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 hiddencost on Thursday March 30, 2017 @01:02AM (#13993049)
Jurafsky & Martin is the canonical textbook but it's pre-deep learning. Check out the wavenet paper[0], and Alan Black's Festvox[1].

[0] https://deepmind.com/blog/wavenet-generative-model-raw-audio... [1] http://www.festvox.org/

[ Parent | on HN ]

There are no comments on this comment yet.