Tempo vs. Pitch: understanding self-supervised tempo estimation

Giovana Morais, Matthew E. P. Davies, Marcelo Queiroz, Magdalena Fuentes
4/14/2023
cs.SDcs.LGeess.AS

No official code found. Best implementation: giovana-morais/steme (13 stars, last commit 2023-08-02).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

giovana-morais/stemeCommunity100%

[ICASSP 2023] Tempo vs. Pitch: understanding self-supervised tempo estimation

132Shell, PythonOct 25, 20223 years ago
python

Similar Papers

Investigating an Overfitting and Degeneration Phenomenon in Self-Supervised Multi-Pitch Estimation

85% match2025

AI and Tempo Estimation: A Review

82% match2023

Toward Fully Self-Supervised Multi-Pitch Estimation

80% match1 repo252024

BeatNet: CRNN and Particle Filtering for Online Joint Beat Downbeat and Meter Tracking

80% match1 repo5032021

Self-supervised Auxiliary Loss for Metric Learning in Music Similarity-based Retrieval and Auto-tagging

80% match2023

An Experimental Comparison Of Multi-view Self-supervised Methods For Music Tagging

79% match1 repo72024

Cite this paper

@article{morais2023tempo,
  title  = {Tempo vs. Pitch: understanding self-supervised tempo estimation},
  author = {Giovana Morais and Matthew E. P. Davies and Marcelo Queiroz and Magdalena Fuentes},
  year   = {2023},
  eprint = {2304.06868},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2304.06868v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2304.06868.svg)](https://codeofpaper.com/paper/2304.06868)

Discussion