# Improving singing voice separation using Deep U-Net and Wave-U-Net with data augmentation

arXiv: https://arxiv.org/abs/1903.01415 · HTML: https://mlsanity.com/paper/1903.01415/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Mar 2019.

## Built on by (most cited first, 4 of 4)

- [Differentiable Model Compression via Pseudo Quantization Noise](https://mlsanity.com/paper/2104.09987/) (2021)
- [Sound Demixing Challenge 2023 Music Demixing Track Technical Report: TFC-TDF-UNet v3](https://mlsanity.com/paper/2306.09382/) (2023)
- [Improved singing voice separation with chromagram-based pitch-aware remixing](https://mlsanity.com/paper/2203.15092/) (2022)
- [Adversarial Unsupervised Domain Adaptation for Harmonic-Percussive Source Separation](https://mlsanity.com/paper/2101.00701/) (2021)

## Abstract (arXiv)

State-of-the-art singing voice separation is based on deep learning making use of CNN structures with skip connections (like U-net model, Wave-U-Net model, or MSDENSELSTM). A key to the success of these models is the availability of a large amount of training data. In the following study, we are interested in singing voice separation for mono signals and will investigate into comparing the U-Net and the Wave-U-Net that are structurally similar, but work on different input representations. First, we report a few results on variations of the U-Net model. Second, we will discuss the potential of state of the art speech and music transformation algorithms for augmentation of existing data sets and demonstrate that the effect of these augmentations depends on the signal representations used by the model. The results demonstrate a considerable improvement due to the augmentation for both models. But pitch transposition is the most effective augmentation strategy for the U-Net model, while transposition, time stretching, and formant shifting have a much more balanced effect on the Wave-U-Net model. Finally, we compare the two models on the same dataset.