-
Notifications
You must be signed in to change notification settings - Fork 2.3k
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
[ASR] Convolution-invariant SDR loss + unit tests #5992
Conversation
db9dbbb
to
c3b0475
Compare
96c453d
to
e21f306
Compare
ebd839e
to
4ee49d0
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Minor arg check, otherwise LGTM.
if remove_mean: | ||
estimate = estimate - temporal_mean(estimate, mask=mask, keepdim=True, eps=eps) | ||
target = target - temporal_mean(target, mask=mask, keepdim=True, eps=eps) | ||
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Shouldn't we throw an error here if both scale_invariant and convolution_invariant are True?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
You're right, added that.
Signed-off-by: Ante Jukić <[email protected]>
Signed-off-by: Ante Jukić <[email protected]>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
* Added convolution-invariant SDR loss + unit tests Signed-off-by: Ante Jukić <[email protected]> * Addressed comment Signed-off-by: Ante Jukić <[email protected]> --------- Signed-off-by: Ante Jukić <[email protected]>
* Added convolution-invariant SDR loss + unit tests Signed-off-by: Ante Jukić <[email protected]> * Addressed comment Signed-off-by: Ante Jukić <[email protected]> --------- Signed-off-by: Ante Jukić <[email protected]> Signed-off-by: hsiehjackson <[email protected]>
What does this PR do ?
This PR adds a convolution-invariant SDR loss for audio-to-audio tasks.
Reference:
C. Boeddeker et al., Convolutive Transfer Function Invariant SDR training criteria for Multi-Channel Reverberant Speech Separation, 2021
Collection: ASR
Changelog
Before your PR is "Ready for review"
Pre checks:
PR Type:
If you haven't finished some of the above items you can still open "Draft" PR.
Who can review?
Anyone in the community is free to review the PR once the checks have passed.
Contributor guidelines contains specific people who can review PRs to various areas.
Additional Information