There is a newer version of this record available.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


JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/9cc0970e-c7d9-4b5c-8e7c-22abe0fcdbf1/VocalSet.zip"
      }, 
      "checksum": "md5:c44f60d34b8724b9a6f6d15e0a3158a9", 
      "bucket": "9cc0970e-c7d9-4b5c-8e7c-22abe0fcdbf1", 
      "key": "VocalSet.zip", 
      "type": "zip", 
      "size": 2077087366
    }
  ], 
  "owners": [
    43054
  ], 
  "doi": "10.5281/zenodo.1193957", 
  "stats": {
    "version_unique_downloads": 2864.0, 
    "unique_views": 2157.0, 
    "views": 2344.0, 
    "version_views": 4579.0, 
    "unique_downloads": 1548.0, 
    "version_unique_views": 3777.0, 
    "volume": 15094193888722.0, 
    "version_downloads": 13568.0, 
    "downloads": 7267.0, 
    "version_volume": 44595689751503.0
  }, 
  "links": {
    "doi": "https://doi.org/10.5281/zenodo.1193957", 
    "conceptdoi": "https://doi.org/10.5281/zenodo.1193956", 
    "bucket": "https://zenodo.org/api/files/9cc0970e-c7d9-4b5c-8e7c-22abe0fcdbf1", 
    "conceptbadge": "https://zenodo.org/badge/doi/10.5281/zenodo.1193956.svg", 
    "html": "https://zenodo.org/record/1193957", 
    "latest_html": "https://zenodo.org/record/1442513", 
    "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.1193957.svg", 
    "latest": "https://zenodo.org/api/records/1442513"
  }, 
  "conceptdoi": "10.5281/zenodo.1193956", 
  "created": "2018-03-08T06:24:19.837624+00:00", 
  "updated": "2020-01-24T19:25:50.644975+00:00", 
  "conceptrecid": "1193956", 
  "revision": 8, 
  "id": 1193957, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.5281/zenodo.1193957", 
    "description": "<p>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. &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.</p>\n\n<p>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.</p>", 
    "license": {
      "id": "CC-BY-4.0"
    }, 
    "title": "VocalSet: A Singing Voice Dataset", 
    "relations": {
      "version": [
        {
          "count": 3, 
          "index": 0, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "1193956"
          }, 
          "is_last": false, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "1442513"
          }
        }
      ]
    }, 
    "version": "1.0", 
    "keywords": [
      "singing", 
      "voice", 
      "singing dataset", 
      "music information retrieval", 
      "vocal technique", 
      "vowel classification", 
      "sung voice"
    ], 
    "publication_date": "2018-03-08", 
    "creators": [
      {
        "affiliation": "Northwestern University", 
        "name": "Wilkins, Julia"
      }, 
      {
        "affiliation": "Northwestern University", 
        "name": "Prem Seetharaman"
      }, 
      {
        "affiliation": "Northwestern University", 
        "name": "Alison Wahl"
      }, 
      {
        "affiliation": "Northwestern University", 
        "name": "Bryan Pardo"
      }
    ], 
    "access_right": "open", 
    "resource_type": {
      "type": "dataset", 
      "title": "Dataset"
    }, 
    "related_identifiers": [
      {
        "scheme": "doi", 
        "identifier": "10.5281/zenodo.1193956", 
        "relation": "isVersionOf"
      }
    ]
  }
}
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