Blind Estimation of Audio Processing Graph
Preprint
Abstract
Musicians and audio engineers sculpt and transform their sounds by connecting multiple processors, forming an audio processing graph. However, most deep-learning methods overlook this real-world practice and assume fixed graph settings. To bridge this gap, we develop a system that reconstructs the entire graph from a given reference audio. We first generate a realistic graph-reference pair dataset and train a simple blind estimation system composed of a convolutional reference encoder and a transformer-based graph decoder. We apply our model to singing voice effects and drum mixing estimation tasks. Evaluation results show that our method can reconstruct complex signal routings, including multi-band processing and sidechaining.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- Style Transfer of Audio Effects with Differentiable Signal ProcessingJournal of the Audio Engineering Society, 2022
- Differentiable Artificial ReverberationIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2022
- Notice of Removal: Deep Graph Generators: A SurveyIEEE Access, 2021
- Reverse engineering of a recording mix with differentiable digital signal processingThe Journal of the Acoustical Society of America, 2021
- Deep Learning for Black-Box Modeling of Audio EffectsApplied Sciences, 2020
- PubChemQC Project: A Large-Scale First-Principles Electronic Structure Database for Data-Driven ChemistryJournal of Chemical Information and Modeling, 2017