metraipolis archive dc_db67f92732c8, sha256 6aa2cf33dac128b10236f346bd4215bbb5a6c4e51c2c6a5f54db070a5c230f95)
BibTeX
@misc{dcdb67f92732c8,
title = {How Close to the Theme? Similarity-Label Conditioning for Game Music Generation — arXiv:2611.01047},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.01047},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_db67f92732c8; sha256 6aa2cf33dac128b10236f346bd4215bbb5a6c4e51c2c6a5f54db070a5c230f95},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01047. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Composers develop music from an original idea, controlling how similar each new section is to it, from near repetition to new material. Game music needs this often, as its material repeats over long play. Music models, however, rarely learn to control similarity from real pieces. We further train a pretrained MIDI model on section pairs from Super Mario pieces. A label states each pair's similarity, and a context vector summarises the given section, or context. For 157 test contexts, the model generates six outputs per label. Twelve measures score the outputs; one main measure each covers melody, pitch content, rhythm and note length. On average, outputs requested as similar are more similar to their context than those requested as dissimilar, and not to other pieces. All twelve measures favour them; each main measure stays significant after correction for multiple tests. On melody, the gap comes mainly from more frequent restatement of the context's melody. Against an otherwise identical model without a label, only the request for high similarity makes outputs more similar. In a listening test, ratings followed melodic overlap with the context most closely of all measures. 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/2611.01047 — 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 2026-11-03T18:12:54.717Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).