Adding voices to voice synthesis corpuses


If one uses one of the open source implementations of the WaveNet generative speech synthesis design, such as, and trains using something like the CMU's arctic corpus, now can one add a voice that sounds younger, older, less professional, or in some other way distinctive. Must the entire training begin from scratch, or is there a more resource and time friendly way?


Posted 2018-09-16T14:55:08.080

Reputation: 1 124

No answers