News for hackers. Stuff that matters.

A comment on Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model. Parent comment

Re:Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model by starmole on Thursday March 30, 2017 @01:38AM (#13993191)
Adobe VoCo does something like that. Demo: https://www.youtube.com/watch?v=I3l4XLZ59iw
[ Parent | on HN ]
Re:Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model by mbrookes on Thursday March 30, 2017 @04:48AM (#13993841)
It was pointed out the last time I posted this that the demo is "fake" at least in as much as the inserted words aren't being synthesized but rather copy-pasted with existing intonation intact.
[ Parent | on HN ]
Re:Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model by NKCSS on Thursday March 30, 2017 @02:19AM (#13993327)
That's pretty cool; any info on a release date?
[ Parent | on HN ]