Monaural Singing Voice Separation with Skip-Filtering Connections and Recurrent Inference of Time-Frequency Mask

2017/11/04 by Mimilakis, Stylianos Ioannis, Drossos, Konstantinos, Santos, João F. +3
#Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Sound (cs.SD) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.1711.01437

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.

Related

• A Recurrent Encoder-Decoder Approach with Skip-filtering Connections for Monaural Singing Voice Separation
• HTMD-Net: A Hybrid Masking-Denoising Approach to Time-Domain Monaural Singing Voice Separation
• Semi-Supervised Monaural Singing Voice Separation With a Masking Network Trained on Synthetic Mixtures
• MaD TwinNet: Masker-Denoiser Architecture with Twin Networks for Monaural Sound Source Separation
• Continual Learning for Singing Voice Separation with Human in the Loop Adaptation