http://youtu.be/EeX1ZBM22Cc
This is the beginning, unedited voice of UTAU-Synth. It feels like there's a layer of "white noise"(this is by far the closet word I can use to describe) in addition to the voice and it's specifically apparent in sounds such as い,う,え.
And when it comes to さ, the "S" pronunciation is even started with that white noise instead of the standard pronunciation.
Any idea to solve this noise problem and turn the voice into more realistic voice? Thanks!
This is the beginning, unedited voice of UTAU-Synth. It feels like there's a layer of "white noise"(this is by far the closet word I can use to describe) in addition to the voice and it's specifically apparent in sounds such as い,う,え.
And when it comes to さ, the "S" pronunciation is even started with that white noise instead of the standard pronunciation.
Any idea to solve this noise problem and turn the voice into more realistic voice? Thanks!