There is a newer version of this record available.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

DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="" xmlns="" xsi:schemaLocation="">
  <identifier identifierType="DOI">10.5281/zenodo.1193957</identifier>
      <creatorName>Wilkins, Julia</creatorName>
      <affiliation>Northwestern University</affiliation>
      <creatorName>Prem Seetharaman</creatorName>
      <affiliation>Northwestern University</affiliation>
      <creatorName>Alison Wahl</creatorName>
      <affiliation>Northwestern University</affiliation>
      <creatorName>Bryan Pardo</creatorName>
      <affiliation>Northwestern University</affiliation>
    <title>VocalSet: A Singing Voice Dataset</title>
    <subject>singing dataset</subject>
    <subject>music information retrieval</subject>
    <subject>vocal technique</subject>
    <subject>vowel classification</subject>
    <subject>sung voice</subject>
    <date dateType="Issued">2018-03-08</date>
  <resourceType resourceTypeGeneral="Dataset"/>
    <alternateIdentifier alternateIdentifierType="url"></alternateIdentifier>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.1193956</relatedIdentifier>
    <rights rightsURI="">Creative Commons Attribution 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
    <description descriptionType="Abstract">&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;</description>
All versions This version
Views 4,5702,338
Downloads 13,5677,267
Data volume 44.6 TB15.1 TB
Unique views 3,7692,151
Unique downloads 2,8631,548


Cite as