LingGe: An Automatic Ancient Chinese Poem-to-Song Generation System

Abstract

This paper presents a novel system, named LingGe ("伶歌" in Chinese), to generate songs for ancient Chinese poems automatically. LingGe takes the poem as the lyric, composes music conditioned on the lyric, and finally outputs a full song including the singing and the accompaniment. It consists of four modules: rhythm recognition, melody generation, accompaniment generation, and audio synthesis. Firstly, the rhythm recognition module analyzes the song structure and rhythm according to the poem. Secondly, the melody generation module assembles the rhythm into the template and then generates the melody. Thirdly, the accompaniment generation module predicts the accompaniment in harmony with the melody. Finally, the audio synthesis module generates singing and accompaniment audio and then mixes them to obtain songs. The results show that LingGe can generate high-quality and expressive songs for ancient Chinese poems, both in harmony and rhythm.

Cite

Text

Shan et al. "LingGe: An Automatic Ancient Chinese Poem-to-Song Generation System." International Joint Conference on Artificial Intelligence, 2023. doi:10.24963/IJCAI.2023/842

Markdown

[Shan et al. "LingGe: An Automatic Ancient Chinese Poem-to-Song Generation System." International Joint Conference on Artificial Intelligence, 2023.](https://mlanthology.org/ijcai/2023/shan2023ijcai-lingge/) doi:10.24963/IJCAI.2023/842

BibTeX

@inproceedings{shan2023ijcai-lingge,
  title     = {{LingGe: An Automatic Ancient Chinese Poem-to-Song Generation System}},
  author    = {Shan, Yong and Zhang, Jinchao and Ren, Huiying and Qiu, Yao and Zhou, Jie},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2023},
  pages     = {7171-7174},
  doi       = {10.24963/IJCAI.2023/842},
  url       = {https://mlanthology.org/ijcai/2023/shan2023ijcai-lingge/}
}