MaD TwinNet: Masker-Denoiser Architecture with Twin Networks for Monaural Sound Source Separation
Abstract
Monaural singing voice separation task focuses on the prediction of the singing voice from a single channel music mixture signal. Current state of the art (SOTA) results in monaural singing voice separation are obtained with deep learning based methods. In this work we present a novel deep learning based method that learns long-term temporal patterns and structures of a musical piece. We build upon the recently proposed Masker-Denoiser (MaD) architecture and we enhance it with the Twin Networks, a technique to regularize a recurrent generative network using a backward running copy of the network. We evaluate our method using the Demixing Secret Dataset and we obtain an increment to signal-to-distortion ratio (SDR) of 0.37 dB and to signal-to-interference ratio (SIR) of 0.23 dB, compared to previous SOTA results.
Keywords
Cite
@article{arxiv.1802.00300,
title = {MaD TwinNet: Masker-Denoiser Architecture with Twin Networks for Monaural Sound Source Separation},
author = {Konstantinos Drossos and Stylianos Ioannis Mimilakis and Dmitriy Serdyuk and Gerald Schuller and Tuomas Virtanen and Yoshua Bengio},
journal= {arXiv preprint arXiv:1802.00300},
year = {2018}
}