November 7, 2021 Conference paper Open Access

Vincenzo Madaghiele; Pasquale Lisena; Raphael Troncy

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.5625684</identifier>
  <creators>
    <creator>
      <creatorName>Vincenzo Madaghiele</creatorName>
    </creator>
    <creator>
      <creatorName>Pasquale Lisena</creatorName>
    </creator>
    <creator>
      <creatorName>Raphael Troncy</creatorName>
    </creator>
  </creators>
  <titles>
    <title>MINGUS: Melodic Improvisation Neural Generator Using Seq2Seq</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2021</publicationYear>
  <dates>
    <date dateType="Issued">2021-11-07</date>
  </dates>
  <resourceType resourceTypeGeneral="ConferencePaper"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/5625684</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.5625683</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://zenodo.org/communities/ismir</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">Sequence to Sequence (Seq2Seq) approaches have shown good performances in automatic music generation. We introduce MINGUS, a Transformer-based Seq2Seq architecture for modelling and generating monophonic jazz melodic lines.
 MINGUS relies on two dedicated embedding models (respectively for pitch and duration) and exploits in prediction features such as chords (current and following), bass line, position inside the measure. 
 The obtained results are comparable with the state of the art of music generation with neural models, with particularly good performances on jazz music.</description>
  </descriptions>
</resource>