search

Wendison / VQMIVC

Official implementation of VQMIVC: One-shot (any-to-any) Voice Conversion @ Interspeech 2021 + Online playing demo!
MIT License
337 stars 55 forks source link

loglikeli and mi_est #6

Closed Liujingxiu23 closed 3 years ago

Liujingxiu23 commented 3 years ago

I understand that in mi_firstforward, the network be to optimized is CLUBSample* which is trained to get mu and logdvar. In mi_second_forward, the core-network(the VC part) is optimized. In mi_first_forward, loglikeli is computed while in mi_second_forward mi_est is computed. I am comfused:

Is the value of loglikeli and mi_est is both used for representation disentanglement? why loglikeli is used instead of mi_est in mi_first_forward?

Liujingxiu23 commented 3 years ago

understand by readding the original paper CLUB.