Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

CREPE: A Convolutional Representation for Pitch Estimation

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.

up
0 users have voted:

Paper Details

Authors:
Jong Wook Kim, Justin Salamon, Peter Li, Juan Pablo Bello
Submitted On:
19 April 2018 - 8:23pm
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Jong Wook Kim
Paper Code:
AASP-L4.3
Document Year:
2018
Cite

Document Files

crepe.pdf

(20 downloads)

Subscribe

[1] Jong Wook Kim, Justin Salamon, Peter Li, Juan Pablo Bello, "CREPE: A Convolutional Representation for Pitch Estimation", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3042. Accessed: May. 25, 2018.
@article{3042-18,
url = {http://sigport.org/3042},
author = {Jong Wook Kim; Justin Salamon; Peter Li; Juan Pablo Bello },
publisher = {IEEE SigPort},
title = {CREPE: A Convolutional Representation for Pitch Estimation},
year = {2018} }
TY - EJOUR
T1 - CREPE: A Convolutional Representation for Pitch Estimation
AU - Jong Wook Kim; Justin Salamon; Peter Li; Juan Pablo Bello
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3042
ER -
Jong Wook Kim, Justin Salamon, Peter Li, Juan Pablo Bello. (2018). CREPE: A Convolutional Representation for Pitch Estimation. IEEE SigPort. http://sigport.org/3042
Jong Wook Kim, Justin Salamon, Peter Li, Juan Pablo Bello, 2018. CREPE: A Convolutional Representation for Pitch Estimation. Available at: http://sigport.org/3042.
Jong Wook Kim, Justin Salamon, Peter Li, Juan Pablo Bello. (2018). "CREPE: A Convolutional Representation for Pitch Estimation." Web.
1. Jong Wook Kim, Justin Salamon, Peter Li, Juan Pablo Bello. CREPE: A Convolutional Representation for Pitch Estimation [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3042