Differentiable Signal Processing With Black-Box Audio Effects
Open Access
- 6 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 66-70
Abstract
We present a data-driven approach to automate audio signal processing by incorporating stateful third-party, audio effects as layers within a deep neural network. We then train a deep encoder to analyze input audio and control effect parameters to perform the desired signal manipulation, requiring only input-target paired audio data as supervision. To train our network with non-differentiable black-box effects layers, we use a fast, parallel stochastic gradient approximation scheme within a standard auto differentiation graph, yielding efficient end-to-end backpropagation. We demonstrate the power of our approach with three separate automatic audio production applications: tube amplifier emulation, automatic removal of breaths and pops from voice recordings, and automatic music mastering. We validate our results with a subjective listening test, showing our approach not only can enable new automatic audio effects tasks, but can yield results comparable to a specialized, state-of-the-art commercial solution for music mastering.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- Casting to Corpus: Segmenting and Selecting Spontaneous Dialogue for Tts with a Cnn-lstm Speaker-dependent Breath Detector2019
- Deep Learning for Tube Amplifier Emulation2019
- ImageNet Training in Minutes2018
- An Algorithm for Detection of Breath Sounds in Spontaneous Speech with Application to Speaker Recognition2017
- Audio Effects2014
- DAFX: Digital Audio Effects2011
- Automatic Noise Gate Settings for Drum Recordings Containing Bleed from Secondary SourcesEURASIP Journal on Advances in Signal Processing, 2011
- Numerical Methods for Simulation of Guitar Distortion CircuitsComputer Music Journal, 2008
- Multivariate stochastic approximation using a simultaneous perturbation gradient approximationIEEE Transactions on Automatic Control, 1992
- Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning1992