posenhuang/deeplearningsourceseparation

Deep Recurrent Neural Networks for Source Separation

51
/ 100
Established

This helps audio engineers and researchers isolate specific sounds from a mixed audio file. You input a single audio recording containing multiple sound sources, like a song with vocals and instruments, or speech with background noise. It then outputs separate audio tracks for each distinct sound source, such as an isolated vocal track or a clean speech recording.

371 stars. No commits in the last 6 months.

Use this if you need to separate singing voices from music, extract clear speech from noisy environments, or break down mixed audio into its constituent sound components.

Not ideal if you are looking for a ready-to-use application with a graphical interface, as this project requires some command-line interaction and familiarity with MATLAB.

audio-editing sound-design speech-enhancement music-production forensic-audio
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

371

Forks

133

Language

MATLAB

License

Last pushed

Jul 21, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/posenhuang/deeplearningsourceseparation"

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