Can I read MaD TwinNet: Masker-Denoiser Architecture with Twin Networks for Monaural Sound Source Separation on EtoBox?

MaD TwinNet: Masker-Denoiser Architecture with Twin Networks for Monaural Sound Source Separation by Drossos, Konstantinos; Mimilakis, Stylianos Ioannis; Serdyuk, Dmitriy; Schuller, Gerald; Virtanen, Tuomas; Bengio, Yoshua is a scholarly article available to read on EtoBox.

What is MaD TwinNet: Masker-Denoiser Architecture with Twin Networks for Monaural Sound Source Separation about?

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.

Author

Drossos, Konstantinos; Mimilakis, Stylianos Ioannis; Serdyuk, Dmitriy; Schuller, Gerald; Virtanen, Tuomas; Bengio, Yoshua

Published

2018

Language

EN