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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keydrossos2018mad

Related papers

• Htmd-net: A Hybrid Masking-denoising Approach To Time-domain Monaural Singing Voice Separation (2021)2.26
• Multichannel Singing Voice Separation By Deep Neural Network Informed DOA Constrained CNMF (2020)5.84
• A Recurrent Encoder-decoder Approach With Skip-filtering Connections For Monaural Singing Voice Separation (2017)9.41
• Monaural Singing Voice Separation With Skip-filtering Connections And Recurrent Inference Of Time-frequency Mask (2017)10.07
• Jointly Detecting And Separating Singing Voice: A Multi-task Approach (2018)7.81
• Voice And Accompaniment Separation In Music Using Self-attention Convolutional Neural Network (2020)0.00
• Depthwise Separable Convolutions Versus Recurrent Neural Networks For Monaural Singing Voice Separation (2020)0.00
• Mmdenselstm: An Efficient Combination Of Convolutional And Recurrent Neural Networks For Audio Source Separation (2018)15.28