GRAFX: An Open-Source Library for Audio Processing Graphs in PyTorch

2024/08/06 by Sungho Lee, Lee, Sungho, Marco A. Martínez-Ramírez +11 · 3 citations
Computer Science · #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Music Technology and Sound Studies #Music and Audio Processing #Sound (cs.SD) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2408.03204

openalex publication_date 2024/08/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We present GRAFX, an open-source library designed for handling audio processing graphs in PyTorch. Along with various library functionalities, we describe technical details on the efficient parallel computation of input graphs, signals, and processor parameters in GPU. Then, we show its example use under a music mixing scenario, where parameters of every differentiable processor in a large graph are optimized via gradient descent. The code is available at https://github.com/sh-lee97/grafx.

Cited by

• Reverse Engineering of Music Mixing Graphs with Differentiable Processors and Iterative Pruning
• WildFX: A DAW-Powered Pipeline for In-the-Wild Audio FX Graph Modeling
• MixAssist: An Audio-Language Dataset for Co-Creative AI Assistance in Music Mixing

Related

• TorchFX: A modern approach to Audio DSP with PyTorch and GPU acceleration
• Searching For Music Mixing Graphs: A Pruning Approach
• Reverse Engineering of Music Mixing Graphs with Differentiable Processors and Iterative Pruning
• String Sound Synthesizer on GPU-accelerated Finite Difference Scheme
• WildFX: A DAW-Powered Pipeline for In-the-Wild Audio FX Graph Modeling