Hellow, so I'm kinda curious about your opinions in this topic. It's something that was wondering my mind a little bit and I can't afford to compare utau's oto with deepvocal's "oto". It has differente parameters and some similar things, like, utau has just overlap, consonant, offset, onset and preutturance, but deepvocal has a bunch of parameters to make the connections better so I wonder: what parameter would you want utau's oto to have/would you create for utau oto if you know how to?
(Ps: I know, it's a kinda crazy question, but just for having fun! :V)
(Ps: I know, it's a kinda crazy question, but just for having fun! :V)