SDLGMMASNov 13, 2018

Neural Wavetable: a playable wavetable synthesizer using neural networks

arXiv:1811.05550v23 citations
Originality Incremental advance
AI Analysis

This is an incremental improvement for audio synthesis enthusiasts and musicians, offering a novel method to create distinct waveforms in digital audio workstations.

The paper tackled the problem of generating new waveforms for wavetable synthesizers by using neural networks to interpolate traditional wavetables in an autoencoder's latent space, resulting in a playable VST/AU plugin.

We present Neural Wavetable, a proof-of-concept wavetable synthesizer that uses neural networks to generate playable wavetables. The system can produce new, distinct waveforms through the interpolation of traditional wavetables in an autoencoder's latent space. It is available as a VST/AU plugin for use in a Digital Audio Workstation.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes