ICLR

Adversarial Audio Synthesis
Audio signals are sampled at high temporal resolutions, and learning to synthesize audio requires capturing structure across a range of â€Ļ
Chris Donahue, Julian McAuley, Miller Puckette
arXiv PDF BibTeX 🔊 Examples Code 🕹ī¸ Demo Notebook
GANSynth: Adversarial Neural Audio Synthesis
Efficient audio synthesis is an inherently difficult machine learning task, as human perception is sensitive to both global structure â€Ļ
Jesse Engel, Kumar Krishna Agrawal, Shuo Chen, Ishaan Gulrajani, Chris Donahue, Adam Roberts
arXiv PDF BibTeX 🔊 Examples Code Blog
Semantically Decomposing the Latent Spaces of Generative Adversarial Networks
We propose a new algorithm for training generative adversarial networks that jointly learns latent codes for both identities (e.g. â€Ļ
Chris Donahue, Zachary C. Lipton, Akshay Balsubramani, Julian McAuley
arXiv PDF BibTeX Code 🕹ī¸ Demo