Conference paper Open Access

A Convolutional Approach to Melody Line Identification in Symbolic Scores

Simonetta, Federico; Cancino-Chacón, Carlos; Ntalampiras, Stavros; Widmer, Gerhard


Dublin Core Export

<?xml version='1.0' encoding='utf-8'?>
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
  <dc:creator>Simonetta, Federico</dc:creator>
  <dc:creator>Cancino-Chacón, Carlos</dc:creator>
  <dc:creator>Ntalampiras, Stavros</dc:creator>
  <dc:creator>Widmer, Gerhard</dc:creator>
  <dc:date>2019-11-04</dc:date>
  <dc:description>In many musical traditions, the melody line is of primary significance in a piece. Human listeners can readily distinguish melodies from accompaniment; however, making this distinction given only the written score -- i.e. without listening to the music performed -- can be a difficult task. Solving this task is of great importance for both Music Information Retrieval and musicological applications. In this paper, we propose an automated approach to identifying the most salient melody line in a symbolic score. The backbone of the method consists of a convolutional neural network (CNN) estimating the probability that each note in the score (more precisely: each pixel in a piano roll encoding of the score) belongs to the melody line. We train and evaluate the method on various datasets, using manual annotations where available and solo instrument parts where not. We also propose a method to inspect the CNN and to analyze the influence exerted by notes on the prediction of other notes; this method can be applied whenever the output of a neural network has the same size as the input.</dc:description>
  <dc:identifier>https://zenodo.org/record/3530592</dc:identifier>
  <dc:identifier>10.5281/zenodo.3530592</dc:identifier>
  <dc:identifier>oai:zenodo.org:3530592</dc:identifier>
  <dc:language>eng</dc:language>
  <dc:publisher>ISMIR</dc:publisher>
  <dc:relation>doi:10.5281/zenodo.3527965</dc:relation>
  <dc:relation>url:https://arxiv.org/abs/1906.10547</dc:relation>
  <dc:relation>doi:10.5281/zenodo.3530591</dc:relation>
  <dc:relation>url:https://zenodo.org/communities/federicosimonetta</dc:relation>
  <dc:rights>info:eu-repo/semantics/openAccess</dc:rights>
  <dc:rights>https://creativecommons.org/licenses/by/4.0/legalcode</dc:rights>
  <dc:subject>Music Information Retrieval</dc:subject>
  <dc:subject>Convolutional Neural Network</dc:subject>
  <dc:subject>Melody Identification</dc:subject>
  <dc:subject>Symbolic scores</dc:subject>
  <dc:subject>MIR</dc:subject>
  <dc:title>A Convolutional Approach to Melody Line Identification in Symbolic Scores</dc:title>
  <dc:type>info:eu-repo/semantics/conferencePaper</dc:type>
  <dc:type>publication-conferencepaper</dc:type>
</oai_dc:dc>
42
27
views
downloads
All versions This version
Views 4242
Downloads 2727
Data volume 40.9 MB40.9 MB
Unique views 3333
Unique downloads 2222

Share

Cite as