English

Song Form-aware Full-Song Text-to-Lyrics Generation with Multi-Level Granularity Syllable Count Control

Computation and Language 2025-06-24 v3 Artificial Intelligence

Abstract

Lyrics generation presents unique challenges, particularly in achieving precise syllable control while adhering to song form structures such as verses and choruses. Conventional line-by-line approaches often lead to unnatural phrasing, underscoring the need for more granular syllable management. We propose a framework for lyrics generation that enables multi-level syllable control at the word, phrase, line, and paragraph levels, aware of song form. Our approach generates complete lyrics conditioned on input text and song form, ensuring alignment with specified syllable constraints. Generated lyrics samples are available at: https://tinyurl.com/lyrics9999

Keywords

Cite

@article{arxiv.2411.13100,
  title  = {Song Form-aware Full-Song Text-to-Lyrics Generation with Multi-Level Granularity Syllable Count Control},
  author = {Yunkee Chae and Eunsik Shin and Suntae Hwang and Seungryeol Paik and Kyogu Lee},
  journal= {arXiv preprint arXiv:2411.13100},
  year   = {2025}
}

Comments

Accepted to Interspeech 2025