LJSing: large-scale singing voice corpus of single Japanese singer

Takuto Fujimura; Takashi Nose; Akinori Ito

doi:10.1109/GCCE50665.2020.9291704

LJSing: large-scale singing voice corpus of single Japanese singer

Takuto Fujimura, Takashi Nose, Akinori Ito

ENG - Communications Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper describes the construction of the LJSing, a large-scale Japanese singing voice corpus by a single female singer for singing voice synthesis based on statistical methods. Singing voice synthesis systems based on machine learning have been widely studied. However, most Japanese singing voice corpora are not enough for the training of recent deep-learningbased synthesis. Furthermore, those corpora were designed without phonetic and prosodic balance. Therefore, we recorded and labeled a five-hour phonetically and prosodically balanced singing corpus sung by a Japanese singer. The corpus consists of two data sets, SongSet and PhraseSet, which are constructed based on songs and phrases, respectively.

Original language	English
Title of host publication	2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	364-365
Number of pages	2
ISBN (Electronic)	9781728198026
DOIs	https://doi.org/10.1109/GCCE50665.2020.9291704
Publication status	Published - 2020 Oct 13
Event	9th IEEE Global Conference on Consumer Electronics, GCCE 2020 - Kobe, Japan Duration: 2020 Oct 13 → 2020 Oct 16

Publication series

Name	2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020

Conference

Conference	9th IEEE Global Conference on Consumer Electronics, GCCE 2020
Country/Territory	Japan
City	Kobe
Period	20/10/13 → 20/10/16

Keywords

Context balance
Deep learning
Singing voice corpus
Singing voice synthesis

ASJC Scopus subject areas

Signal Processing
Electrical and Electronic Engineering
Media Technology
Instrumentation
Computer Networks and Communications
Computer Vision and Pattern Recognition

Access to Document

10.1109/GCCE50665.2020.9291704

Cite this

Fujimura, T., Nose, T., & Ito, A. (2020). LJSing: large-scale singing voice corpus of single Japanese singer. In 2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020 (pp. 364-365). [9291704] (2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/GCCE50665.2020.9291704

LJSing: large-scale singing voice corpus of single Japanese singer. / Fujimura, Takuto; Nose, Takashi ; Ito, Akinori.
2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020. Institute of Electrical and Electronics Engineers Inc., 2020. p. 364-365 9291704 (2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Fujimura, T, Nose, T & Ito, A 2020, LJSing: large-scale singing voice corpus of single Japanese singer. in 2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020., 9291704, 2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020, Institute of Electrical and Electronics Engineers Inc., pp. 364-365, 9th IEEE Global Conference on Consumer Electronics, GCCE 2020, Kobe, Japan, 20/10/13. https://doi.org/10.1109/GCCE50665.2020.9291704

@inproceedings{1ef214cf4c2b4fc987fb1f1ff2bb86c3,

title = "LJSing: large-scale singing voice corpus of single Japanese singer",

abstract = "This paper describes the construction of the LJSing, a large-scale Japanese singing voice corpus by a single female singer for singing voice synthesis based on statistical methods. Singing voice synthesis systems based on machine learning have been widely studied. However, most Japanese singing voice corpora are not enough for the training of recent deep-learningbased synthesis. Furthermore, those corpora were designed without phonetic and prosodic balance. Therefore, we recorded and labeled a five-hour phonetically and prosodically balanced singing corpus sung by a Japanese singer. The corpus consists of two data sets, SongSet and PhraseSet, which are constructed based on songs and phrases, respectively. ",

keywords = "Context balance, Deep learning, Singing voice corpus, Singing voice synthesis",

author = "Takuto Fujimura and Takashi Nose and Akinori Ito",

note = "Funding Information: A part of this work was supported by the JST COI Grant Number JPMJCE1303. Publisher Copyright: {\textcopyright} 2020 IEEE.; 9th IEEE Global Conference on Consumer Electronics, GCCE 2020 ; Conference date: 13-10-2020 Through 16-10-2020",

year = "2020",

month = oct,

day = "13",

doi = "10.1109/GCCE50665.2020.9291704",

language = "English",

series = "2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "364--365",

booktitle = "2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020",

}

TY - GEN

T1 - LJSing

T2 - 9th IEEE Global Conference on Consumer Electronics, GCCE 2020

AU - Fujimura, Takuto

AU - Nose, Takashi

AU - Ito, Akinori

PY - 2020/10/13

Y1 - 2020/10/13

N2 - This paper describes the construction of the LJSing, a large-scale Japanese singing voice corpus by a single female singer for singing voice synthesis based on statistical methods. Singing voice synthesis systems based on machine learning have been widely studied. However, most Japanese singing voice corpora are not enough for the training of recent deep-learningbased synthesis. Furthermore, those corpora were designed without phonetic and prosodic balance. Therefore, we recorded and labeled a five-hour phonetically and prosodically balanced singing corpus sung by a Japanese singer. The corpus consists of two data sets, SongSet and PhraseSet, which are constructed based on songs and phrases, respectively.

AB - This paper describes the construction of the LJSing, a large-scale Japanese singing voice corpus by a single female singer for singing voice synthesis based on statistical methods. Singing voice synthesis systems based on machine learning have been widely studied. However, most Japanese singing voice corpora are not enough for the training of recent deep-learningbased synthesis. Furthermore, those corpora were designed without phonetic and prosodic balance. Therefore, we recorded and labeled a five-hour phonetically and prosodically balanced singing corpus sung by a Japanese singer. The corpus consists of two data sets, SongSet and PhraseSet, which are constructed based on songs and phrases, respectively.

KW - Context balance

KW - Deep learning

KW - Singing voice corpus

KW - Singing voice synthesis

UR - http://www.scopus.com/inward/record.url?scp=85099378228&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85099378228&partnerID=8YFLogxK

U2 - 10.1109/GCCE50665.2020.9291704

DO - 10.1109/GCCE50665.2020.9291704

M3 - Conference contribution

AN - SCOPUS:85099378228

T3 - 2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020

SP - 364

EP - 365

BT - 2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 13 October 2020 through 16 October 2020

ER -

LJSing: large-scale singing voice corpus of single Japanese singer

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this