Conference paper Open Access

ASMD: an automatic framework for compiling multimodal datasets with audio and scores

Simonetta, Federico; Ntalampiras, Stavros; Avanzini, Federico


DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="DOI">10.5281/zenodo.3773286</identifier>
  <creators>
    <creator>
      <creatorName>Simonetta, Federico</creatorName>
      <givenName>Federico</givenName>
      <familyName>Simonetta</familyName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0002-5928-9836</nameIdentifier>
      <affiliation>University of Milan</affiliation>
    </creator>
    <creator>
      <creatorName>Ntalampiras, Stavros</creatorName>
      <givenName>Stavros</givenName>
      <familyName>Ntalampiras</familyName>
      <affiliation>University of Milan</affiliation>
    </creator>
    <creator>
      <creatorName>Avanzini, Federico</creatorName>
      <givenName>Federico</givenName>
      <familyName>Avanzini</familyName>
      <affiliation>University of Milan</affiliation>
    </creator>
  </creators>
  <titles>
    <title>ASMD: an automatic framework for compiling multimodal datasets with audio and scores</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2020</publicationYear>
  <subjects>
    <subject>MIR</subject>
    <subject>Dataset</subject>
    <subject>Python</subject>
    <subject>Audio</subject>
    <subject>Music Scores</subject>
    <subject>Music Sheets</subject>
    <subject>Music Information Retrieval</subject>
  </subjects>
  <dates>
    <date dateType="Issued">2020-04-28</date>
  </dates>
  <resourceType resourceTypeGeneral="Text">Conference paper</resourceType>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/3773286</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="arXiv" relationType="IsIdenticalTo" resourceTypeGeneral="Text">arXiv:2003.01958</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.3773285</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://zenodo.org/communities/federicosimonetta</relatedIdentifier>
  </relatedIdentifiers>
  <rightsList>
    <rights rightsURI="https://creativecommons.org/licenses/by/4.0/legalcode">Creative Commons Attribution 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&lt;p&gt;This paper describes an open-source Python framework for handling datasets for music processing tasks, built with the aim of improving the reproducibility of research projects in music computing and assessing the generalization abilities of machine learning models. The framework enables the automatic download and installation of several commonly used datasets for multimodal music processing. Specifically, we provide a Python API to access the datasets through Boolean set operations based on particular attributes, such as intersections and unions of composers, instruments, and so on. The framework is designed to ease the inclusion of new datasets and the respective ground-truth annotations so that one can build, convert, and extend one&amp;#39;s own collection as well as distribute it by means of a compliant format to take advantage of the API. All code and ground-truth are released under suitable open licenses.&lt;/p&gt;</description>
  </descriptions>
</resource>
21
17
views
downloads
All versions This version
Views 2121
Downloads 1717
Data volume 3.3 MB3.3 MB
Unique views 1717
Unique downloads 1414

Share

Cite as