PS: the codename of the backend that powers all this is actually "tldr" since I can't be stuffed reading :)
PS: the codename of the backend that powers all this is actually "tldr" since I can't be stuffed reading :)
You're absolutely right about the TTS uncanny valley problem. We're betting on the fact that this is an industry effort. Currently we don't have the resources to really invest in the core TTS technology but always on the look-out for breakthrough/experimental tech.
For my kids, it's at least a few minutes entertainment to make the computer speak high-quality foreign curse words.
http://reviews.cnet.com/8301-13727_7-20082143-263/how-to-ins...
The only major problem I seem to perceive is that the transitions between certain words and phones aren't smooth enough and are jarring. It doesn't sound like they're far off but I guess 90% of the work is in the last 10% ;-)