piotrkawa/audio-deepfake-source-tracing

Baselines for IS25 Source Tracing Special Session

21
/ 100
Experimental

This project helps audio forensics experts, researchers, and content authenticators identify the source or generation method of manipulated or synthetic speech (deepfakes). You input audio recordings, and it outputs classifications indicating whether the audio is real or fake, and if fake, which deepfake system likely created it. It's designed for those investigating the origins of suspicious audio.

No commits in the last 6 months.

Use this if you need to trace the original generation method of an audio deepfake to understand its provenance.

Not ideal if you are looking for a simple 'real or fake' audio detector without needing to pinpoint the specific deepfake source.

audio-forensics speech-analysis deepfake-detection content-authentication digital-security
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 6 / 25

How are scores calculated?

Stars

33

Forks

2

Language

Python

License

Last pushed

Jan 03, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/piotrkawa/audio-deepfake-source-tracing"

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