Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
lachlan_gray
on April 19, 2023
|
parent
|
context
|
favorite
| on:
NaturalSpeech 2: Zero-shot speech and singing synt...
Is the approach similar to what they did for Riffusion? (On front page a while ago)
https://www.riffusion.com/
woodson
on April 21, 2023
[–]
No, it’s not similar (other than superficially, as both use diffusion methods in some way). It uses diffusion to generate latent vectors that are entered in a neural audio codec model to produce speech.
Consider applying for YC's Spring batch! Applications are open till Feb 11.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
https://www.riffusion.com/