Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Chris Donahue

Enabling Language Models to Fill in the Blanks


May 11, 2020
Chris Donahue, Mina Lee, Percy Liang

* To appear in the proceedings of ACL 2020 

  Access Paper or Ask Questions

LakhNES: Improving multi-instrumental music generation with cross-domain pre-training


Jul 10, 2019
Chris Donahue, Huanru Henry Mao, Yiting Ethan Li, Garrison W. Cottrell, Julian McAuley

* Published as a conference paper at ISMIR 2019 

  Access Paper or Ask Questions

Expediting TTS Synthesis with Adversarial Vocoding


Apr 16, 2019
Paarth Neekhara, Chris Donahue, Miller Puckette, Shlomo Dubnov, Julian McAuley


  Access Paper or Ask Questions

GANSynth: Adversarial Neural Audio Synthesis


Apr 15, 2019
Jesse Engel, Kumar Krishna Agrawal, Shuo Chen, Ishaan Gulrajani, Chris Donahue, Adam Roberts

* Colab Notebook: http://goo.gl/magenta/gansynth-demo 

  Access Paper or Ask Questions

Exploring Speech Enhancement with Generative Adversarial Networks for Robust Speech Recognition


Oct 31, 2018
Chris Donahue, Bo Li, Rohit Prabhavalkar

* Published as a conference paper at ICASSP 2018 

  Access Paper or Ask Questions

Piano Genie


Oct 11, 2018
Chris Donahue, Ian Simon, Sander Dieleman


  Access Paper or Ask Questions

Adversarial Audio Synthesis


Sep 27, 2018
Chris Donahue, Julian McAuley, Miller Puckette


  Access Paper or Ask Questions

The NES Music Database: A multi-instrumental dataset with expressive performance attributes


Jun 12, 2018
Chris Donahue, Huanru Henry Mao, Julian McAuley

* Published as a conference paper at ISMIR 2018 

  Access Paper or Ask Questions

Semantically Decomposing the Latent Spaces of Generative Adversarial Networks


Feb 22, 2018
Chris Donahue, Zachary C. Lipton, Akshay Balsubramani, Julian McAuley

* Published as a conference paper at ICLR 2018 

  Access Paper or Ask Questions

Dance Dance Convolution


Jun 21, 2017
Chris Donahue, Zachary C. Lipton, Julian McAuley

* Published as a conference paper at ICML 2017 

  Access Paper or Ask Questions