santi-pdp/segan
Speech Enhancement Generative Adversarial Network in TensorFlow
This project helps audio engineers, researchers, and developers clean up noisy speech recordings. It takes raw audio files containing speech mixed with various background noises and produces cleaner speech waveforms. You would use this if you need to improve the clarity of spoken audio by automatically removing unwanted sounds.
859 stars. No commits in the last 6 months.
Use this if you have speech recordings corrupted by background noise and need a robust, generalizable way to enhance speech quality without knowing the specific noise conditions or speaker identities.
Not ideal if you are looking for a simple, off-the-shelf application to clean audio without any technical setup, or if your primary need is for music denoising rather than speech.
Stars
859
Forks
281
Language
Python
License
MIT
Category
Last pushed
Mar 24, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/santi-pdp/segan"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
iver56/audiomentations
A Python library for audio data augmentation. Useful for making audio ML models work well in the...
Rikorose/DeepFilterNet
Noise supression using deep filtering
torchsynth/torchsynth
A GPU-optional modular synthesizer in pytorch, 16200x faster than realtime, for audio ML researchers.
marl/openl3
OpenL3: Open-source deep audio and image embeddings
archinetai/audio-data-pytorch
A collection of useful audio datasets and transforms for PyTorch.