Rap Lyrics Generation Using Vowel GAN

Tomoya Miyano; Hiroaki Saito

doi:10.1007/978-981-15-6168-9_26

Rap Lyrics Generation Using Vowel GAN

Tomoya Miyano, Hiroaki Saito

Department of Information and Computer Science

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

Abstract

Despite the success of recent rap and poetry generations using neural models, many of them do not consider vowels of the entire lyrics. Also, in many cases it is virtually impossible to generate completely new lyrics, because only existing rap lyrics are used as data sets. This paper proposes a new method of rap lyrics generation using a large amount of text such as novels in addition to rap lyrics. We divided the generation of rap lyrics into two steps; first, Generative Adversalial Net (GAN) generates rhymes and flows. Second, sequence-to-sequence converts them into rap lyrics. In addition, this method refers to the generation style of rap songs. In other words, they determine the music and rhythm first and apply the words second. We evaluated our method based on BLEU that can be measured mechanically.

Original language	English
Title of host publication	Computational Linguistics - 16th International Conference of the Pacific Association for Computational Linguistics, PACLING 2019, Revised Selected Papers
Editors	Le-Minh Nguyen, Satoshi Tojo, Xuan-Hieu Phan, Kôiti Hasida
Publisher	Springer
Pages	307-318
Number of pages	12
ISBN (Print)	9789811561672
DOIs	https://doi.org/10.1007/978-981-15-6168-9_26
Publication status	Published - 2020
Event	16th International Conference of the Pacific Association for Computational Linguistics, PACLING 2019 - Hanoi, Viet Nam Duration: 2019 Oct 11 → 2019 Oct 13

Publication series

Name	Communications in Computer and Information Science
Volume	1215 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	16th International Conference of the Pacific Association for Computational Linguistics, PACLING 2019
Country/Territory	Viet Nam
City	Hanoi
Period	19/10/11 → 19/10/13

Keywords

GAN
Rap song
Sequence-to-sequence

ASJC Scopus subject areas

Computer Science(all)
Mathematics(all)

Access to Document

10.1007/978-981-15-6168-9_26

Cite this

Miyano, T., & Saito, H. (2020). Rap Lyrics Generation Using Vowel GAN. In L-M. Nguyen, S. Tojo, X-H. Phan, & K. Hasida (Eds.), Computational Linguistics - 16th International Conference of the Pacific Association for Computational Linguistics, PACLING 2019, Revised Selected Papers (pp. 307-318). (Communications in Computer and Information Science; Vol. 1215 CCIS). Springer. https://doi.org/10.1007/978-981-15-6168-9_26

Rap Lyrics Generation Using Vowel GAN. / Miyano, Tomoya; Saito, Hiroaki.

Computational Linguistics - 16th International Conference of the Pacific Association for Computational Linguistics, PACLING 2019, Revised Selected Papers. ed. / Le-Minh Nguyen; Satoshi Tojo; Xuan-Hieu Phan; Kôiti Hasida. Springer, 2020. p. 307-318 (Communications in Computer and Information Science; Vol. 1215 CCIS).

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

Miyano, T & Saito, H 2020, Rap Lyrics Generation Using Vowel GAN. in L-M Nguyen, S Tojo, X-H Phan & K Hasida (eds), Computational Linguistics - 16th International Conference of the Pacific Association for Computational Linguistics, PACLING 2019, Revised Selected Papers. Communications in Computer and Information Science, vol. 1215 CCIS, Springer, pp. 307-318, 16th International Conference of the Pacific Association for Computational Linguistics, PACLING 2019, Hanoi, Viet Nam, 19/10/11. https://doi.org/10.1007/978-981-15-6168-9_26

Miyano T, Saito H. Rap Lyrics Generation Using Vowel GAN. In Nguyen L-M, Tojo S, Phan X-H, Hasida K, editors, Computational Linguistics - 16th International Conference of the Pacific Association for Computational Linguistics, PACLING 2019, Revised Selected Papers. Springer. 2020. p. 307-318. (Communications in Computer and Information Science). doi: 10.1007/978-981-15-6168-9_26

Miyano, Tomoya ; Saito, Hiroaki. / Rap Lyrics Generation Using Vowel GAN. Computational Linguistics - 16th International Conference of the Pacific Association for Computational Linguistics, PACLING 2019, Revised Selected Papers. editor / Le-Minh Nguyen ; Satoshi Tojo ; Xuan-Hieu Phan ; Kôiti Hasida. Springer, 2020. pp. 307-318 (Communications in Computer and Information Science).

@inproceedings{1a6afa1e26244316aa4bdf0ca9827b2f,

title = "Rap Lyrics Generation Using Vowel GAN",

abstract = "Despite the success of recent rap and poetry generations using neural models, many of them do not consider vowels of the entire lyrics. Also, in many cases it is virtually impossible to generate completely new lyrics, because only existing rap lyrics are used as data sets. This paper proposes a new method of rap lyrics generation using a large amount of text such as novels in addition to rap lyrics. We divided the generation of rap lyrics into two steps; first, Generative Adversalial Net (GAN) generates rhymes and flows. Second, sequence-to-sequence converts them into rap lyrics. In addition, this method refers to the generation style of rap songs. In other words, they determine the music and rhythm first and apply the words second. We evaluated our method based on BLEU that can be measured mechanically.",

keywords = "GAN, Rap song, Sequence-to-sequence",

author = "Tomoya Miyano and Hiroaki Saito",

note = "Publisher Copyright: {\textcopyright} 2020, Springer Nature Singapore Pte Ltd. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.; 16th International Conference of the Pacific Association for Computational Linguistics, PACLING 2019 ; Conference date: 11-10-2019 Through 13-10-2019",

year = "2020",

doi = "10.1007/978-981-15-6168-9_26",

language = "English",

isbn = "9789811561672",

series = "Communications in Computer and Information Science",

publisher = "Springer",

pages = "307--318",

editor = "Le-Minh Nguyen and Satoshi Tojo and Xuan-Hieu Phan and K{\^o}iti Hasida",

booktitle = "Computational Linguistics - 16th International Conference of the Pacific Association for Computational Linguistics, PACLING 2019, Revised Selected Papers",

}

TY - GEN

T1 - Rap Lyrics Generation Using Vowel GAN

AU - Miyano, Tomoya

AU - Saito, Hiroaki

PY - 2020

Y1 - 2020

N2 - Despite the success of recent rap and poetry generations using neural models, many of them do not consider vowels of the entire lyrics. Also, in many cases it is virtually impossible to generate completely new lyrics, because only existing rap lyrics are used as data sets. This paper proposes a new method of rap lyrics generation using a large amount of text such as novels in addition to rap lyrics. We divided the generation of rap lyrics into two steps; first, Generative Adversalial Net (GAN) generates rhymes and flows. Second, sequence-to-sequence converts them into rap lyrics. In addition, this method refers to the generation style of rap songs. In other words, they determine the music and rhythm first and apply the words second. We evaluated our method based on BLEU that can be measured mechanically.

AB - Despite the success of recent rap and poetry generations using neural models, many of them do not consider vowels of the entire lyrics. Also, in many cases it is virtually impossible to generate completely new lyrics, because only existing rap lyrics are used as data sets. This paper proposes a new method of rap lyrics generation using a large amount of text such as novels in addition to rap lyrics. We divided the generation of rap lyrics into two steps; first, Generative Adversalial Net (GAN) generates rhymes and flows. Second, sequence-to-sequence converts them into rap lyrics. In addition, this method refers to the generation style of rap songs. In other words, they determine the music and rhythm first and apply the words second. We evaluated our method based on BLEU that can be measured mechanically.

KW - GAN

KW - Rap song

KW - Sequence-to-sequence

UR - http://www.scopus.com/inward/record.url?scp=85088502670&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85088502670&partnerID=8YFLogxK

U2 - 10.1007/978-981-15-6168-9_26

DO - 10.1007/978-981-15-6168-9_26

M3 - Conference contribution

AN - SCOPUS:85088502670

SN - 9789811561672

T3 - Communications in Computer and Information Science

SP - 307

EP - 318

BT - Computational Linguistics - 16th International Conference of the Pacific Association for Computational Linguistics, PACLING 2019, Revised Selected Papers

A2 - Nguyen, Le-Minh

A2 - Tojo, Satoshi

A2 - Phan, Xuan-Hieu

A2 - Hasida, Kôiti

PB - Springer

T2 - 16th International Conference of the Pacific Association for Computational Linguistics, PACLING 2019

Y2 - 11 October 2019 through 13 October 2019

ER -

Rap Lyrics Generation Using Vowel GAN

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this