# TheGlueNote: Learned Representations for Robust and Flexible Note Alignment

arXiv: https://arxiv.org/abs/2408.04309 · HTML: https://mlsanity.com/paper/2408.04309/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 28 references that are in the map.
- First posted on arXiv 8 Aug 2024.

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

- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023)
- [Soft-DTW: a Differentiable Loss Function for Time-Series](https://mlsanity.com/paper/1703.01541/) (2017)
- [miditok: A Python package for MIDI file tokenization](https://mlsanity.com/paper/2310.17202/) (2023)
- [Local Feature Matching Using Deep Learning: A Survey](https://mlsanity.com/paper/2401.17592/) (2024)
- [The Piano Inpainting Application](https://mlsanity.com/paper/2107.05944/) (2021)
- [Learning to Listen, Read, and Follow: Score Following as a Reinforcement Learning Game](https://mlsanity.com/paper/1807.06391/) (2018)
- [Online Symbolic Music Alignment with Offline Reinforcement Learning](https://mlsanity.com/paper/2401.00466/) (2023)
- [The ACCompanion: Combining Reactivity, Robustness, and Musical Expressivity in an Automatic Piano Accompanist](https://mlsanity.com/paper/2304.12939/) (2023)
- [The Batik-plays-Mozart Corpus: Linking Performance to Score to Musicological Annotations](https://mlsanity.com/paper/2309.02399/) (2023)
- [Outer-Product Hidden Markov Model and Polyphonic MIDI Score Following](https://mlsanity.com/paper/1404.2313/) (2014)
- [A Stochastic Temporal Model of Polyphonic MIDI Performance with Ornaments](https://mlsanity.com/paper/1404.2314/) (2014)

## Built on by (most cited first, 1 of 1)

- [RUMAA: Repeat-Aware Unified Music Audio Analysis for Score-Performance Alignment, Transcription, and Mistake Detection](https://mlsanity.com/paper/2507.12175/) (2025)

## Abstract (arXiv)

Note alignment refers to the task of matching individual notes of two versions of the same symbolically encoded piece. Methods addressing this task commonly rely on sequence alignment algorithms such as Hidden Markov Models or Dynamic Time Warping (DTW) applied directly to note or onset sequences. While successful in many cases, such methods struggle with large mismatches between the versions. In this work, we learn note-wise representations from data augmented with various complex mismatch cases, e.g. repeats, skips, block insertions, and long trills. At the heart of our approach lies a transformer encoder network - TheGlueNote - which predicts pairwise note similarities for two 512 note subsequences. We postprocess the predicted similarities using flavors of weightedDTW and pitch-separated onsetDTW to retrieve note matches for two sequences of arbitrary length. Our approach performs on par with the state of the art in terms of note alignment accuracy, is considerably more robust to version mismatches, and works directly on any pair of MIDI files.