-
Notifications
You must be signed in to change notification settings - Fork 83
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
MGE training: Incorporate MLPG into training process #75
Labels
Comments
I won't probably work on this because (1) it adds extra implementation complexity (2) didn't give us significant performance gain based on my experience (2) I was able to get good results without using dynamic features. For example, the model used for https://soundcloud.com/r9y9/20220802-nnsvs-ritsu-test-tellme?in=r9y9/sets/dnn-based-singing-voice doesn't use dynamic features at all; MLPG is not used. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
https://r9y9.github.io/blog/2017/10/05/ganvc/
The text was updated successfully, but these errors were encountered: