Can I read NotaGen: Advancing Musicality in Symbolic Music Generation with Large Language Model Training Paradigms on EtoBox?

NotaGen: Advancing Musicality in Symbolic Music Generation with Large Language Model Training Paradigms by Wang, Yashan; Wu, Shangda; Hu, Jianhuai; Du, Xingjian; Peng, Yueqi; Huang, Yongxin; Fan, Shuai; Li, Xiaobing; Yu, Feng; Sun, Maosong is a scholarly article available to read on EtoBox.

What is NotaGen: Advancing Musicality in Symbolic Music Generation with Large Language Model Training Paradigms about?

We introduce NotaGen, a symbolic music generation model aiming to explore the potential of producing high-quality classical sheet music. Inspired by the success of Large Language Models (LLMs), NotaGen adopts pre-training, fine-tuning, and reinforcement learning paradigms (henceforth referred to as the LLM training paradigms). It is pre-trained on 1.6M pieces of music in ABC notation, and then fine-tuned on approximately 9K high-quality classical compositions conditioned on "period-composer-instrumentation" prompts. For reinforcement learning, we propose the CLaMP-DPO method, which further enhances generation quality and controllability without requiring human annotations or predefined rewards. Our experiments demonstrate the efficacy of CLaMP-DPO in symbolic music generation models with different architectures and encoding schemes. Furthermore, subjective A/B tests show that NotaGen outperforms baseline models against human compositions, greatly advancing musical aesthetics in symbolic music generation.

Author

Wang, Yashan; Wu, Shangda; Hu, Jianhuai; Du, Xingjian; Peng, Yueqi; Huang, Yongxin; Fan, Shuai; Li, Xiaobing; Yu, Feng; Sun, Maosong

Published

2025

Language

EN