iComposer: An Automatic Songwriting System for Chinese Popular Music

Hsin-Pei Lee, Jhih-Sheng Fang, Wei-Yun Ma


Abstract
In this paper, we introduce iComposer, an interactive web-based songwriting system designed to assist human creators by greatly simplifying music production. iComposer automatically creates melodies to accompany any given text. It also enables users to generate a set of lyrics given arbitrary melodies. iComposer is based on three sequence-to-sequence models, which are used to predict melody, rhythm, and lyrics, respectively. Songs generated by iComposer are compared with human-composed and randomly-generated ones in a subjective test, the experimental results of which demonstrate the capability of the proposed system to write pleasing melodies and meaningful lyrics at a level similar to that of humans.
Anthology ID:
N19-4015
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Waleed Ammar, Annie Louis, Nasrin Mostafazadeh
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
84–88
Language:
URL:
https://aclanthology.org/N19-4015
DOI:
10.18653/v1/N19-4015
Bibkey:
Cite (ACL):
Hsin-Pei Lee, Jhih-Sheng Fang, and Wei-Yun Ma. 2019. iComposer: An Automatic Songwriting System for Chinese Popular Music. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations), pages 84–88, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
iComposer: An Automatic Songwriting System for Chinese Popular Music (Lee et al., NAACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/N19-4015.pdf
Code
 hhpslily/iComposer