Skip to content

Singing-Voice Separation From Monaural Recordings Using Robust Principal Component Analysis

Notifications You must be signed in to change notification settings

posenhuang/singingvoiceseparationrpca

Repository files navigation

Singing-Voice Separation From Monaural Recordings Using Robust Principal Component

This package contains the Matlab codes implementing the RPCA source separation algorithm described in "Singing-Voice Separation From Monaural Recordings Using Robust Principal Component Analysis," ICASSP 2012.

Our algorithm is composed of the following parts:

The algorithm achieves the state-of-the-art performance on MIR-1K Dataset in an unsupervised way.

Demo

Run rpca_mask_demo.m to see how the functions are called. Change RUN_EVALUATION = 0 if you don't need evaluation.

For more information, please check: https://sites.google.com/site/singingvoiceseparationrpca/

License

MIT

About

Singing-Voice Separation From Monaural Recordings Using Robust Principal Component Analysis

Resources

Stars

Watchers

Forks

Packages

No packages published