GANSynth: Making music with GANs
In this post, we introduce GANSynth, a method for generating high-fidelity audio with Generative Adversarial Networks (GANs). Colab Notebook 🎵Audio E...
GANSynth: Making music with GANs Feb 25, 2019 Jesse Engel jesseengel jesseengel In this post, we introduce GANSynth, a method for generating high-fidelity audio with Generative Adversarial Networks (GANs). Colab Notebook 🎵 Audio Examples 📝 ICLR 2019 Paper GitHub Code Why generate audio with GANs? GANs are a state-of-the-art method for generating high-quality images . However, researchers have struggled to apply them to more sequential data such as audio and music, where autoregressive (AR) models such as WaveNets and Transformers dominate by predicting a single sample at a time. While this a
saved by
related reading
- Generating music in the waveform domain – Sander Dielemansander.ai
- WaveGrad: Estimating Gradients for Waveform Generationarxiv.org
- Introducing "Lucid Sonic Dreams": Sync GAN Art to Music with a Few Lines of Python Code! | Towards Data Sciencetowardsdatascience.com
- WaveNetdeepmind.com
- MusicLM: Generating Music From Textgoogle-research.github.io
- Diffusion is spectral autoregression – Sander Dielemansander.ai
- Woosh: A Sound Effects Foundation Modelarxiv.org
- Yang Songyang-song.net
- What are Diffusion Models?lilianweng.github.io
- Replicate - Run AI with an APIreplicate.com
- Machine Learning for Synthetic Data Generation: A Reviewarxiv.org
- DDSP: Differentiable Digital Signal Processingmagenta.tensorflow.org