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

Update AudioEffects with New Audio Attacks and Update Configuration #507

Open
wants to merge 2 commits into
base: main
Choose a base branch
from

Conversation

hastagAB
Copy link

Summary

Update new audio attacks to the AudioEffects class and update the configuration in default.yaml to reflect the newly added effects.

New Audio Effects Added:

  1. Pitch Shift: Changes the pitch of the audio signal by a given number of steps without altering the duration.
  2. Reverse: Reverses the entire audio signal, simulating a backward playback.
  3. Clipping: Clips the audio signal to a specific threshold, introducing distortion.
  4. Time Stretch: Changes the duration of the audio without modifying the pitch, useful for testing stretched audio scenarios.
  5. Tremolo: Applies amplitude modulation to create a tremolo effect.
  6. Flanger: Introduces a delayed version of the signal with periodic modulation, creating a swirling sound effect.
  7. Bit Crusher: Reduces the bit depth of the audio signal, introducing digital distortion for lo-fi simulation.
  8. Ring Modulation: Multiplies the audio signal with a sine wave, resulting in a metallic sound effect.
  9. Granulate: Breaks the audio into overlapping grains, creating a stutter-like or granulated effect.

Changes Made:

  1. AudioEffects Class:

    • Add new methods for the above effects to expand the transformation possibilities.
    • Ensure all new methods return audio tensors consistent with the existing interface.
  2. default.yaml Configuration File:

    • Add configurations for each of the newly added audio effects.
    • Included default parameters such as sample rates, modulation frequencies, bit depths, etc.
    • Updated aug_weights to include the new effects, with default weights for augmentation selection during evaluations.

Ref: facebookresearch/audioseal#57

@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Nov 26, 2024
@antoine-tran antoine-tran self-requested a review November 26, 2024 01:56
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants