# Unsupervised Symbolic Music Segmentation using Ensemble Temporal Prediction Errors

arXiv: https://arxiv.org/abs/2207.00760 · HTML: https://mlsanity.com/paper/2207.00760/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 41 references that are in the map.
- First posted on arXiv 2 Jul 2022.

## Builds on (most cited first, 7 of 7)

- [Self-Supervised Contrastive Learning for Unsupervised Phoneme Segmentation](https://mlsanity.com/paper/2007.13465/) (2020)
- [Contrastive prediction strategies for unsupervised segmentation and categorization of phonemes and words](https://mlsanity.com/paper/2110.15909/) (2021)
- [Song From PI: A Musically Plausible Network for Pop Music Generation](https://mlsanity.com/paper/1611.03477/) (2016)
- [Blind phoneme segmentation with temporal prediction errors](https://mlsanity.com/paper/1608.00508/) (2016)
- [Gate Activation Signal Analysis for Gated Recurrent Neural Networks and Its Correlation with Phoneme Boundaries](https://mlsanity.com/paper/1703.07588/) (2017)
- [Melodic Phrase Segmentation By Deep Neural Networks](https://mlsanity.com/paper/1811.05688/) (2018)
- [Automatic measurement of vowel duration via structured prediction](https://mlsanity.com/paper/1610.08166/) (2016)

## Built on by (most cited first, 4 of 4)

- [Simple and Controllable Music Generation](https://mlsanity.com/paper/2306.05284/) (2023)
- [MeLFusion: Synthesizing Music from Image and Language Cues using Diffusion Models](https://mlsanity.com/paper/2406.04673/) (2024)
- [Symbolic Music Structure Analysis with Graph Representations and Changepoint Detection Methods](https://mlsanity.com/paper/2303.13881/) (2023)
- [Barwise Section Boundary Detection in Symbolic Music Using Convolutional Neural Networks](https://mlsanity.com/paper/2509.16566/) (2025)

## Abstract (arXiv)

Symbolic music segmentation is the process of dividing symbolic melodies into smaller meaningful groups, such as melodic phrases. We proposed an unsupervised method for segmenting symbolic music. The proposed model is based on an ensemble of temporal prediction error models. During training, each model predicts the next token to identify musical phrase changes. While at test time, we perform a peak detection algorithm to select segment candidates. Finally, we aggregate the predictions of each of the models participating in the ensemble to predict the final segmentation. Results suggest the proposed method reaches state-of-the-art performance on the Essen Folksong dataset under the unsupervised setting when considering F-Score and R-value. We additionally provide an ablation study to better assess the contribution of each of the model components to the final results. As expected, the proposed method is inferior to the supervised setting, which leaves room for improvement in future research considering closing the gap between unsupervised and supervised methods.