There is a newer version of this record available.

Dataset Open Access

EMOPIA: A Multi-Modal Pop Piano Dataset For Emotion Recognition and Emotion-based Music Generation

Hung, Hsiao-Tzu; Ching, Joann; Doh, Seungheon; Kim, Nabin; Nam, Juhan; Yang, Yi-Hsuan


DCAT Export

<?xml version='1.0' encoding='utf-8'?>
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:adms="http://www.w3.org/ns/adms#" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dct="http://purl.org/dc/terms/" xmlns:dctype="http://purl.org/dc/dcmitype/" xmlns:dcat="http://www.w3.org/ns/dcat#" xmlns:duv="http://www.w3.org/ns/duv#" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:frapo="http://purl.org/cerif/frapo/" xmlns:geo="http://www.w3.org/2003/01/geo/wgs84_pos#" xmlns:gsp="http://www.opengis.net/ont/geosparql#" xmlns:locn="http://www.w3.org/ns/locn#" xmlns:org="http://www.w3.org/ns/org#" xmlns:owl="http://www.w3.org/2002/07/owl#" xmlns:prov="http://www.w3.org/ns/prov#" xmlns:rdfs="http://www.w3.org/2000/01/rdf-schema#" xmlns:schema="http://schema.org/" xmlns:skos="http://www.w3.org/2004/02/skos/core#" xmlns:vcard="http://www.w3.org/2006/vcard/ns#" xmlns:wdrs="http://www.w3.org/2007/05/powder-s#">
  <rdf:Description rdf:about="https://doi.org/10.5281/zenodo.5090631">
    <rdf:type rdf:resource="http://www.w3.org/ns/dcat#Dataset"/>
    <dct:type rdf:resource="http://purl.org/dc/dcmitype/Dataset"/>
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://doi.org/10.5281/zenodo.5090631</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.5090631"/>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Hung, Hsiao-Tzu</foaf:name>
        <foaf:givenName>Hsiao-Tzu</foaf:givenName>
        <foaf:familyName>Hung</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Academia Sinica</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Ching, Joann</foaf:name>
        <foaf:givenName>Joann</foaf:givenName>
        <foaf:familyName>Ching</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Academia Sinica</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Doh, Seungheon</foaf:name>
        <foaf:givenName>Seungheon</foaf:givenName>
        <foaf:familyName>Doh</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>KAIST</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Kim, Nabin</foaf:name>
        <foaf:givenName>Nabin</foaf:givenName>
        <foaf:familyName>Kim</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Georgia Institute of Technology</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0003-2664-2119">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0003-2664-2119</dct:identifier>
        <foaf:name>Nam, Juhan</foaf:name>
        <foaf:givenName>Juhan</foaf:givenName>
        <foaf:familyName>Nam</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>KAIST</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0002-2724-6161">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0002-2724-6161</dct:identifier>
        <foaf:name>Yang, Yi-Hsuan</foaf:name>
        <foaf:givenName>Yi-Hsuan</foaf:givenName>
        <foaf:familyName>Yang</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Academia Sinica</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:title>EMOPIA: A Multi-Modal Pop Piano Dataset For Emotion Recognition and Emotion-based Music Generation</dct:title>
    <dct:publisher>
      <foaf:Agent>
        <foaf:name>Zenodo</foaf:name>
      </foaf:Agent>
    </dct:publisher>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#gYear">2021</dct:issued>
    <dcat:keyword>piano</dcat:keyword>
    <dcat:keyword>emotion</dcat:keyword>
    <dcat:keyword>music</dcat:keyword>
    <dcat:keyword>midi</dcat:keyword>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2021-07-18</dct:issued>
    <owl:sameAs rdf:resource="https://zenodo.org/record/5090631"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/5090631</skos:notation>
        <adms:schemeAgency>url</adms:schemeAgency>
      </adms:Identifier>
    </adms:identifier>
    <dct:isVersionOf rdf:resource="https://doi.org/10.5281/zenodo.5090630"/>
    <owl:versionInfo>1.0</owl:versionInfo>
    <dct:description>&lt;p&gt;EMOPIA (pronounced &amp;lsquo;yee-m&amp;ograve;-pi-uh&amp;rsquo;) dataset is a shared multi-modal (audio and MIDI) database focusing on perceived emotion in&amp;nbsp;&lt;strong&gt;pop piano music&lt;/strong&gt;, to facilitate research on various tasks related to music emotion. The dataset contains&amp;nbsp;&lt;strong&gt;1,087&lt;/strong&gt;&amp;nbsp;music clips from 387 songs and&amp;nbsp;&lt;strong&gt;clip-level&lt;/strong&gt;&amp;nbsp;emotion labels annotated by four dedicated annotators.&amp;nbsp;&lt;/p&gt; &lt;p&gt;For more detailed information about the dataset, please refer to our paper:&amp;nbsp;&lt;a href="https://arxiv.org/abs/2108.01374"&gt;&lt;strong&gt;EMOPIA: A Multi-Modal Pop Piano Dataset For Emotion Recognition and Emotion-based Music Generation&lt;/strong&gt;&lt;/a&gt;.&amp;nbsp;&lt;/p&gt; &lt;p&gt;&lt;strong&gt;File Description&lt;/strong&gt;&lt;/p&gt; &lt;ul&gt; &lt;li&gt;&lt;em&gt;&lt;strong&gt;midis/&lt;/strong&gt;&lt;/em&gt;:&amp;nbsp;midi clips transcribed using GiantMIDI. &lt;ul&gt; &lt;li&gt;Filename `Q1_xxxxxxx_2.mp3`: Q1 means this clip belongs to Q1 on the V-A space; xxxxxxx is the song ID on YouTube, and the `2` means this clip is the 2nd clip taken from the full song.&lt;/li&gt; &lt;/ul&gt; &lt;/li&gt; &lt;li&gt;&lt;em&gt;&lt;strong&gt;metadata/&lt;/strong&gt;&lt;/em&gt;:&amp;nbsp;metadata from YouTube. (Got when crawling)&lt;/li&gt; &lt;li&gt; &lt;p&gt;&lt;em&gt;&lt;strong&gt;songs_lists/&lt;/strong&gt;&lt;/em&gt;:&amp;nbsp;YouTube URLs of songs.&lt;/p&gt; &lt;/li&gt; &lt;li&gt; &lt;p&gt;&lt;em&gt;&lt;strong&gt;tagging_lists/&lt;/strong&gt;&lt;/em&gt;:&amp;nbsp;raw tagging result for each sample.&lt;/p&gt; &lt;/li&gt; &lt;li&gt; &lt;p&gt;&lt;em&gt;&lt;strong&gt;label.csv&lt;/strong&gt;&lt;/em&gt;: metadata that records filename, clip timestamps, and annotator.&lt;/p&gt; &lt;/li&gt; &lt;li&gt; &lt;p&gt;&lt;em&gt;&lt;strong&gt;metadata_by_song.csv&lt;/strong&gt;&lt;/em&gt;: list all the clips by the song. Can be used to create the train/val/test splits to avoid the same song appear in both train and test.&lt;/p&gt; &lt;/li&gt; &lt;li&gt; &lt;p&gt;&lt;em&gt;&lt;strong&gt;scripts/prepare_split.ipynb:&lt;/strong&gt;&lt;/em&gt; the script to create train/val/test splits and save them to csv files.&lt;/p&gt; &lt;/li&gt; &lt;/ul&gt; &lt;p&gt;&amp;nbsp;&lt;/p&gt; &lt;p&gt;&lt;strong&gt;Cite this dataset&lt;/strong&gt;&lt;/p&gt; &lt;pre&gt;&lt;code&gt;@inproceedings{{EMOPIA}, author = {Hung, Hsiao-Tzu and Ching, Joann and Doh, Seungheon and Kim, Nabin and Nam, Juhan and Yang, Yi-Hsuan}, title = {{MOPIA}: A Multi-Modal Pop Piano Dataset For Emotion Recognition and Emotion-based Music Generation}, booktitle = {Proc. Int. Society for Music Information Retrieval Conf.}, year = {2021} }&lt;/code&gt;&lt;/pre&gt;</dct:description>
    <dct:accessRights rdf:resource="http://publications.europa.eu/resource/authority/access-right/PUBLIC"/>
    <dct:accessRights>
      <dct:RightsStatement rdf:about="info:eu-repo/semantics/openAccess">
        <rdfs:label>Open Access</rdfs:label>
      </dct:RightsStatement>
    </dct:accessRights>
    <dcat:distribution>
      <dcat:Distribution>
        <dct:license rdf:resource="https://creativecommons.org/licenses/by/4.0/legalcode"/>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.5090631"/>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.5090631"/>
        <dcat:byteSize>5510182</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/5090631/files/EMOPIA_1.0.zip"/>
        <dcat:mediaType>application/zip</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
</rdf:RDF>
941
491
views
downloads
All versions This version
Views 941702
Downloads 491170
Data volume 10.4 GB936.7 MB
Unique views 697592
Unique downloads 274160

Share

Cite as