Monaural Singing Voice Separation with Skip-Filtering Connections and Recurrent Inference of Time-Frequency Mask
Stylianos Ioannis Mimilakis, Konstantinos Drossos, João Felipe Santos, Gerald Schuller, Tuomas Virtanen, Yoshua Bengio
Abstract
Singing voice separation based on deep learning relies on the usage of time-frequency masking. In many cases the masking process is not a learnable function or is not encapsulated into the deep learning optimization. Consequently, most of the existing methods rely on a post processing step using the generalized Wiener filtering. This work proposes a method that learns and optimizes (during training) a source-dependent mask and does not need the aforementioned post processing step. We introduce a recurrent inference algorithm, a sparse transformation step to improve the mask generation process, and a learned denoising filter. Obtained results show an increase of 0.49 dB for the signal to distortion ratio and 0.30 dB for the signal to interference ratio, compared to previous state-of-the-art approaches for monaural singing voice separation.
BibTeX
@inproceedings{icassp2018_monauralsingingv,
title = {Monaural Singing Voice Separation with Skip-Filtering Connections and Recurrent Inference of Time-Frequency Mask},
author = {Stylianos Ioannis Mimilakis and Konstantinos Drossos and João Felipe Santos and Gerald Schuller and Tuomas Virtanen and Yoshua Bengio},
booktitle = {ICASSP 2018},
year = {2018}
}