# Complex ratio masking for singing voice separation

arXiv: https://arxiv.org/abs/2011.02008 · HTML: https://mlsanity.com/paper/2011.02008/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Nov 2020.

## Built on by (most cited first, 1 of 1)

- [Cross-modal Generative Model for Visual-Guided Binaural Stereo Generation](https://mlsanity.com/paper/2311.07630/) (2023)

## Abstract (arXiv)

Music source separation is important for applications such as karaoke and remixing. Much of previous research focuses on estimating short-time Fourier transform (STFT) magnitude and discarding phase information. We observe that, for singing voice separation, phase can make considerable improvement in separation quality. This paper proposes a complex ratio masking method for voice and accompaniment separation. The proposed method employs DenseUNet with self attention to estimate the real and imaginary components of STFT for each sound source. A simple ensemble technique is introduced to further improve separation performance. Evaluation results demonstrate that the proposed method outperforms recent state-of-the-art models for both separated voice and accompaniment.