[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

add speaker personality information

Dear listers,
The conventional way to implement voice conversion is to find the mapping rules between the source and target speaker, linearly or non-linearly.
However, I always thought that the mapping rules  could not precisely display the target speaker's characteristics. There must be some crucial factors that help determine the perceptual feeling of the speaker's personality. So, I wonder if there is  a way to add the speaker's personality information to a text-to-speech voice and how to manipulate it.
Would someone give some suggestions?
Best regards,
Yinqiu Gao
College of Signal Processing & Transmission
Nanjing University of Posts & Telecommunications
Nanjing, Jiangsu, People's Republic of China, 210003
E-mail: y050920@xxxxxxxxxxxx
Phone: +86-13770787592

GIF image