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

TL;DR

This paper introduces a novel lyrics generation framework that ensures precise syllable control across multiple levels, aligning with song structures like verses and choruses, resulting in more natural and form-consistent song lyrics.

Contribution

It presents a multi-level syllable control method for full-song lyrics generation that considers song form, improving over traditional line-by-line approaches.

Findings

Achieves accurate syllable counts at word, phrase, line, and paragraph levels.

Generates complete, song-form-aware lyrics conditioned on input text.

Samples demonstrate improved naturalness and structural adherence.

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