hammaad2002/ASRAdversarialAttacks

An ASR (Automatic Speech Recognition) adversarial attack repository.

21
/ 100
Experimental

This helps you test how vulnerable an Automatic Speech Recognition (ASR) system is to subtle changes in audio. You provide an audio file and an ASR model, and it outputs a modified audio file designed to trick the ASR system into transcribing it incorrectly, even though a human listener might not notice the change. It's useful for researchers or developers working on speech recognition technology.

No commits in the last 6 months.

Use this if you need to evaluate the security and robustness of your ASR models against intentionally crafted audio designed to fool them.

Not ideal if you are looking to improve the general accuracy of your ASR system or simply transcribe audio without testing its vulnerabilities.

speech-recognition-security audio-adversarial-testing model-robustness-evaluation AI-security-research
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

39

Forks

2

Language

Jupyter Notebook

License

Last pushed

Nov 07, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/hammaad2002/ASRAdversarialAttacks"

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