Monaural Singing Voice Separation With Skip-filtering Connections And Recurrent Inference Of Time-frequency Mask

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.

Stats

• citations21
• S2 citations—
• github stars0
• HF likes0
• heat score10.07
• arxiv keymimilakis2017monaural

Related papers

• A Recurrent Encoder-decoder Approach With Skip-filtering Connections For Monaural Singing Voice Separation (2017)9.41
• Htmd-net: A Hybrid Masking-denoising Approach To Time-domain Monaural Singing Voice Separation (2021)2.26
• Mad Twinnet: Masker-denoiser Architecture With Twin Networks For Monaural Sound Source Separation (2018)0.00
• Unsupervised Interpretable Representation Learning For Singing Voice Separation (2020)5.84
• Multichannel Singing Voice Separation By Deep Neural Network Informed DOA Constrained CNMF (2020)5.84
• Singing Voice Separation Using A Deep Convolutional Neural Network Trained By Ideal Binary Mask And Cross Entropy (2018)11.19
• Depthwise Separable Convolutions Versus Recurrent Neural Networks For Monaural Singing Voice Separation (2020)0.00
• Voicefilter: Targeted Voice Separation By Speaker-conditioned Spectrogram Masking (2018)17.48