There is a newer version of this record available.

Dataset Open Access

Clotho dataset

Konstantinos Drossos; Samuel Lipping; Tuomas Virtanen


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.3490684">
    <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.3490684</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.3490684"/>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0002-3605-7127">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0002-3605-7127</dct:identifier>
        <foaf:name>Konstantinos Drossos</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Audio Research Group, Faculty of Information Technology and Communication Sciences, Tampere University</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>Samuel Lipping</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Audio Research Group, Faculty of Information Technology and Communication Sciences, Tampere University</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0002-4604-9729">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0002-4604-9729</dct:identifier>
        <foaf:name>Tuomas Virtanen</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Audio Research Group, Faculty of Information Technology and Communication Sciences, Tampere University</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:title>Clotho dataset</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">2019</dct:issued>
    <dcat:keyword>Clotho</dcat:keyword>
    <dcat:keyword>Audio captioning</dcat:keyword>
    <dcat:keyword>Dataset</dcat:keyword>
    <dcat:keyword>Audio processing</dcat:keyword>
    <dcat:keyword>Signal processing</dcat:keyword>
    <dcat:keyword>Machine listening</dcat:keyword>
    <dcat:keyword>Computational auditory scene analysis</dcat:keyword>
    <dcat:keyword>Captioning</dcat:keyword>
    <dcat:keyword>Deep learning</dcat:keyword>
    <frapo:isFundedBy rdf:resource="info:eu-repo/grantAgreement/EC/H2020/637422/"/>
    <schema:funder>
      <foaf:Organization>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">10.13039/501100000780</dct:identifier>
        <foaf:name>European Commission</foaf:name>
      </foaf:Organization>
    </schema:funder>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2019-10-15</dct:issued>
    <dct:language rdf:resource="http://publications.europa.eu/resource/authority/language/ENG"/>
    <owl:sameAs rdf:resource="https://zenodo.org/record/3490684"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/3490684</skos:notation>
        <adms:schemeAgency>url</adms:schemeAgency>
      </adms:Identifier>
    </adms:identifier>
    <dct:relation rdf:resource="https://github.com/audio-captioning/clotho-dataset"/>
    <dct:relation rdf:resource="https://arxiv.org/abs/1910.09387"/>
    <dct:isVersionOf rdf:resource="https://doi.org/10.5281/zenodo.3490683"/>
    <dct:isPartOf rdf:resource="https://zenodo.org/communities/audio-captioning"/>
    <dct:isPartOf rdf:resource="https://zenodo.org/communities/tut-arg"/>
    <owl:versionInfo>1.0</owl:versionInfo>
    <dct:description>&lt;p&gt;Clotho is a novel audio captioning dataset, consisting of&amp;nbsp;4981 audio samples, and each audio sample has five captions (a total of&amp;nbsp;24 905 captions).&amp;nbsp;Audio samples are of 15 to 30 s duration and captions are eight to 20 words long.&amp;nbsp;&lt;/p&gt; &lt;p&gt;Clotho is thoroughly described in our paper:&lt;/p&gt; &lt;p&gt;&lt;em&gt;K. Drossos, S. Lipping and T. Virtanen, &amp;quot;Clotho: an Audio Captioning Dataset,&amp;quot; IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, 2020, pp. 736-740, doi: 10.1109/ICASSP40776.2020.9052990.&lt;/em&gt;&lt;/p&gt; &lt;p&gt;available online at:&amp;nbsp;&lt;a href="https://arxiv.org/abs/1910.09387"&gt;https://arxiv.org/abs/1910.09387&lt;/a&gt;&amp;nbsp;and at:&amp;nbsp;&lt;a href="https://ieeexplore.ieee.org/document/9052990"&gt;https://ieeexplore.ieee.org/document/9052990&lt;/a&gt;&amp;nbsp;&lt;/p&gt; &lt;p&gt;&lt;strong&gt;If you use Clotho, please cite our paper.&lt;/strong&gt;&lt;/p&gt; &lt;p&gt;&amp;nbsp;&lt;/p&gt; &lt;p&gt;&lt;strong&gt;To use the dataset, you can use our code at:&lt;/strong&gt;&amp;nbsp;&lt;a href="https://github.com/audio-captioning/clotho-dataset"&gt;https://github.com/audio-captioning/clotho-dataset&lt;/a&gt;&amp;nbsp;&lt;/p&gt; &lt;p&gt;&amp;nbsp;&lt;/p&gt; &lt;p&gt;These are the files for the development and evaluation splits of Clotho dataset.&amp;nbsp;&lt;/p&gt; &lt;p&gt;--------------------------------------------------------------------------------------------------------&lt;/p&gt; &lt;p&gt;&lt;strong&gt;== Usage ==&lt;/strong&gt;&lt;/p&gt; &lt;p&gt;To use the dataset you have to:&lt;/p&gt; &lt;ol&gt; &lt;li&gt;Download the audio files:&amp;nbsp;clotho_audio_development.7z and&amp;nbsp;clotho_audio_evalution.7z&lt;/li&gt; &lt;li&gt;Download the files with the captions:&amp;nbsp;clotho_captions_development.csv and&amp;nbsp;clotho_captions_evaluation.csv&lt;/li&gt; &lt;li&gt;Download the files with the associated metadata:&amp;nbsp;clotho_metadata_development.csv and&amp;nbsp;clotho_metadata_evaluation.csv&lt;/li&gt; &lt;li&gt;Extract the audio files&lt;/li&gt; &lt;li&gt;Then you can use each audio file with its corresponding captions&lt;/li&gt; &lt;/ol&gt; &lt;p&gt;--------------------------------------------------------------------------------------------------------&lt;/p&gt; &lt;p&gt;&lt;strong&gt;== License&amp;nbsp;==&lt;/strong&gt;&lt;/p&gt; &lt;p&gt;The audio files in the archives:&lt;/p&gt; &lt;ul&gt; &lt;li&gt;clotho_audio_development.7z and&lt;/li&gt; &lt;li&gt;clotho_audio_evalution.7z&lt;/li&gt; &lt;/ul&gt; &lt;p&gt;and the associated meta-data in the CSV files:&lt;/p&gt; &lt;ul&gt; &lt;li&gt;clotho_metadata_development.csv&lt;/li&gt; &lt;li&gt;clotho_metadata_evaluation.csv&lt;/li&gt; &lt;/ul&gt; &lt;p&gt;are under the corresponding licences (&lt;strong&gt;&lt;em&gt;mostly CreativeCommons with attribution&lt;/em&gt;&lt;/strong&gt;) of Freesound [1] platform, mentioned explicitly in the CSV files for each of the audio files. That is, each audio file in the 7z archives is listed in the CSV files with the meta-data. The meta-data for each file are:&amp;nbsp;&lt;/p&gt; &lt;ul&gt; &lt;li&gt;File name&lt;/li&gt; &lt;li&gt;Keywords&lt;/li&gt; &lt;li&gt;URL for the original audio file&lt;/li&gt; &lt;li&gt;Start and ending samples for the excerpt that is used in the Clotho dataset&lt;/li&gt; &lt;li&gt;Uploader/user in the Freesound platform&amp;nbsp;(manufacturer)&lt;/li&gt; &lt;li&gt;Link to the licence of the file&lt;/li&gt; &lt;/ul&gt; &lt;p&gt;The captions in the files:&lt;/p&gt; &lt;ul&gt; &lt;li&gt;clotho_captions_development.csv&lt;/li&gt; &lt;li&gt;clotho_captions_evaluation.csv&lt;/li&gt; &lt;/ul&gt; &lt;p&gt;are under the Tampere University licence, described in the LICENCE file (&lt;strong&gt;&lt;em&gt;mainly a non-commercial with attribution licence&lt;/em&gt;&lt;/strong&gt;).&amp;nbsp;&lt;/p&gt; &lt;p&gt;--------------------------------------------------------------------------------------------------------&lt;/p&gt; &lt;p&gt;&lt;strong&gt;== References ==&lt;/strong&gt;&lt;br&gt; [1]&amp;nbsp;Frederic Font, Gerard Roma, and Xavier Serra. 2013. Freesound technical demo. In Proceedings of the 21st ACM international conference on Multimedia (MM &amp;#39;13). ACM, New York, NY, USA, 411-412. DOI: https://doi.org/10.1145/2502081.2502245&lt;/p&gt;</dct:description>
    <dct:description>{"references": ["Frederic Font, Gerard Roma, and Xavier Serra. 2013. Freesound technical demo. In Proceedings of the 21st ACM international conference on Multimedia (MM '13). ACM, New York, NY, USA, 411-412. DOI: https://doi.org/10.1145/2502081.2502245"]}</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>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3490684"/>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3490684">https://doi.org/10.5281/zenodo.3490684</dcat:accessURL>
        <dcat:byteSize>3433217203</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/3490684/files/clotho_audio_development.7z">https://zenodo.org/record/3490684/files/clotho_audio_development.7z</dcat:downloadURL>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3490684">https://doi.org/10.5281/zenodo.3490684</dcat:accessURL>
        <dcat:byteSize>1249726503</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/3490684/files/clotho_audio_evaluation.7z">https://zenodo.org/record/3490684/files/clotho_audio_evaluation.7z</dcat:downloadURL>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3490684">https://doi.org/10.5281/zenodo.3490684</dcat:accessURL>
        <dcat:byteSize>1002092</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/3490684/files/clotho_captions_development.csv">https://zenodo.org/record/3490684/files/clotho_captions_development.csv</dcat:downloadURL>
        <dcat:mediaType>text/csv</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3490684">https://doi.org/10.5281/zenodo.3490684</dcat:accessURL>
        <dcat:byteSize>361995</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/3490684/files/clotho_captions_evaluation.csv">https://zenodo.org/record/3490684/files/clotho_captions_evaluation.csv</dcat:downloadURL>
        <dcat:mediaType>text/csv</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3490684">https://doi.org/10.5281/zenodo.3490684</dcat:accessURL>
        <dcat:byteSize>624848</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/3490684/files/clotho_metadata_development.csv">https://zenodo.org/record/3490684/files/clotho_metadata_development.csv</dcat:downloadURL>
        <dcat:mediaType>text/csv</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3490684">https://doi.org/10.5281/zenodo.3490684</dcat:accessURL>
        <dcat:byteSize>225311</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/3490684/files/clotho_metadata_evaluation.csv">https://zenodo.org/record/3490684/files/clotho_metadata_evaluation.csv</dcat:downloadURL>
        <dcat:mediaType>text/csv</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3490684">https://doi.org/10.5281/zenodo.3490684</dcat:accessURL>
        <dcat:byteSize>1864</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/3490684/files/LICENSE">https://zenodo.org/record/3490684/files/LICENSE</dcat:downloadURL>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
  <foaf:Project rdf:about="info:eu-repo/grantAgreement/EC/H2020/637422/">
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">637422</dct:identifier>
    <dct:title>Computational Analysis of Everyday Soundscapes</dct:title>
    <frapo:isAwardedBy>
      <foaf:Organization>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">10.13039/501100000780</dct:identifier>
        <foaf:name>European Commission</foaf:name>
      </foaf:Organization>
    </frapo:isAwardedBy>
  </foaf:Project>
</rdf:RDF>
10,189
14,510
views
downloads
All versions This version
Views 10,1898,920
Downloads 14,51011,980
Data volume 11.4 TB8.9 TB
Unique views 8,9898,005
Unique downloads 7,6576,775

Share

Cite as