Added reference

This commit is contained in:
Romain Hennequin
2019-12-20 18:27:06 +01:00
committed by GitHub
parent 5a36b6aa27
commit 3c6b794ccf

View File

@@ -2,8 +2,10 @@
# coding: utf8
"""
This module contains building functions for U-net source separation source
separation models. Each instrument is modeled by a single U-netconvolutional
This module contains building functions for U-net source
separation models in a similar way as in A. Jansson et al. "Singing
voice separation with deep u-net convolutional networks", ISMIR 2017.
Each instrument is modeled by a single U-net convolutional
/ deconvolutional network that take a mix spectrogram as input and the
estimated sound spectrogram as output.
"""