C
Chris Donahue
Researcher at University of California, San Diego
Publications - 35
Citations - 1674
Chris Donahue is an academic researcher from University of California, San Diego. The author has contributed to research in topics: Computer science & Engineering. The author has an hindex of 15, co-authored 30 publications receiving 1252 citations. Previous affiliations of Chris Donahue include Stanford University.
Papers
More filters
Proceedings Article
Adversarial Audio Synthesis
TL;DR: WaveGAN is a first attempt at applying GANs to unsupervised synthesis of raw-waveform audio, capable of synthesizing one second slices of audio waveforms with global coherence, suitable for sound effect generation.
Posted Content
Adversarial Audio Synthesis
TL;DR: WaveGAN as mentioned in this paper uses GANs to synthesize one second slices of audio waveforms with global coherence, suitable for sound effect generation, which can also synthesize audio from other domains such as drums, bird vocalizations, and piano.
Proceedings ArticleDOI
Enabling Language Models to Fill in the Blanks.
TL;DR: It is shown that humans have difficulty identifying sentences infilled by the approach, which can enable LMs to infill entire sentences effectively on three different domains: short stories, scientific abstracts, and lyrics.
Proceedings ArticleDOI
Exploring Speech Enhancement with Generative Adversarial Networks for Robust Speech Recognition
TL;DR: In this article, the authors investigate the effectiveness of GANs for speech enhancement, in the context of improving noise robustness of automatic speech recognition (ASR) systems, and propose operating GAN on log-Mel filterbank spectra instead of waveforms, which requires less computation and is robust to reverberant noise.
Posted Content
Synthesizing Audio with Generative Adversarial Networks
TL;DR: WaveGAN is introduced, a first attempt at applying GANs to raw audio synthesis in an unsupervised setting and it is found that human judges prefer the generated examples from WaveGAN over those from a method which naively apply GAns on image-like audio feature representations.