There is a newer version of this record available.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

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.  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.

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.

Files (2.1 GB)
Name Size
2.1 GB Download
All versions This version
Views 10,1205,588
Downloads 15,7408,434
Data volume 50.9 TB17.5 TB
Unique views 8,2335,075
Unique downloads 4,3202,389


Cite as