Audio Source Separation Via Multi-scale Learning With Dilated Dense U-nets

Abstract

Modern audio source separation techniques rely on optimizing sequence model architectures such as, 1D-CNNs, on mixture recordings to generalize well to unseen mixtures. Specifically, recent focus is on time-domain based architectures such as Wave-U-Net which exploit temporal context by extracting multi-scale features. However, the optimality of the feature extraction process in these architectures has not been well investigated. In this paper, we examine and recommend critical architectural changes that forge an optimal multi-scale feature extraction process. To this end, we replace regular \(1-\)D convolutions with adaptive dilated convolutions that have innate capability of capturing increased context by using large temporal receptive fields. We also investigate the impact of dense connections on the extraction process that encourage feature reuse and better gradient flow. The dense connections between the downsampling and upsampling paths of a U-Net architecture capture multi-resolu

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keynarayanaswamy2019audio

Related papers

• Wave-u-net: A Multi-scale Neural Network For End-to-end Audio Source Separation (2018)0.00
• D3net: Densely Connected Multidilated Densenet For Music Source Separation (2020)0.00
• Time-domain Audio Source Separation Based On Wave-u-net Combined With Discrete Wavelet Transform (2020)9.76
• Mmdenselstm: An Efficient Combination Of Convolutional And Recurrent Neural Networks For Audio Source Separation (2018)15.28
• Raw Multi-channel Audio Source Separation Using Multi-resolution Convolutional Auto-encoders (2018)11.58
• Multi-resolution Fully Convolutional Neural Networks For Monaural Audio Source Separation (2017)8.82
• Dilated U-net Based Approach For Multichannel Speech Enhancement From First-order Ambisonics Recordings (2020)0.00
• Interleaved Multitask Learning For Audio Source Separation With Independent Databases (2019)0.00