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

facebooktwittermailshare

Vocal melody extraction using patch-based CNN

Abstract: 

A patch-based convolutional neural network (CNN) model presented in this paper for vocal melody extraction in polyphonic music is inspired from object detection in image processing. The input of the model is a novel time-frequency representation which enhances the pitch contours and suppresses the harmonic components of a signal. This succinct data representation and the patch-based CNN model enable an efficient training process with limited labeled data. Experiments on various datasets show excellent speed and competitive accuracy comparing to other deep learning approaches.

up
0 users have voted:

Paper Details

Authors:
Submitted On:
17 April 2018 - 8:41am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Li Su
Paper Code:
AASP-P7.4
Document Year:
2018
Cite

Document Files

poster_icassp_v2.pdf

(14 downloads)

Subscribe

[1] , "Vocal melody extraction using patch-based CNN", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2932. Accessed: Apr. 26, 2018.
@article{2932-18,
url = {http://sigport.org/2932},
author = { },
publisher = {IEEE SigPort},
title = {Vocal melody extraction using patch-based CNN},
year = {2018} }
TY - EJOUR
T1 - Vocal melody extraction using patch-based CNN
AU -
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2932
ER -
. (2018). Vocal melody extraction using patch-based CNN. IEEE SigPort. http://sigport.org/2932
, 2018. Vocal melody extraction using patch-based CNN. Available at: http://sigport.org/2932.
. (2018). "Vocal melody extraction using patch-based CNN." Web.
1. . Vocal melody extraction using patch-based CNN [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2932