Recent Releases of audiodeepfake-detection
audiodeepfake-detection - audiofakedetect v0.1.3
Audiodeepfake detection using WPT - Version 0.1.4
What's Changed
- added AST model by @kgasenzer in https://github.com/gan-police/audiodeepfake-detection/pull/33
- add type check tensorboard by @kgasenzer in https://github.com/gan-police/audiodeepfake-detection/pull/32
Full Changelog: https://github.com/gan-police/audiodeepfake-detection/compare/v0.1.2...v0.1.3
- Python
Published by kgasenzer over 2 years ago
audiodeepfake-detection - audiofakedetect v0.1.2
Audiodeepfake detection using WPT - Version 0.1.2
Summary
This release introduces some new content to provide evidence and example results, like demo models for the package.
What's Changed
- add example models for coif4, sym5, stft for standard config by @kgasenzer in https://github.com/gan-police/audiodeepfake-detection/pull/30
- Fix broken links by @kgasenzer in https://github.com/gan-police/audiodeepfake-detection/pull/31
Full Changelog: https://github.com/gan-police/audiodeepfake-detection/compare/v0.1.1...v0.1.2
- Python
Published by kgasenzer over 2 years ago
audiodeepfake-detection - audiofakedetect v0.1.1
Audiodeepfake detection using WPT - Version 0.1.1
Summary
This release introduces some new features, and bug fixes. Mainly some training and evaluating bugs were fixed and a pipeline extraction feature for creating example audios that are misclassified by some models but not by ours.
What's Changed
- Improve appearance by @kgasenzer in https://github.com/gan-police/audiodeepfake-detection/pull/28
- Path extraction by @kgasenzer in https://github.com/gan-police/audiodeepfake-detection/pull/29
Full Changelog: https://github.com/gan-police/audiodeepfake-detection/compare/v0.1.0...v0.1.1
- Python
Published by kgasenzer over 2 years ago
audiodeepfake-detection - audiofakedetect v0.1.0
Audiodeepfake detection using WPT - Version 0.1.0
Summary
This release introduces several new features, enhancements, and bug fixes. It shows the used scripts and modules we used to create the experiment results in our research paper "Towards generalizing deep-audio fake detection networks". It serves as supplementary code.
Deprecations and Removals
- Removal of all CWT dependent modules
Known Issues
- Even though we are using fixed seeds to ensure reproducibility the results might be slightly different, if not the exact same hardware is used.
What's New
- LFCC Support by @kgasenzer in https://github.com/gan-police/audiodeepfake-detection/pull/6
- LCNN baseline by @kgasenzer in https://github.com/gan-police/audiodeepfake-detection/pull/8
- Minor Fixes by @kgasenzer in https://github.com/gan-police/audiodeepfake-detection/pull/9
- Multi gpu training and testing by @kgasenzer in https://github.com/gan-police/audiodeepfake-detection/pull/11
- booster modifications by @kgasenzer in https://github.com/gan-police/audiodeepfake-detection/pull/12
- preparation fixes and downsampling by @kgasenzer in https://github.com/gan-police/audiodeepfake-detection/pull/13
- ASVspoof Prep by @kgasenzer in https://github.com/gan-police/audiodeepfake-detection/pull/14
- Block Norm by @kgasenzer in https://github.com/gan-police/audiodeepfake-detection/pull/15
- Cross evaluation and hyper model search by @kgasenzer in https://github.com/gan-police/audiodeepfake-detection/pull/16
- Grid search model hyperparameters by @kgasenzer in https://github.com/gan-police/audiodeepfake-detection/pull/17
- Fix dataloader and stft functionality by @kgasenzer in https://github.com/gan-police/audiodeepfake-detection/pull/18
- Efficient new dataloading by @kgasenzer in https://github.com/gan-police/audiodeepfake-detection/pull/23
- Fingerprints by @v0lta
- Documentation added
- Clean up and Tests @kgasenzer in https://github.com/gan-police/audiodeepfake-detection/pull/27
- Python
Published by kgasenzer over 2 years ago