seorim0/DNN-based-Speech-Enhancement-in-the-frequency-domain

DNN-based SE in the frequency domain using Pytorch. You can test some state-of-the-art networks using T-F masking or spectral mapping method.

42
/ 100
Emerging

This tool helps improve the clarity of noisy audio recordings by separating speech from background noise. You provide audio files containing speech mixed with various noises, and it outputs enhanced audio where the speech is much clearer. This is ideal for researchers or engineers working on voice applications who need to clean up audio data for further analysis or use.

No commits in the last 6 months.

Use this if you need to significantly reduce background noise in speech recordings for tasks like voice assistant development, audio forensics, or call center analytics.

Not ideal if you need a plug-and-play solution without deep learning training, or if you're dealing with music or non-speech audio enhancement.

speech-processing audio-enhancement noise-reduction voice-technology audio-forensics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

58

Forks

16

Language

Python

License

MIT

Last pushed

Apr 02, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/seorim0/DNN-based-Speech-Enhancement-in-the-frequency-domain"

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