# Tempo estimation as fully self-supervised binary classification

arXiv: https://arxiv.org/abs/2401.08891 · HTML: https://mlsanity.com/paper/2401.08891/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 29 references that are in the map.
- First posted on arXiv 17 Jan 2024.

## Builds on (most cited first, 8 of 8)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training](https://mlsanity.com/paper/2306.00107/) (2023)
- [Supervised and Unsupervised Learning of Audio Representations for Music Understanding](https://mlsanity.com/paper/2210.03799/) (2022)
- [SPICE: Self-supervised Pitch Estimation](https://mlsanity.com/paper/1910.11664/) (2019)
- [Equivariant Self-Supervision for Musical Tempo Estimation](https://mlsanity.com/paper/2209.01478/) (2022)
- [Tempo vs. Pitch: understanding self-supervised tempo estimation](https://mlsanity.com/paper/2304.06868/) (2023)

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

- [Toward Fully Self-Supervised Multi-Pitch Estimation](https://mlsanity.com/paper/2402.15569/) (2024)

## Abstract (arXiv)

This paper addresses the problem of global tempo estimation in musical audio. Given that annotating tempo is time-consuming and requires certain musical expertise, few publicly available data sources exist to train machine learning models for this task. Towards alleviating this issue, we propose a fully self-supervised approach that does not rely on any human labeled data. Our method builds on the fact that generic (music) audio embeddings already encode a variety of properties, including information about tempo, making them easily adaptable for downstream tasks. While recent work in self-supervised tempo estimation aimed to learn a tempo specific representation that was subsequently used to train a supervised classifier, we reformulate the task into the binary classification problem of predicting whether a target track has the same or a different tempo compared to a reference. While the former still requires labeled training data for the final classification model, our approach uses arbitrary unlabeled music data in combination with time-stretching for model training as well as a small set of synthetically created reference samples for predicting the final tempo. Evaluation of our approach in comparison with the state-of-the-art reveals highly competitive performance when the constraint of finding the precise tempo octave is relaxed.