{"ID":6536399,"CreatedAt":"2026-07-14T01:21:01.169441415Z","UpdatedAt":"2026-07-14T08:33:44.272455028Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.10233","arxiv_id":"2607.10233","title":"MeloBottleneck: Self-Supervised Melody Skeleton Extraction with a Latent Subsequence Bottleneck","abstract":"Melody skeleton extraction aims to derive a shorter melody that preserves structural notes while removing ornaments. Prior methods rely on hand-crafted reduction rules or note-wise salience classifiers trained with heuristically or procedurally generated pseudo-labels. Such supervision can inherit generator bias and does not explicitly optimize a coherent reduced melody. We introduce MeloBottleneck, a self-supervised framework that represents a skeleton as a length-controlled, order-preserving latent subsequence. A hard-bottleneck extractor selects note events, a rhythmic-closure operator produces a self-consistent skeleton, and a re-ornamentation decoder reconstructs the input melody. Training combines reconstruction, a frozen autoregressive melody prior, ornament-invariant consistency across procedurally ornamented views, and ornament exclusion. We evaluate three regimes: synthetic out-of-distribution ornament-to-skeleton, TAVERN variation-to-theme, and Jiugong ornamented-to-gongche. A matched pseudo-label classifier excels on the synthetic benchmark, while MeloBottleneck transfers better, achieving competitive selection quality on TAVERN and Jiugong. Skeletonized melodies also improve BM25-based fragment retrieval, boosting Recall@K and MRR while reducing query time. Overall, the results suggest that learning skeletons as latent subsequences yields more robust transfer than pseudo-label imitation.","short_abstract":"Melody skeleton extraction aims to derive a shorter melody that preserves structural notes while removing ornaments. Prior methods rely on hand-crafted reduction rules or note-wise salience classifiers trained with heuristically or procedurally generated pseudo-labels. Such supervision can inherit generator bias and do...","url_abs":"https://arxiv.org/abs/2607.10233","url_pdf":"https://arxiv.org/pdf/2607.10233v1","authors":"[\"Fan Bu\",\"Rongfeng Li\",\"Linfeng Fan\"]","published":"2026-07-11T09:44:32Z","proceeding":"cs.SD","tasks":"[\"cs.SD\",\"cs.LG\"]","methods":"[]","has_code":false}