search

liusongxiang / StarGAN-Voice-Conversion

This is a pytorch implementation of the paper: StarGAN-VC: Non-parallel many-to-many voice conversion with star generative adversarial networks
https://arxiv.org/abs/1806.02169
513 stars 93 forks source link

Id mapping loss #13

Closed SamuelBroughton closed 4 years ago

SamuelBroughton commented 4 years ago

Hi,

I can see from this line:

g_loss = g_loss_fake + self.lambda_rec * g_loss_rec + self.lambda_cls * g_loss_cls_spks

in solver.py that adv. loss, reconstruction loss and domian class loss are being computed however, am I correct in saying that this paper does not implement the id mapping loss introduced in the StarGAN-VC paper?

Thank you, Sam

SamuelBroughton commented 4 years ago

I realise this implementation is just a take on StarGAN-VC and not an actual implementation of the paper. Still works very well though.