Skip to content
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.

Sign up for GitHub

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

Jump to bottom

MGE training: Incorporate MLPG into training process #75

Open
r9y9 opened this issue Mar 8, 2022 · 1 comment
Open

MGE training: Incorporate MLPG into training process #75

r9y9 opened this issue Mar 8, 2022 · 1 comment
Labels
training

Comments

@r9y9
Copy link
Collaborator

r9y9 commented Mar 8, 2022

https://r9y9.github.io/blog/2017/10/05/ganvc/
@r9y9 r9y9 added the training label Mar 10, 2022
@r9y9
Copy link
Collaborator Author

r9y9 commented Aug 17, 2022

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
Assignees
No one assigned
Labels
training
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@r9y9