Re:WaveNet launches in the Google Assistant
by microcolonel on Wednesday October 04, 2017 @10:31PM
(#15406371)
Mm, I see what you mean. It seems like voicetext.jp has more "correct" prosody, and seems to reproduce vocal fry correctly, I'm noticing that's missing from the WaveNet sample now. There's still some work to be done around filtering with voicetext, I hear pretty glaring artifacts between the units, whereas WaveNet doesn't produce any such artifacts.
Listen to the samples here for example: http://voicetext.jp/samplevoice/