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.

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

Add data augmentation #16

Open
vvolhejn opened this issue Mar 22, 2022 · 1 comment
Open

Add data augmentation #16

vvolhejn opened this issue Mar 22, 2022 · 1 comment
Labels
low priority training For improvements not related to inference speed.

Comments

@vvolhejn
Copy link
Owner

DDSP and NEWT papers don't mention it, but RAVE does: "We use dequantization, random crop and allpass filters with random coefficients as our data augmentation strategy."

@vvolhejn vvolhejn added the training For improvements not related to inference speed. label Mar 28, 2022
@vvolhejn
Copy link
Owner Author

Random crop is actually tricky to do with the way DDSP is set up because the chunks are pre-cut into four-second segments with a fixed overlap, so this would require a larger change where the cutting would happen during data loading. Additionally, we would need to deal with cutting the pitch and loudness signals too.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
low priority training For improvements not related to inference speed.
Projects
None yet
Development

No branches or pull requests

1 participant