seorim0/SE-using-SRL-Model

Causal Speech Enhancement Based on a Two-Branch Nested U-Net Architecture Using Self-Supervised Speech Embeddings

32
/ 100
Emerging

This project helps audio engineers and speech scientists improve the clarity and naturalness of spoken audio by removing background noise in real-time. It takes noisy speech recordings as input and produces enhanced speech that is easier to understand and sounds more natural. The primary users are researchers and practitioners working with audio data where clean speech is critical.

No commits in the last 6 months.

Use this if you need to enhance speech quality from noisy environments in live applications, ensuring low latency and improved intelligibility.

Not ideal if your primary goal is offline noise reduction without real-time constraints, or if you are working with non-speech audio.

speech-enhancement audio-processing real-time-audio noise-reduction voice-clarity
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

19

Forks

2

Language

Python

License

MIT

Last pushed

Jun 06, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/seorim0/SE-using-SRL-Model"

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