CREPE: A Convolutional Representation for Pitch Estimation

Jong Wook Kim, Justin Salamon, Peter Li, Juan Pablo Bello
2/17/2018
eess.AScs.LGcs.SD

Official code: marl/crepe (1,421 stars, MIT, TensorFlow, last commit 2024-08-19).

Abstract

The task of estimating the fundamental frequency of a monophonic sound recording, also known as pitch tracking, is fundamental to audio processing with multiple applications in speech processing and music information retrieval. To date, the best performing techniques, such as the pYIN algorithm, are based on a combination of DSP pipelines and heuristics. While such techniques perform very well on average, there remain many cases in which they fail to correctly estimate the pitch. In this paper, we propose a data-driven pitch tracking algorithm, CREPE, which is based on a deep convolutional neural network that operates directly on the time-domain waveform. We show that the proposed model produces state-of-the-art results, performing equally or better than pYIN. Furthermore, we evaluate the model's generalizability in terms of noise robustness. A pre-trained version of CREPE is made freely available as an open-source Python module for easy application.

View on arXivView PDF

Code Implementations(1)

marl/crepeOfficial100%
TensorFlowMIT

CREPE: A Convolutional REpresentation for Pitch Estimation -- pre-trained model (ICASSP 2018)

1,421188PythonDec 17, 20172 years agoMIT
kerasmusic-information-retrievalpitch-estimationtensorflow

Similar Papers

Human Voice Pitch Estimation: A Convolutional Network with Auto-Labeled and Synthetic Data

82% match1 repo32023

SwiftF0: Fast and Accurate Monophonic Pitch Detection

81% match2 repos1712025

FCPE: A Fast Context-based Pitch Estimation Model

81% match1 repo2132025

Vocal melody extraction using patch-based CNN

79% match1 repo322018

Unsupervised Harmonic Parameter Estimation Using Differentiable DSP and Spectral Optimal Transport

79% match1 repo302023

Lightweight Self-Supervised Detection of Fundamental Frequency and Accurate Probability of Voicing in Monophonic Music

78% match2026

Cite this paper

@article{kim2018crepe,
  title  = {CREPE: A Convolutional Representation for Pitch Estimation},
  author = {Jong Wook Kim and Justin Salamon and Peter Li and Juan Pablo Bello},
  year   = {2018},
  eprint = {1802.06182},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1802.06182}
}

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/1802.06182.svg)](https://codeofpaper.com/paper/1802.06182)

Discussion