MCMG: Multi-level Controllable Music Generation Model Based on Fine-grained Control

Jingge Zhao, Xiaobing Li, Xinran Zhang, Xiaoqing Wang, Qingwen Zhou, Yun Tie

Abstract: The task of controlled music generation has been well developed, but the lack of modeling of music control attributes and neglect of music structure affect the quality of music creation. In order to solve the above problems, we first classify music into three levels according to its essentially different nature and extract the corresponding interpretable control attributes. Then by adding the control attributes to the music representation, a multi-level connection between music generation process and human composition is established. Finally, we propose a multi-level controllable music generation model with fine-grained control (MCMG). This model considers the structural relationships between music levels, enabling the music generation process highly controllable. The experiments show that our generative model not only improves on the basic music metric compared to the baseline, but also performs well on the controllability metric.

External IDs:dblp:conf/smc/ZhaoLZWZT25