santi-pdp/segan

Speech Enhancement Generative Adversarial Network in TensorFlow

51
/ 100
Established

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.

audio-processing speech-enhancement noise-reduction sound-engineering voice-clarity
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

859

Forks

281

Language

Python

License

MIT

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.