Singing-Voice-Separation

This is an implementation of U-Net for vocal separation with tensorflow

Requirement

I prepare CCMixter datasets in "./data" and Each track consisted of Mixed, instrumental, Vocal version

$ python CCMixter_process.py

$ python Training.py

$ python Test.py

Andreas Jansson, et al. SINGING VOICE SEPARATION WITH DEEP U-NET CONVOLUTIONAL NETWORKS. 2017.
paper: https://ismir2017.smcnus.org/wp-content/uploads/2017/10/171_Paper.pdf

Name		Name	Last commit message	Last commit date
Latest commit History 14 Commits
Spectrogram		Spectrogram
data		data
model		model
CCMixter_process.py		CCMixter_process.py
README.md		README.md
Test.py		Test.py
Training.py		Training.py
U_net.py		U_net.py
config.py		config.py
util.py		util.py