Reverse Engineering of Music Mixing Graphs with Differentiable Processors and Iterative Pruning

2025-09-19

AI Summary

This work addresses the black-box nature of music mixing by proposing a differentiable graph-structured inverse engineering method to automatically infer the processing chain and combination topology applied to dry source signals from the final mix. The approach constructs a parameterized mixing graph using differentiable audio processors and jointly optimizes both graph structure and parameters via gradient descent, augmented by a dry–wet ratio-guided iterative pruning strategy. Compared to manual modeling, it achieves high-fidelity mix reconstruction (PESQ ≥ 3.2, STOI ≥ 0.92) while removing approximately 67% of redundant processors, substantially reducing model complexity. The framework supports batch-parallel optimization and scalable generation of large mixing graphs. Experiments demonstrate its efficiency, scalability, and perceptual naturalness, establishing a novel paradigm for mixing analysis, AI-assisted production, and interpretable audio processing.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Search and Optimization: Mixed Discrete/Continuous Search
• Constraint Satisfaction and Optimization: Mixed Discrete/Continuous Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Reverse engineering of music mixes aims to uncover how dry source signals are processed and combined to produce a final mix. We extend the prior works to reflect the compositional nature of mixing and search for a graph of audio processors. First, we construct a mixing console, applying all available processors to every track and subgroup. With differentiable processor implementations, we optimize their parameters with gradient descent. Then, we repeat the process of removing negligible processors and fine-tuning the remaining ones. This way, the quality of the full mixing console can be preserved while removing approximately two-thirds of the processors. The proposed method can be used not only to analyze individual music mixes but also to collect large-scale graph data that can be used for downstream tasks, e.g., automatic mixing. Especially for the latter purpose, efficient implementation of the search is crucial. To this end, we present an efficient batch-processing method that computes multiple processors in parallel. We also exploit the "dry/wet" parameter of the processors to accelerate the search. Extensive quantitative and qualitative analyses are conducted to evaluate the proposed method's performance, behavior, and computational cost.

Problem

• Reverse engineering music mixes to uncover processing techniques
• Optimizing differentiable audio processors with gradient descent
• Pruning mixing graphs for efficiency while preserving quality

Innovation

• Differentiable processors optimize mixing parameters
• Iterative pruning removes negligible audio processors
• Batch-processing computes multiple processors in parallel