There is a newer version of this record available.

Dataset Open Access

VocalSet: A Singing Voice Dataset

Wilkins, Julia; Prem Seetharaman; Alison Wahl; Bryan Pardo


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">singing</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">voice</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">singing dataset</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">music information retrieval</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">vocal technique</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">vowel classification</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">sung voice</subfield>
  </datafield>
  <controlfield tag="005">20200124192550.0</controlfield>
  <controlfield tag="001">1193957</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Northwestern University</subfield>
    <subfield code="a">Prem Seetharaman</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Northwestern University</subfield>
    <subfield code="a">Alison Wahl</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Northwestern University</subfield>
    <subfield code="a">Bryan Pardo</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">2077087366</subfield>
    <subfield code="z">md5:c44f60d34b8724b9a6f6d15e0a3158a9</subfield>
    <subfield code="u">https://zenodo.org/record/1193957/files/VocalSet.zip</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2018-03-08</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire_data</subfield>
    <subfield code="o">oai:zenodo.org:1193957</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Northwestern University</subfield>
    <subfield code="a">Wilkins, Julia</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">VocalSet: A Singing Voice Dataset</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;We present VocalSet, a singing voice dataset consisting of 10.1 hours of monophonic recorded audio of professional singers demonstrating both standard and extended vocal techniques on all 5 vowels. Existing singing voice datasets aim to capture a focused subset of singing voice characteristics, and generally consist of just a few singers. VocalSet contains recordings from 20 different singers (9 male, 11 female) and a range of voice types. &amp;nbsp;VocalSet aims to improve the state of existing singing voice datasets and singing voice research by capturing not only a range of vowels, but also a diverse set of voices on many different vocal techniques, sung in contexts of scales, arpeggios, long tones, and excerpts.&lt;/p&gt;

&lt;p&gt;We have included two .rtf files test_singers and train_singers in which you will find a list of the singers we used to train and test the majority of our deep learning models on.&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isVersionOf</subfield>
    <subfield code="a">10.5281/zenodo.1193956</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.1193957</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">dataset</subfield>
  </datafield>
</record>
4,579
13,568
views
downloads
All versions This version
Views 4,5792,344
Downloads 13,5687,267
Data volume 44.6 TB15.1 TB
Unique views 3,7772,157
Unique downloads 2,8641,548

Share

Cite as