Multi-band multi-scale DenseNet with dilated convolution for background music separation

Abstract

We propose a multi-band multi-scale DenseNet with dilated convolution that separates background music signals from broadcast content. Dilated convolution can learn the multi-scale context information represented by spectrogram. In computer simulation experiments, the proposed architecture is shown to improve Signal to Distortion Ratio (SDR) by 0.15 dB and 0.27 dB in 0dB and –10 dB Signal to Noise Ratio (SNR) environments, respectively.