DeepMind Blog company blog
WaveNet: A Generative Model for Raw Audio
This post presents WaveNet, a deep generative model of raw audio waveforms. We show that WaveNets are able to generate speech which mimics any human voice and which sounds more natural than the best existing Text-to-Speech systems, reducing the gap with human performance by over 50%.
- Points
- 627
- HN comments
- 145
- Submissions
- 1
- Cited by
- 30 commenters
AI & Machine LearningSoftware Engineering2016
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Sep 8, 2016 | WaveNet: A Generative Model for Raw Audio by benanne | 627 | 145 |
Cited in comments
Linked from 32 Hacker News comments by 30 different people, from Sep 2016 to Apr 2019.
Most recent:
- bduerst · Apr 5, 2019
- The_Amp_Walrus · Mar 22, 2019
- cs702 · Dec 10, 2018
- MaBu · Nov 9, 2018
- jacksmith21006 · May 24, 2018
- fragilistical · May 8, 2018
