PierreChouteau/umss_icassp

ICASSP 2024 paper - A Fully Differentiable Model for Unsupervised Singing Voice Separation

27
/ 100
Experimental

This project helps audio engineers, music producers, and researchers separate singing voices from instrumental music, especially in complex vocal ensembles. You provide an audio file with mixed vocals and instruments, and it outputs individual tracks for each distinct singing voice and the accompanying music. It's designed for anyone needing to isolate vocal performances or analyze individual voices within a musical piece.

No commits in the last 6 months.

Use this if you need to extract individual singing voice tracks from a multi-vocal and instrumental audio recording without manually labelling or supervising the separation process.

Not ideal if you are looking for general sound source separation beyond singing voices or if you only need to remove vocals entirely from a track.

music-production audio-engineering vocal-performance-analysis ethnomusicology sound-design
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

14

Forks

1

Language

Python

License

Apache-2.0

Last pushed

Mar 07, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/PierreChouteau/umss_icassp"

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