There is a newer version of this record available.

Dataset Open Access

Clotho dataset

Konstantinos Drossos; Samuel Lipping; Tuomas Virtanen


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="999" ind1="C" ind2="5">
    <subfield code="x">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</subfield>
  </datafield>
  <datafield tag="041" ind1=" " ind2=" ">
    <subfield code="a">eng</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Clotho</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Audio captioning</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Dataset</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Audio processing</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Signal processing</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Machine listening</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Computational auditory scene analysis</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Captioning</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Deep learning</subfield>
  </datafield>
  <controlfield tag="005">20210526154213.0</controlfield>
  <controlfield tag="001">3490684</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Audio Research Group, Faculty of Information Technology and Communication Sciences, Tampere University</subfield>
    <subfield code="a">Samuel Lipping</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Audio Research Group, Faculty of Information Technology and Communication Sciences, Tampere University</subfield>
    <subfield code="0">(orcid)0000-0002-4604-9729</subfield>
    <subfield code="a">Tuomas Virtanen</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">3433217203</subfield>
    <subfield code="z">md5:e3ce88561b317cc3825e8c861cae1ec6</subfield>
    <subfield code="u">https://zenodo.org/record/3490684/files/clotho_audio_development.7z</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">1249726503</subfield>
    <subfield code="z">md5:4569624ccadf96223f19cb59fe4f849f</subfield>
    <subfield code="u">https://zenodo.org/record/3490684/files/clotho_audio_evaluation.7z</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">1002092</subfield>
    <subfield code="z">md5:dd568352389f413d832add5cf604529f</subfield>
    <subfield code="u">https://zenodo.org/record/3490684/files/clotho_captions_development.csv</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">361995</subfield>
    <subfield code="z">md5:1b16b9e57cf7bdb7f13a13802aeb57e2</subfield>
    <subfield code="u">https://zenodo.org/record/3490684/files/clotho_captions_evaluation.csv</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">624848</subfield>
    <subfield code="z">md5:582c18ee47cebdbe33dce1feeab53a56</subfield>
    <subfield code="u">https://zenodo.org/record/3490684/files/clotho_metadata_development.csv</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">225311</subfield>
    <subfield code="z">md5:13946f054d4e1bf48079813aac61bf77</subfield>
    <subfield code="u">https://zenodo.org/record/3490684/files/clotho_metadata_evaluation.csv</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">1864</subfield>
    <subfield code="z">md5:afceb2583a64aea27ed4f14099126af0</subfield>
    <subfield code="u">https://zenodo.org/record/3490684/files/LICENSE</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2019-10-15</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire_data</subfield>
    <subfield code="p">user-audio-captioning</subfield>
    <subfield code="p">user-tut-arg</subfield>
    <subfield code="o">oai:zenodo.org:3490684</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Audio Research Group, Faculty of Information Technology and Communication Sciences, Tampere University</subfield>
    <subfield code="0">(orcid)0000-0002-3605-7127</subfield>
    <subfield code="a">Konstantinos Drossos</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Clotho dataset</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-audio-captioning</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-tut-arg</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">637422</subfield>
    <subfield code="a">Computational Analysis of Everyday Soundscapes</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="a">Other (Attribution)</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;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;</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">url</subfield>
    <subfield code="i">isSupplementedBy</subfield>
    <subfield code="a">https://github.com/audio-captioning/clotho-dataset</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">url</subfield>
    <subfield code="i">isSupplementTo</subfield>
    <subfield code="a">https://arxiv.org/abs/1910.09387</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isVersionOf</subfield>
    <subfield code="a">10.5281/zenodo.3490683</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.3490684</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">dataset</subfield>
  </datafield>
</record>
10,180
14,494
views
downloads
All versions This version
Views 10,1808,917
Downloads 14,49411,978
Data volume 11.4 TB8.9 TB
Unique views 8,9828,002
Unique downloads 7,6506,773

Share

Cite as