Neural Granular Sound Synthesis

TL;DR

This paper introduces a neural network-based approach to granular sound synthesis that uses a variational auto-encoder to create an invertible, structured latent space for more flexible and high-quality audio generation.

Contribution

It replaces traditional acoustic descriptors with a learned probabilistic latent space, enabling continuous, invertible sound synthesis and structured navigation within the sound space.

Findings

Latent space allows continuous sound synthesis.

Model supports various sound types including pitched, unpitched, and environmental noises.

Enables novel processes like conditional sampling and morphing.

Abstract

Granular sound synthesis is a popular audio generation technique based on rearranging sequences of small waveform windows. In order to control the synthesis, all grains in a given corpus are analyzed through a set of acoustic descriptors. This provides a representation reflecting some form of local similarities across the grains. However, the quality of this grain space is bound by that of the descriptors. Its traversal is not continuously invertible to signal and does not render any structured temporality. We demonstrate that generative neural networks can implement granular synthesis while alleviating most of its shortcomings. We efficiently replace its audio descriptor basis by a probabilistic latent space learned with a Variational Auto-Encoder. In this setting the learned grain space is invertible, meaning that we can continuously synthesize sound when traversing its dimensions. It also implies that original grains are not stored for synthesis. Another major advantage of our approach is to learn structured paths inside this latent space by training a higher-level temporal embedding over arranged grain sequences. The model can be applied to many types of libraries, including pitched notes or unpitched drums and environmental noises. We report experiments on the common granular synthesis processes as well as novel ones such as conditional sampling and morphing.