There is a newer version of this record available.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


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nmm##2200000uu#4500</leader>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">piano</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">emotion</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">music</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">midi</subfield>
  </datafield>
  <controlfield tag="005">20210826014043.0</controlfield>
  <controlfield tag="001">5090631</controlfield>
  <datafield tag="711" ind1=" " ind2=" ">
    <subfield code="g">ISMIR</subfield>
    <subfield code="a">International Society for Music Information Retrieval Conference 2021</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Academia Sinica</subfield>
    <subfield code="a">Ching, Joann</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">KAIST</subfield>
    <subfield code="a">Doh, Seungheon</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Georgia Institute of Technology</subfield>
    <subfield code="a">Kim, Nabin</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">KAIST</subfield>
    <subfield code="0">(orcid)0000-0003-2664-2119</subfield>
    <subfield code="a">Nam, Juhan</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Academia Sinica</subfield>
    <subfield code="0">(orcid)0000-0002-2724-6161</subfield>
    <subfield code="a">Yang, Yi-Hsuan</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">5510182</subfield>
    <subfield code="z">md5:8f760ddcc014d144f1e2c5451bf003ac</subfield>
    <subfield code="u">https://zenodo.org/record/5090631/files/EMOPIA_1.0.zip</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="y">Conference website</subfield>
    <subfield code="u">https://ismir2021.ismir.net/</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2021-07-18</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire_data</subfield>
    <subfield code="o">oai:zenodo.org:5090631</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Academia Sinica</subfield>
    <subfield code="a">Hung, Hsiao-Tzu</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">EMOPIA: A Multi-Modal Pop Piano Dataset For Emotion Recognition and Emotion-based Music Generation</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://creativecommons.org/licenses/by/4.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution 4.0 International</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&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;</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isVersionOf</subfield>
    <subfield code="a">10.5281/zenodo.5090630</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.5090631</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">dataset</subfield>
  </datafield>
</record>
937
489
views
downloads
All versions This version
Views 937699
Downloads 489169
Data volume 10.4 GB931.2 MB
Unique views 694589
Unique downloads 273159

Share

Cite as