Skip to content

adding the sign flip augmentation#2636

Merged
asumagic merged 2 commits intospeechbrain:developfrom
gfdb:add-sign-flip
Sep 5, 2024
Merged

adding the sign flip augmentation#2636
asumagic merged 2 commits intospeechbrain:developfrom
gfdb:add-sign-flip

Conversation

@gfdb
Copy link
Copy Markdown
Contributor

@gfdb gfdb commented Aug 1, 2024 •
edited
Loading

What does this PR do?

This PR adds the sign flip augmentation outlined in the paper "CADDA: Class-wise Automatic Differentiable Data Augmentation for EEG Signals". Although originally used for augmenting EEG data, my experiments show that sign flip gives consistent gains on a variety of ASR tasks. It also adds unit tests for the augmentation.

Dataset / Model WER/PER no augment WER/PER sign flip (flip_prob) % gain over no augment
LibriSpeech 100h (Transformer) 11.64 10.09 (0.2) 13.32
CommonVoice (wav2vec CTC) 12.33 11.8 (1.0) 4.30
VoiceBank (CRDNN Transducers) 17.02 16.05 (0.6) 5.70

$$ gain = \left( \frac{\text{BASELINE} - \text{AUGMENT}}{\text{BASELINE}} \right) \times 100 $$

Fixes #<issue_number>

Before submitting
  • Did you read the contributor guideline?
  • Did you make sure your PR does only one thing, instead of bundling different changes together?
  • Did you make sure to update the documentation with your changes? (if necessary)
  • Did you write any new necessary tests? (not for typos and docs)
  • Did you verify new and existing tests pass locally with your changes?
  • Did you list all the breaking changes introduced by this pull request?
  • Does your code adhere to project-specific code style and conventions?

PR review

Reviewer checklist
  • Is this pull request ready for review? (if not, please submit in draft mode)
  • Check that all items from Before submitting are resolved
  • Make sure the title is self-explanatory and the description concisely explains the PR
  • Add labels and milestones (and optionally projects) to the PR so it can be classified
  • Confirm that the changes adhere to compatibility requirements (e.g., Python version, platform)
  • Review the self-review checklist to ensure the code is ready for review

gfdb
gfdb commented Aug 1, 2024
View reviewed changes
Comment thread tests/unittests/test_augment.py
@asumagic asumagic added this to the v1.1.0 milestone Sep 4, 2024
@asumagic asumagic merged commit 188bd75 into speechbrain:develop Sep 5, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@asumagic asumagic asumagic approved these changes

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

v1.0.2

Development

Successfully merging this pull request may close these issues.

2 participants

@gfdb @asumagic