Implement pitch expressiveness controlling mechanism #97
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Conflicts: # deployment/exporters/variance_exporter.py # deployment/modules/toplevel.py # inference/ds_variance.py # modules/toplevel.py
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Expressiveness controls how freely the variance model generates pitch curves. By default, the variance model predicts pitch at a 100% expressiveness, which means completely following the style of the voice provider. Correspondingly, a 0% expressiveness will produce pitch completely close to the smoothened music score. Expressiveness can be freely adjusted from 0% to 100%, statically, or even dynamically on frame level.
The mechanism of expressiveness is a trick on
retake_embed. Regions whereretake == 1(100% expressiveness) will generate pitch as normal, while those whereretake == 0(0% expressiveness) will return the givenbase_pitchthat represents the music score. When a linear fusion is applied on the two types of embeddings, we get the effects of an expressiveness curve with continuous values between 0 and 1.