# Tempo vs. Pitch: understanding self-supervised tempo estimation

arXiv: https://arxiv.org/abs/2304.06868 · HTML: https://mlsanity.com/paper/2304.06868/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 23 references that are in the map.
- First posted on arXiv 14 Apr 2023.

## Builds on (most cited first, 4 of 4)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [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)
- [Exploring modality-agnostic representations for music classification](https://mlsanity.com/paper/2106.01149/) (2021)

## Built on by (most cited first, 2 of 2)

- [PESTO: Real-Time Pitch Estimation with Self-supervised Transposition-equivariant Objective](https://mlsanity.com/paper/2508.01488/) (2025)
- [Tempo estimation as fully self-supervised binary classification](https://mlsanity.com/paper/2401.08891/) (2024)

## Abstract (arXiv)

Self-supervision methods learn representations by solving pretext tasks that do not require human-generated labels, alleviating the need for time-consuming annotations. These methods have been applied in computer vision, natural language processing, environmental sound analysis, and recently in music information retrieval, e.g. for pitch estimation. Particularly in the context of music, there are few insights about the fragility of these models regarding different distributions of data, and how they could be mitigated. In this paper, we explore these questions by dissecting a self-supervised model for pitch estimation adapted for tempo estimation via rigorous experimentation with synthetic data. Specifically, we study the relationship between the input representation and data distribution for self-supervised tempo estimation.