aminul-huq/Adversarial-Examples-For-Audio-Data
Repo for papers to read on adversarial attack and defense techniques in the audio domain.
This collection helps researchers and practitioners understand how audio-based AI systems, like speech-to-text, speaker verification, and voice assistants, can be fooled. It categorizes papers on methods for creating 'adversarial examples' that make AI misinterpret spoken input, and techniques to defend against these attacks. Anyone working on or deploying speech AI who needs to assess and improve the security and robustness of their systems would use this.
No commits in the last 6 months.
Use this if you are developing or deploying AI systems that process speech and want to understand how to make them more resilient to malicious audio inputs or evaluate their current vulnerabilities.
Not ideal if you are looking for ready-to-use code or tools to immediately implement attacks or defenses without diving into the underlying research.
Stars
41
Forks
4
Language
—
License
—
Category
Last pushed
Dec 06, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/aminul-huq/Adversarial-Examples-For-Audio-Data"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
kan-bayashi/ParallelWaveGAN
Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch
fatchord/WaveRNN
WaveRNN Vocoder + TTS
shangeth/wavencoder
WavEncoder is a Python library for encoding audio signals, transforms for audio augmentation,...
rishikksh20/iSTFTNet-pytorch
iSTFTNet : Fast and Lightweight Mel-spectrogram Vocoder Incorporating Inverse Short-time Fourier...
seungwonpark/melgan
MelGAN vocoder (compatible with NVIDIA/tacotron2)