# AlignBeat: A Latent Variable Model for Multi-Class Beat Tracking from Partially Labeled Data

arXiv: https://arxiv.org/abs/2510.14391 · HTML: https://mlsanity.com/paper/2510.14391/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 33 references that are in the map.
- First posted on arXiv 16 Oct 2025.

## Builds on (most cited first, 6 of 6)

- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [madmom: a new Python Audio and Music Signal Processing Library](https://mlsanity.com/paper/1605.07008/) (2016)
- [Learning to Groove with Inverse Sequence Transformations](https://mlsanity.com/paper/1905.06118/) (2019)
- [Beat this! Accurate beat tracking without DBN postprocessing](https://mlsanity.com/paper/2407.21658/) (2024)
- [Modeling Beats and Downbeats with a Time-Frequency Transformer](https://mlsanity.com/paper/2205.14701/) (2022)
- [Beat Transformer: Demixed Beat and Downbeat Tracking with Dilated Self-Attention](https://mlsanity.com/paper/2209.07140/) (2022)

## Abstract (arXiv)

Recent neural beat trackers predict beats and downbeats with two independent frame-wise binary classification heads, a convention adopted because a single multi-class head cannot fully exploit datasets that annotate only beats. The heads can disagree, so Beat This moves each predicted downbeat to the nearest predicted beat. We instead predict a sparse set of grid points, each with an event time and one distribution over downbeat, beat and no event, so a downbeat is a beat by construction and no reconciliation is needed. The alignment between grid points and annotated events is latent, and we fit the model by expectation-maximization. Where no downbeat labels were recorded the event class is latent too and is marginalized out. Over eight-fold cross-validation on eighteen datasets, retaining rather than discarding the beat-only labeled data raises beat CMLt by 4.6 points on the datasets that provide it; downbeat CMLt rises 3.6 points over Beat This, with both F-measures moving by less than one point and no post-processing at any stage.