One Billion Audio Sounds from GPU-enabled Modular Synthesis
Sound
2021-07-21 v2 Artificial Intelligence
Machine Learning
Audio and Speech Processing
Signal Processing
Abstract
We release synth1B1, a multi-modal audio corpus consisting of 1 billion 4-second synthesized sounds, paired with the synthesis parameters used to generate them. The dataset is 100x larger than any audio dataset in the literature. We also introduce torchsynth, an open source modular synthesizer that generates the synth1B1 samples on-the-fly at 16200x faster than real-time (714MHz) on a single GPU. Finally, we release two new audio datasets: FM synth timbre and subtractive synth pitch. Using these datasets, we demonstrate new rank-based evaluation criteria for existing audio representations. Finally, we propose a novel approach to synthesizer hyperparameter optimization.
Keywords
Cite
@article{arxiv.2104.12922,
title = {One Billion Audio Sounds from GPU-enabled Modular Synthesis},
author = {Joseph Turian and Jordie Shier and George Tzanetakis and Kirk McNally and Max Henry},
journal= {arXiv preprint arXiv:2104.12922},
year = {2021}
}