Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
kastnerkyle
on Sept 8, 2016
|
parent
|
context
|
favorite
| on:
WaveNet: A Generative Model for Raw Audio
Relatively, training is fast (due to parallelism / masking so you don't have to sample during training) but during generation sampling is a sequential process. They talk about it a bit in the previous papers for PixelCNN and PixelRNN.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: