Syllable-level lyrics generation from melody exploiting character-level language model
This addresses a domain-specific challenge in music and AI for generating lyrics that align with melodies, offering an incremental improvement by leveraging existing models.
The paper tackles the problem of generating lyrics from melodies by mapping musical notes to syllables, using a fine-tuned character-level language model integrated into a Transformer generator's beam search. It shows improved coherence and correctness in generated lyrics, validated by ChatGPT-based and human evaluations, without requiring expensive new model training.
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.