About frequency discriminator
Closed this issue · 2 comments
Yablon commented
Hi, the time loss calculated by convolution layer is very impressive.
I have questions about frequency discriminator
As we know, the output of discriminators are supposed to be real or fake labels for input waves. Your frequency discriminator seems to get [B, channels, T] shape output. Does that obey the rule of discriminator or there is something more I can learn from ?
Thank you !
Yablon commented
@rishikksh20 hi, I close this due to lack of attention here.
rishikksh20 commented
@Yablon When we dealing with audio domain, least squares(LSGAN) loss works better than real and fake audio. Check out MelGAN paper and https://arxiv.org/abs/1611.04076 .