Re:Show HN: VoiceClonr attempts to reconstruct human voices
by michael_h on Wednesday July 01, 2015 @04:47PM
(#9815028)
That's exactly how unit selection systems like Festival work. The trouble starts when you hit a previously unencountered phoneme sequence and you have to interpolate. Sometimes good, sometimes bad.
Edit: Text to pronunciation is a whole other problem.
Edit: Text to pronunciation is a whole other problem.