DDSP: Differentiable Digital Signal Processing
Today, we’re pleased to introduce the Differentiable Digital Signal Processing (DDSP) library. DDSP lets you combine the interpretable structure of classical...
DDSP: Differentiable Digital Signal Processing Jan 15, 2020 Jesse Engel jesseengel jesseengel Hanoi Hantrakul lamtharnhantrakul hanoihantrakul Chenjie Gu gcj calbeargu Adam Roberts adarob ada_rob Today, we’re pleased to introduce the Differentiable Digital Signal Processing (DDSP) library. DDSP lets you combine the interpretable structure of classical DSP elements (such as filters, oscillators, reverberation, etc.) with the expressivity of deep learning. GitHub Code 🎵 Audio Examples Colab Demo Colab Tutorials 📝 ICLR Paper Neural networks (such as WaveNet or GANSynth ) are often black boxes.
Explore this link on the map →saved by
related reading
- Diffusion is spectral autoregression – Sander Dielemansander.ai
- Generating music in the waveform domain – Sander Dielemansander.ai
- Synthesizer for thought | thesephist.comthesephist.com
- The Little Book of Deep Learningfleuret.org
- GANSynth: Making music with GANsmagenta.tensorflow.org
- Circles Sines and Signals - Introductionjackschaedler.github.io
- Yang Songyang-song.net
- Diffusion models from scratchchenyang.co
- Diffusion is not necessarily Spectral Autoregression | Fabian Falckfabianfalck.com
- Annotated Research Paper Implementations: Transformers, StyleGAN, Stable Diffusion, DDPM/DDIM, LayerNorm, Nucleus Sampling and morenn.labml.ai
- WaveGrad: Estimating Gradients for Waveform Generationarxiv.org
- GitHub - DiffEqML/torchdyn: A PyTorch library entirely dedicated to neural differential equations, implicit models and related numerical methods · GitHubgithub.com