Differentiable Wavetable Synthesis

1 code implementation • 19 Nov 2021 • Siyuan Shan, Lamtharn Hantrakul, Jitong Chen, Matt Avent, David Trevelyan

Differentiable Wavetable Synthesis (DWTS) is a technique for neural audio synthesis which learns a dictionary of one-period waveforms i. e. wavetables, through end-to-end training.

Audio Synthesis One-Shot Learning

DDSP: Differentiable Digital Signal Processing

3 code implementations • ICLR 2020 • Jesse Engel, Lamtharn Hantrakul, Chenjie Gu, Adam Roberts

In this paper, we introduce the Differentiable Digital Signal Processing (DDSP) library, which enables direct integration of classic signal processing elements with deep learning methods.

Audio Generation Audio Synthesis

Neural Wavetable: a playable wavetable synthesizer using neural networks

1 code implementation • 13 Nov 2018 • Lamtharn Hantrakul, Li-Chia Yang

We present Neural Wavetable, a proof-of-concept wavetable synthesizer that uses neural networks to generate playable wavetables.