期刊
COMPUTER COMMUNICATIONS
卷 168, 期 -, 页码 33-53出版社
ELSEVIER
DOI: 10.1016/j.comcom.2021.01.002
关键词
Music style transfer; Lyric generator; GPT-2; Natural language processing
资金
- Ministry of Science and Technology, Taiwan, R.O.C. [MOST 108-2218-E-025-002MY3, MOST 109-2221-E-025-009]
This study proposes a framework to generate singable lyrics by combining the GPT-2 model with musical style to create lyrics suitable for singing.
The lyrics generator should consider the context and the singability of the songs because every song expresses a story through the context of lyrics, and the lyrics should sound with the music well. Therefore, this study proposes a framework to generate the singable lyrics, and the context of lyrics should fit the given musical style. For the context, this study adopts the GPT-2 model which is powerful for text generation. The conditional GPT-2 model can be used to generate lyrics according to the given style. For suitable for singing, this study adjusts the structure and rhyme of lyrics through the use of a syntactic parser and a rhyme modification module. With automatic and human evaluations, the experimental results show that the proposed method can generate lyrics with high structural consistency, rhyme consistency, and originality according to the given music style.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据