Guri10/Deepfake-Audio-Detection-with-XAI

This project focuses on detecting deepfake audio using advanced neural network architectures like VGG16, MobileNet, ResNet, and custom CNNs. It incorporates explainable AI (XAI) methods like LIME, Grad-CAM, and SHAP to enhance detection accuracy and provide insights into model predictions.

31
/ 100
Emerging

This tool helps you determine if an audio recording is a deepfake or authentic. You provide an audio file, and it tells you whether the sound has been artificially generated, along with explanations for its decision. This is ideal for professionals who need to verify the authenticity of spoken audio, such as journalists, researchers, or legal professionals.

No commits in the last 6 months.

Use this if you need to reliably identify fabricated audio content and understand why the detection system made its judgment.

Not ideal if you are looking to detect other forms of media manipulation, such as deepfake video, or if you need to analyze music or non-speech audio.

audio-verification digital-forensics content-authentication fraud-detection journalism-ethics
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 15 / 25

How are scores calculated?

Stars

54

Forks

9

Language

Jupyter Notebook

License

Last pushed

Feb 16, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Guri10/Deepfake-Audio-Detection-with-XAI"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.