They (Yamaha) call this vocal synthesizer which is supposed to be more than text-to-speech synthesizer. You get to input notes, and other information I think. If you don’t, then it’s as good as text-to-speech synthesizer.
What is state-of-the-art text to speech synthesizer?
Hm. I don’t know what else they’re inputting besides vibrato—it didn’t seem to change its vowels when it changed pitch, for example, or slide between notes. Maybe they do stress/volume information separately rather than the computer being able to do it?
They (Yamaha) call this vocal synthesizer which is supposed to be more than text-to-speech synthesizer. You get to input notes, and other information I think. If you don’t, then it’s as good as text-to-speech synthesizer.
What is state-of-the-art text to speech synthesizer?
Hm. I don’t know what else they’re inputting besides vibrato—it didn’t seem to change its vowels when it changed pitch, for example, or slide between notes. Maybe they do stress/volume information separately rather than the computer being able to do it?
For speech, IBM’s Watson was pretty good.