dimitriStoidis/GenGAN
Repository for the paper: Generating gender-ambiguous voices for privacy-preserving speech recognition
This project helps protect privacy in speech recognition by transforming voices to sound gender-ambiguous. It takes an audio file with a specific person's voice and outputs a new audio file where the speaker's gender is concealed, while the speech content remains clear. This is useful for privacy officers, researchers, or anyone working with voice data who needs to remove gender information.
No commits in the last 6 months.
Use this if you need to process spoken audio data while protecting the privacy of the speaker's gender.
Not ideal if your primary goal is speaker authentication or precise gender analysis.
Stars
8
Forks
1
Language
Python
License
MIT
Category
Last pushed
Nov 28, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/dimitriStoidis/GenGAN"
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)