# MeloBottleneck: Self-Supervised Melody Skeleton Extraction with a Latent Subsequence Bottleneck

arXiv: https://arxiv.org/abs/2607.10233 · HTML: https://mlsanity.com/paper/2607.10233/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 29 references that are in the map.
- First posted on arXiv 11 Jul 2026.

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

- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training](https://mlsanity.com/paper/2106.05630/) (2021)
- [Efficiently Trainable Text-to-Speech System Based on Deep Convolutional Networks with Guided Attention](https://mlsanity.com/paper/1710.08969/) (2017)
- [SEQ^3: Differentiable Sequence-to-Sequence-to-Sequence Autoencoder for Unsupervised Abstractive Sentence Compression](https://mlsanity.com/paper/1904.03651/) (2019)
- [TunesFormer: Forming Irish Tunes with Control Codes by Bar Patching](https://mlsanity.com/paper/2301.02884/) (2023)
- [PianoBART: Symbolic Piano Music Generation and Understanding with Large-Scale Pre-Training](https://mlsanity.com/paper/2407.03361/) (2024)
- [WuYun: Exploring hierarchical skeleton-guided melody generation using knowledge-enhanced deep learning](https://mlsanity.com/paper/2301.04488/) (2023)
- [Extractive Summary as Discrete Latent Variables](https://mlsanity.com/paper/1811.05542/) (2018)
- [A Statistical Model for Melody Reduction](https://mlsanity.com/paper/2105.05385/) (2021)
- [Automatic Melody Reduction via Shortest Path Finding](https://mlsanity.com/paper/2508.01571/) (2025)
- [The Renaissance of Expert Systems: Optical Recognition of Printed Chinese Jianpu Musical Scores with Lyrics](https://mlsanity.com/paper/2512.14758/) (2025)

## Abstract (arXiv)

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.