Denoising Auto-Encoder with Recurrent Skip Connections and Residual Regression for Music Source Separation
By Jen-Yu Liu, Yi-Hsuan Yang. 2018
44 citations recorded by the source corpus.
Convolutional neural networks with skip connections have shown good performance in music source separation. In this work, we propose a denoising Auto-encoder with Recurrent skip Connections (ARC). We use 1D convolution along the temporal axis of the time-frequency feature map in all layers of the fully-convolutional network. The use of 1D convolution makes it possible to apply recurrent layers to the intermediate outputs of the convolution layers. In addition, we also propose an enhancement network and a residual regression method to further improve the separation result. The recurrent skip connections, the enhancement module, and the residual regression all improve the separation quality. The ARC model with residual regression achieves 5.74 siganl-to-distoration ratio (SDR) in vocals with MUSDB (used in SiSEC 2018). We also evaluate the ARC model alone on the older dataset DSD100 (used in SiSEC 2016) and it achieves 5.91 SDR in vocals.
Subfields: Artificial Intelligence, Signal Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- David Samuel
- Jason Naradowsky
- Aditya Ganeshan
- Yejin Choi
- Yuki Mitsufuji
- Naoya Takahashi
- Samuel R. Bowman
- Yonatan Belinkov
In Signal Processing
Citations in the corpus
- Music Source Separation in the Waveform Domain (2019, neutral): “…on speech source separation [Grais et al., 2014], followed by works on music using simple fully connected networks over few spectrogram frames [Uhlich et al., 2015], LSTMs [Uhlich et al., 2017], or multi scale convolutional/recurrent networks [Liu and Yang, 2018, Takahashi and Mitsufuji, 2017].”
- Meta-Learning Extractors for Music Source Separation (2020, methodology): “Here SDR was either taken from the respective papers ([10][11][12]) or from the SiSEC18 [4] evaluation scores ([13][14][15]), and we show the median of frames, median of tracks, evaluated with BSSEval v4 [4].”