D3net: Densely Connected Multidilated Densenet For Music Source Separation

Abstract

Music source separation involves a large input field to model a long-term dependence of an audio signal. Previous convolutional neural network (CNN)-based approaches address the large input field modeling using sequentially down- and up-sampling feature maps or dilated convolution. In this paper, we claim the importance of a rapid growth of a receptive field and a simultaneous modeling of multi-resolution data in a single convolution layer, and propose a novel CNN architecture called densely connected dilated DenseNet (D3Net). D3Net involves a novel multi-dilated convolution that has different dilation factors in a single layer to model different resolutions simultaneously. By combining the multi-dilated convolution with DenseNet architecture, D3Net avoids the aliasing problem that exists when we naively incorporate the dilated convolution in DenseNet. Experimental results on MUSDB18 dataset show that D3Net achieves state-of-the-art performance with an average signal to distortion rati

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keytakahashi2020d3net

Related papers

• Audio Source Separation Via Multi-scale Learning With Dilated Dense U-nets (2019)0.00
• Mmdenselstm: An Efficient Combination Of Convolutional And Recurrent Neural Networks For Audio Source Separation (2018)15.28
• Audio-based Music Classification With Densenet And Data Augmentation (2019)10.48
• Sams-net: A Sliced Attention-based Neural Network For Music Source Separation (2019)9.03
• Depthwise Separable Convolutions Versus Recurrent Neural Networks For Monaural Singing Voice Separation (2020)0.00
• MDCNN-SID: Multi-scale Dilated Convolution Network For Singer Identification (2020)5.24
• Voice And Accompaniment Separation In Music Using Self-attention Convolutional Neural Network (2020)0.00
• Denoising Auto-encoder With Recurrent Skip Connections And Residual Regression For Music Source Separation (2018)10.35