# Voice and accompaniment separation in music using self-attention convolutional neural network

arXiv: https://arxiv.org/abs/2003.08954 · HTML: https://mlsanity.com/paper/2003.08954/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Mar 2020.

## Built on by (most cited first, 3 of 3)

- [CWS-PResUNet: Music Source Separation with Channel-wise Subband Phase-aware ResUNet](https://mlsanity.com/paper/2112.04685/) (2021)
- [MuSLCAT: Multi-Scale Multi-Level Convolutional Attention Transformer for Discriminative Music Modeling on Raw Waveforms](https://mlsanity.com/paper/2104.02309/) (2021)
- [Improving Real-Time Music Accompaniment Separation with MMDenseNet](https://mlsanity.com/paper/2407.00657/) (2024)

## Abstract (arXiv)

Music source separation has been a popular topic in signal processing for decades, not only because of its technical difficulty, but also due to its importance to many commercial applications, such as automatic karoake and remixing. In this work, we propose a novel self-attention network to separate voice and accompaniment in music. First, a convolutional neural network (CNN) with densely-connected CNN blocks is built as our base network. We then insert self-attention subnets at different levels of the base CNN to make use of the long-term intra-dependency of music, i.e., repetition. Within self-attention subnets, repetitions of the same musical patterns inform reconstruction of other repetitions, for better source separation performance. Results show the proposed method leads to 19.5% relative improvement in vocals separation in terms of SDR. We compare our methods with state-of-the-art systems i.e. MMDenseNet and MMDenseLSTM.