[michael_h]

This was kind of the target of the 2016 Blizzard Challenge (http://festvox.org/blizzard/blizzard2016.html), as the training data was children's books (clean audio, 'reading voice' prosody, etc).

Some of the voices that came out of that were incredible.

[rightos]

Are any of those voices published? Would be interesting to try rendering audio books with them.

[michael_h]

I'm not sure - the exact voices themselves generally aren't published, but the papers are detailed enough that you could recreate the system if you wanted.