Rap Lyrics Generation Using Vowel GAN

Tomoya Miyano, Hiroaki Saito

研究成果: Conference contribution

抄録

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.

本文言語English
ホスト出版物のタイトルComputational Linguistics - 16th International Conference of the Pacific Association for Computational Linguistics, PACLING 2019, Revised Selected Papers
編集者Le-Minh Nguyen, Satoshi Tojo, Xuan-Hieu Phan, Kôiti Hasida
出版社Springer
ページ307-318
ページ数12
ISBN(印刷版)9789811561672
DOI
出版ステータスPublished - 2020
イベント16th International Conference of the Pacific Association for Computational Linguistics, PACLING 2019 - Hanoi, Viet Nam
継続期間: 2019 10月 112019 10月 13

出版物シリーズ

名前Communications in Computer and Information Science
1215 CCIS
ISSN(印刷版)1865-0929
ISSN(電子版)1865-0937

Conference

Conference16th International Conference of the Pacific Association for Computational Linguistics, PACLING 2019
国/地域Viet Nam
CityHanoi
Period19/10/1119/10/13

ASJC Scopus subject areas

  • コンピュータ サイエンス(全般)
  • 数学 (全般)

フィンガープリント

「Rap Lyrics Generation Using Vowel GAN」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル