# On the Design of Deep Priors for Unsupervised Audio Restoration

arXiv: https://arxiv.org/abs/2104.07161 · HTML: https://mlsanity.com/paper/2104.07161/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 26 references that are in the map.
- First posted on arXiv 14 Apr 2021.

## Builds on (most cited first, 16 of 16)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation](https://mlsanity.com/paper/1809.07454/) (2018)
- [Adversarial Audio Synthesis](https://mlsanity.com/paper/1802.04208/) (2018)
- [SEGAN: Speech Enhancement Generative Adversarial Network](https://mlsanity.com/paper/1703.09452/) (2017)
- [Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation](https://mlsanity.com/paper/1806.03185/) (2018)
- ["Double-DIP": Unsupervised Image Decomposition via Coupled Deep-Image-Priors](https://mlsanity.com/paper/1812.00467/) (2018)
- [Self-Supervised Generation of Spatial Audio for 360 Video](https://mlsanity.com/paper/1809.02587/) (2018)
- [Solving Linear Inverse Problems Using GAN Priors: An Algorithm with Provable Guarantees](https://mlsanity.com/paper/1802.08406/) (2018)
- [Demucs: Deep Extractor for Music Sources with extra unlabeled data remixed](https://mlsanity.com/paper/1909.01174/) (2019)
- [The 2018 Signal Separation Evaluation Campaign](https://mlsanity.com/paper/1804.06267/) (2018)
- [Unsupervised Audio Source Separation using Generative Priors](https://mlsanity.com/paper/2005.13769/) (2020)
- [Deep Long Audio Inpainting](https://mlsanity.com/paper/1911.06476/) (2019)
- [Deep Audio Prior](https://mlsanity.com/paper/1912.10292/) (2019)

## Built on by (most cited first, 2 of 2)

- [A2SB: Audio-to-Audio Schrodinger Bridges](https://mlsanity.com/paper/2501.11311/) (2025)
- [Deep Audio Waveform Prior](https://mlsanity.com/paper/2207.10441/) (2022)

## Abstract (arXiv)

Unsupervised deep learning methods for solving audio restoration problems extensively rely on carefully tailored neural architectures that carry strong inductive biases for defining priors in the time or spectral domain. In this context, lot of recent success has been achieved with sophisticated convolutional network constructions that recover audio signals in the spectral domain. However, in practice, audio priors require careful engineering of the convolutional kernels to be effective at solving ill-posed restoration tasks, while also being easy to train. To this end, in this paper, we propose a new U-Net based prior that does not impact either the network complexity or convergence behavior of existing convolutional architectures, yet leads to significantly improved restoration. In particular, we advocate the use of carefully designed dilation schedules and dense connections in the U-Net architecture to obtain powerful audio priors. Using empirical studies on standard benchmarks and a variety of ill-posed restoration tasks, such as audio denoising, in-painting and source separation, we demonstrate that our proposed approach consistently outperforms widely adopted audio prior architectures.