Vocal melody extraction using patch-based CNN

Li Su
4/24/2018
cs.SDeess.AS

Official code: leo-so/VocalMelodyExtPatchCNN (32 stars, GPL-3.0, last commit 2018-02-05).

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.

View on arXivView PDF

Code Implementations(1)

GPL-3.0

Vocal melody extraction using patch-based CNN

328PythonFeb 5, 20188 years agoGPL-3.0

Similar Papers

Cite this paper

@article{su2018vocal,
  title  = {Vocal melody extraction using patch-based CNN},
  author = {Li Su},
  year   = {2018},
  eprint = {1804.09202},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1804.09202}
}

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/1804.09202.svg)](https://codeofpaper.com/paper/1804.09202)

Discussion