Syllable-level lyrics generation from melody exploiting character-level language model

TL;DR

This paper presents a method for generating syllable-level lyrics from melodies by fine-tuning character-level language models and integrating linguistic knowledge into the generation process, improving coherence without new model training.

Contribution

It introduces a novel approach that fine-tunes existing character-level language models for syllable-level lyrics generation from melodies, incorporating linguistic knowledge into the decoding process.

Findings

Enhanced coherence and correctness of generated lyrics

Eliminates the need for training new language models

Effective use of ChatGPT-based evaluation and human assessment

Abstract

The generation of lyrics tightly connected to accompanying melodies involves establishing a mapping between musical notes and syllables of lyrics. This process requires a deep understanding of music constraints and semantic patterns at syllable-level, word-level, and sentence-level semantic meanings. However, pre-trained language models specifically designed at the syllable level are publicly unavailable. To solve these challenging issues, we propose to exploit fine-tuning character-level language models for syllable-level lyrics generation from symbolic melody. In particular, our method endeavors to incorporate linguistic knowledge of the language model into the beam search process of a syllable-level Transformer generator network. Additionally, by exploring ChatGPT-based evaluation for generated lyrics, along with human subjective evaluation, we demonstrate that our approach enhances the coherence and correctness of the generated lyrics, eliminating the need to train expensive new language models.