YNote: A Novel Music Notation for Fine-Tuning LLMs in Music Generation
YNote offers a practical alternative to existing music notations for machine learning applications, particularly for music generation using LLMs, which is significant for researchers and developers in the music generation field.
The authors tackled the problem of complex music notation systems hindering the fine-tuning of Large Language Models (LLMs) in music generation, achieving BLEU and ROUGE scores of 0.883 and 0.766 with their novel YNote notation system. This resulted in coherent and stylistically relevant music generation with just two notes as prompts.
The field of music generation using Large Language Models (LLMs) is evolving rapidly, yet existing music notation systems, such as MIDI, ABC Notation, and MusicXML, remain too complex for effective fine-tuning of LLMs. These formats are difficult for both machines and humans to interpret due to their variability and intricate structure. To address these challenges, we introduce YNote, a simplified music notation system that uses only four characters to represent a note and its pitch. YNote's fixed format ensures consistency, making it easy to read and more suitable for fine-tuning LLMs. In our experiments, we fine-tuned GPT-2 (124M) on a YNote-encoded dataset and achieved BLEU and ROUGE scores of 0.883 and 0.766, respectively. With just two notes as prompts, the model was able to generate coherent and stylistically relevant music. We believe YNote offers a practical alternative to existing music notations for machine learning applications and has the potential to significantly enhance the quality of music generation using LLMs.