Multi-scale Multi-band DenseNets for Audio Source Separation

Abstract

This paper deals with the problem of audio source separation. To handle the complex and ill-posed nature of the problems of audio source separation, the current state-of-the-art approaches employ deep neural networks to obtain instrumental spectra from a mixture. In this study, we propose a novel network architecture that extends the recently developed densely connected convolutional network (DenseNet), which has shown excellent results on image classification tasks. To deal with the specific problem of audio source separation, an up-sampling layer, block skip connection and band-dedicated dense blocks are incorporated on top of DenseNet. The proposed approach takes advantage of long contextual information and outperforms state-of-the-art results on SiSEC 2016 competition by a large margin in terms of signal-to-distortion ratio. Moreover, the proposed architecture requires significantly fewer parameters and considerably less training time compared with other methods.

to appear at WASPAA 2017

References in corpus (3)

• Densely Connected Convolutional Networks
• A Fully Convolutional Deep Auditory Model for Musical Chord Recognition
• AENet: Learning Deep Audio Features for Video Analysis

Cited by in corpus (6)

• Voice and accompaniment separation in music using self-attention convolutional neural network
• Audio query-based music source separation
• Improving DNN-based Music Source Separation using Phase Features
• LightSAFT: Lightweight Latent Source Aware Frequency Transform for Source Separation
• Harmonic-Percussive Source Separation with Deep Neural Networks and Phase Recovery
• Improving Voice Separation by Incorporating End-to-end Speech Recognition