MuseControlLite: Multifunctional Music Generation with Lightweight Conditioners
Journal
Proceedings of Machine Learning Research
Journal Volume
267
Start Page
60266
End Page
60279
ISSN
26403498
Date Issued
2025-07
Author(s)
Abstract
We propose MuseControlLite, a lightweight mechanism designed to fine-tune text-to-music generation models for precise conditioning using various time-varying musical attributes and reference audio signals. The key finding is that positional embeddings, which have been seldom used by text-to-music generation models in the conditioner for text conditions, are critical when the condition of interest is a function of time. Using melody control as an example, our experiments show that simply adding rotary positional embeddings to the decoupled cross-attention layers increases control accuracy from 56.6% to 61.1%, while requiring 6.75 times fewer trainable parameters than state-of-the-art fine-tuning mechanisms, using the same pre-trained diffusion Transformer model of Stable Audio Open. We evaluate various forms of musical attribute control, audio in-painting, and audio outpainting, demonstrating improved controllability over MusicGen-Large and Stable Audio Open ControlNet at a significantly lower fine-tuning cost, with only 85M trainable parameters. Source code, model checkpoints, and demo examples are available at: https: //MuseControlLite.github.io/web/.
Event(s)
42nd International Conference on Machine Learning, ICML 2025
Type
conference paper