There is a newer version of this record available.

Dataset Open Access

Medley-solos-DB: a cross-collection dataset for musical instrument recognition

Lostanlen, Vincent; Cella, Carmine-Emanuele; Bittner, Rachel; Essid, Slim


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.1344103">
    <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.1344103</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.1344103"/>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0003-0580-1651">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0003-0580-1651</dct:identifier>
        <foaf:name>Lostanlen, Vincent</foaf:name>
        <foaf:givenName>Vincent</foaf:givenName>
        <foaf:familyName>Lostanlen</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>New York 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>Cella, Carmine-Emanuele</foaf:name>
        <foaf:givenName>Carmine-Emanuele</foaf:givenName>
        <foaf:familyName>Cella</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Ircam</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0001-7757-2232">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0001-7757-2232</dct:identifier>
        <foaf:name>Bittner, Rachel</foaf:name>
        <foaf:givenName>Rachel</foaf:givenName>
        <foaf:familyName>Bittner</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Spotify Inc.</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>Essid, Slim</foaf:name>
        <foaf:givenName>Slim</foaf:givenName>
        <foaf:familyName>Essid</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Télécom ParisTech</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:title>Medley-solos-DB: a cross-collection dataset for musical instrument recognition</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">2018</dct:issued>
    <dcat:keyword>music</dcat:keyword>
    <dcat:keyword>instrument</dcat:keyword>
    <dcat:keyword>audio</dcat:keyword>
    <dcat:keyword>machine listening</dcat:keyword>
    <dcat:keyword>music information retrieval</dcat:keyword>
    <dcat:keyword>timbre</dcat:keyword>
    <dcat:keyword>machine learning</dcat:keyword>
    <dcat:keyword>classification</dcat:keyword>
    <frapo:isFundedBy rdf:resource="info:eu-repo/grantAgreement/EC/FP7/320959/"/>
    <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">2018-09-28</dct:issued>
    <owl:sameAs rdf:resource="https://zenodo.org/record/1344103"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/1344103</skos:notation>
        <adms:schemeAgency>url</adms:schemeAgency>
      </adms:Identifier>
    </adms:identifier>
    <dct:isVersionOf rdf:resource="https://doi.org/10.5281/zenodo.1344102"/>
    <owl:versionInfo>1.0</owl:versionInfo>
    <dct:description>&lt;p&gt;Medley-solos-DB&lt;br&gt; =============&lt;br&gt; Version 1.0, February 2019.&lt;br&gt; &amp;nbsp;&lt;/p&gt; &lt;p&gt;&amp;nbsp;&lt;/p&gt; &lt;p&gt;Created By&lt;br&gt; --------------&lt;/p&gt; &lt;p&gt;Vincent Lostanlen (1), Carmine-Emanuele Cella (2), Rachel Bittner (3), Slim Essid&amp;nbsp;(4).&lt;br&gt; &lt;br&gt; (1): New York University&lt;br&gt; (2): UC Berkeley&lt;br&gt; (3): Spotify, Inc.&lt;br&gt; (4): T&amp;eacute;l&amp;eacute;com ParisTech&lt;/p&gt; &lt;p&gt;&amp;nbsp;&lt;/p&gt; &lt;p&gt;&lt;br&gt; Description&lt;br&gt; ---------------&lt;/p&gt; &lt;p&gt;&amp;nbsp;&lt;/p&gt; &lt;p&gt;Medley-solos-DB is a cross-collection dataset for automatic musical instrument recognition in solo recordings. It consists of a training set of 3-second audio clips, which are extracted from the MedleyDB dataset of Bittner et al. (ISMIR 2014) as well as a test set set of 3-second clips, which are extracted from the solosDB dataset of Essid et al. (IEEE TASLP 2009). Each of these clips contains a single instrument among a taxonomy of&amp;nbsp;eight: clarinet, distorted electric guitar, female singer,&amp;nbsp;flute,&amp;nbsp;piano,&amp;nbsp;tenor saxophone,&amp;nbsp;trumpet,&amp;nbsp;and&amp;nbsp;violin.&lt;/p&gt; &lt;p&gt;The Medley-solos-DB dataset is the dataset that is used in the benchmarks of musical instrument recognition in the publications of Lostanlen and Cella&amp;nbsp;(ISMIR 2016) and And&amp;eacute;n et al. (IEEE TSP 2019).&lt;/p&gt; &lt;p&gt;&amp;nbsp;&lt;/p&gt; &lt;p&gt;[1] V. Lostanlen, C.E. Cella. Deep convolutional networks on the pitch spiral for musical instrument recognition. Proceedings of the International Society for Music Information Retrieval Conference&amp;nbsp;(ISMIR), 2016.&lt;/p&gt; &lt;p&gt;[2] J. And&amp;eacute;n, V. Lostanlen S. Mallat. Joint time-frequency scattering. IEEE Transactions in Signal Processing. 2019, to appear.&lt;/p&gt; &lt;p&gt;&amp;nbsp;&lt;/p&gt; &lt;p&gt;&lt;br&gt; Data Files&lt;br&gt; --------------&lt;/p&gt; &lt;p&gt;The Medley-solos-DB&amp;nbsp;contains 21572&amp;nbsp;audio clips as WAV files, sampled at 44.1&amp;nbsp;kHz, with a single channel (mono), at a bit depth of 32. Every audio clip has a fixed duration of&amp;nbsp;2972 milliseconds, that is, 65536 discrete-time samples.&lt;/p&gt; &lt;p&gt;Every audio file has a name of the form:&lt;/p&gt; &lt;p&gt;Medley-solos-DB_SUBSET-INSTRUMENTID_UUID.wav&lt;/p&gt; &lt;p&gt;&amp;nbsp;&lt;/p&gt; &lt;p&gt;For example:&lt;/p&gt; &lt;p&gt;Medley-solos-DB_test-0_0a282672-c22c-59ff-faaa-ff9eb73fc8e6.wav&lt;/p&gt; &lt;p&gt;corresponds to the snippet whose universally unique identifier (UUID) is&amp;nbsp;0a282672-c22c-59ff-faaa-ff9eb73fc8e6, contains clarinet sounds (clarinet has instrument id equal to 0), and belongs to the test set.&lt;/p&gt; &lt;p&gt;&amp;nbsp;&lt;/p&gt; &lt;p&gt;&lt;br&gt; Metadata Files&lt;br&gt; -------------------&lt;/p&gt; &lt;p&gt;The&amp;nbsp;Medley-solos-DB_metadata is a CSV file containing 21572 rows (one for each audio clip) and five&amp;nbsp;columns:&lt;/p&gt; &lt;p&gt;1. subset: either &amp;quot;training&amp;quot;, &amp;quot;validation&amp;quot;, or &amp;quot;test&amp;quot;&lt;/p&gt; &lt;p&gt;2. instrument: tag in Medley-DB taxonomy, such as&amp;nbsp;&amp;quot;clarinet&amp;quot;, &amp;quot;distorted electric guitar&amp;quot;, etc.&lt;/p&gt; &lt;p&gt;3. instrument id: integer from 0 to 7. There is a one-to-one&amp;nbsp;between &amp;quot;instrument&amp;quot; (string format) and &amp;quot;instrument id&amp;quot; (integer). We provide both for convenience.&lt;/p&gt; &lt;p&gt;4. track id: integer from 0 to 226. The track and artist names are anonymized.&lt;/p&gt; &lt;p&gt;5. UUID: universally unique identifier. Assigned and random, and different for every row.&lt;/p&gt; &lt;p&gt;&amp;nbsp;&lt;/p&gt; &lt;p&gt;The list of instrument classes is:&lt;/p&gt; &lt;p&gt;0. clarinet&lt;/p&gt; &lt;p&gt;1. distorted electric guitar&lt;/p&gt; &lt;p&gt;2. female singer&lt;/p&gt; &lt;p&gt;3. flute&lt;/p&gt; &lt;p&gt;4. piano&lt;/p&gt; &lt;p&gt;5. tenor saxophone&lt;/p&gt; &lt;p&gt;6. trumpet&lt;/p&gt; &lt;p&gt;7. violin&lt;/p&gt; &lt;p&gt;&amp;nbsp;&lt;/p&gt; &lt;p&gt;&lt;br&gt; Please acknowledge Medley-solos-DB&amp;nbsp;in academic research&lt;br&gt; ---------------------------------------------------------------------------------&lt;/p&gt; &lt;p&gt;When Medley-solos-DB&amp;nbsp;is used for academic research, we would highly appreciate it if&amp;nbsp; scientific publications of works partly based on this dataset cite the following publication:&lt;/p&gt; &lt;p&gt;V. Lostanlen, C.E. Cella. Deep convolutional networks on the pitch spiral for musical instrument recognition. Proceedings of the International Society for Music Information Retrieval Conference&amp;nbsp;(ISMIR), 2016.&lt;/p&gt; &lt;p&gt;The creation of this dataset was supported by ERC InvariantClass grant&amp;nbsp;320959.&lt;/p&gt; &lt;p&gt;&amp;nbsp;&lt;/p&gt; &lt;p&gt;&lt;br&gt; Conditions of Use&lt;br&gt; ------------------------&lt;/p&gt; &lt;p&gt;Dataset created by Vincent Lostanlen, Rachel Bittner, and Slim Essid, as a derivative work of Medley-DB and solos-Db.&lt;/p&gt; &lt;p&gt;The Medley-solos-DB&amp;nbsp;dataset is offered free of charge under the terms of the Creative Commons Attribution 4.0 International (CC BY 4.0) license:&lt;br&gt; https://creativecommons.org/licenses/by/4.0/&lt;/p&gt; &lt;p&gt;The dataset and its contents are made available on an &amp;quot;as is&amp;quot; basis and without warranties of any kind, including without limitation satisfactory quality and conformity, merchantability, fitness for a particular purpose, accuracy or&amp;nbsp;completeness, or absence of errors. Subject to any liability that may not be excluded or limited by law, the authors are&amp;nbsp;not liable for, and expressly exclude&amp;nbsp;all liability for, loss or damage however and whenever caused to anyone by any use of the Medley-solos-DB&amp;nbsp;dataset or any part of it.&lt;/p&gt; &lt;p&gt;&amp;nbsp;&lt;/p&gt; &lt;p&gt;&lt;br&gt; Feedback&lt;br&gt; -------------&lt;/p&gt; &lt;p&gt;Please help us improve Medley-solos-DB&amp;nbsp;by sending your feedback to:&lt;br&gt; vincent.lostanlen@nyu.edu&lt;/p&gt; &lt;p&gt;In case of a problem, please include as many details as possible.&lt;/p&gt; &lt;p&gt;&amp;nbsp;&lt;/p&gt; &lt;p&gt;&amp;nbsp;&lt;/p&gt; &lt;p&gt;Acknowledgement&lt;br&gt; -------------------------&lt;br&gt; We thank all artists, recording engineers, curators, and annotators of both MedleyDB and solosDb.&lt;/p&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.1344103"/>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL>https://doi.org/10.5281/zenodo.1344103</dcat:accessURL>
        <dcat:byteSize>1276169</dcat:byteSize>
        <dcat:downloadURL>https://zenodo.org/record/1344103/files/Medley-solos-DB_metadata.csv</dcat:downloadURL>
        <dcat:mediaType>text/csv</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL>https://doi.org/10.5281/zenodo.1344103</dcat:accessURL>
        <dcat:byteSize>6663778174</dcat:byteSize>
        <dcat:downloadURL>https://zenodo.org/record/1344103/files/Medley-solos-DB.zip</dcat:downloadURL>
        <dcat:mediaType>application/zip</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
  <foaf:Project rdf:about="info:eu-repo/grantAgreement/EC/FP7/320959/">
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">320959</dct:identifier>
    <dct:title>Invariant Representations for High-Dimensional Signal Classifications</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>
2,022
1,849
views
downloads
All versions This version
Views 2,0221,124
Downloads 1,849613
Data volume 8.4 TB3.0 TB
Unique views 1,6921,017
Unique downloads 1,108387

Share

Cite as