Search papers, labs, and topics across Lattice.
This paper introduces Diff2Mix, a novel generative automatic mixing system that leverages diffusion models and a differentiable mixing console to integrate music mixing and stylistic control into a single framework. By allowing users to manipulate both overall production style through reference audio and fine-tune audio effects parameters, Diff2Mix achieves a balance between high-quality mixes and user-directed customization. The system demonstrates competitive performance in both objective and subjective evaluations, highlighting its effectiveness in producing coherent musical pieces while maintaining stylistic flexibility.
Achieving high-quality music mixing while allowing for nuanced stylistic control could redefine how producers approach automated mixing.
Automatic music mixing aims to combine multitrack recordings into a balanced and coherent musical piece. Because the content of different songs and the subjective preferences of mixing engineers jointly shape the final outcome, a practical system should deliver well-balanced mixes while allowing for controllable stylistic variation. However, most existing methods treat automatic mixing and mixing style control as separate tasks, making it difficult for a single system to produce high-quality mixes while remaining editable and style-aware. To address this limitation, this paper presents Diff2Mix, a generative automatic mixing system based on diffusion models and a differentiable mixing console. This system offers two levels of optional user control: a reference audio enables overall production style control, and the differentiable mixing console provides explicit audio effects parameters for interpretability and fine-grained optimization. We demonstrate our system's competitive performance through both objective and subjective evaluations in terms of mixing quality and control ability. We provide code and audio samples at our project page https://zys711.github.io/Diff2Mix .
