# Deep Audio Waveform Prior

arXiv: https://arxiv.org/abs/2207.10441 · HTML: https://mlsanity.com/paper/2207.10441/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 20 references that are in the map.
- First posted on arXiv 21 Jul 2022.

## Builds on (most cited first, 11 of 11)

- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Real Time Speech Enhancement in the Waveform Domain](https://mlsanity.com/paper/2006.12847/) (2020)
- [Pyroomacoustics: A Python package for audio room simulations and array processing algorithms](https://mlsanity.com/paper/1710.04196/) (2017)
- ["Double-DIP": Unsupervised Image Decomposition via Coupled Deep-Image-Priors](https://mlsanity.com/paper/1812.00467/) (2018)
- [Music Source Separation in the Waveform Domain](https://mlsanity.com/paper/1911.13254/) (2019)
- [Hybrid Spectrogram and Waveform Source Separation](https://mlsanity.com/paper/2111.03600/) (2021)
- [Voice Separation with an Unknown Number of Multiple Speakers](https://mlsanity.com/paper/2003.01531/) (2020)
- [Weighted Speech Distortion Losses for Neural-network-based Real-time Speech Enhancement](https://mlsanity.com/paper/2001.10601/) (2020)
- [Single channel voice separation for unknown number of speakers under reverberant and noisy settings](https://mlsanity.com/paper/2011.02329/) (2020)
- [Deep Audio Prior](https://mlsanity.com/paper/1912.10292/) (2019)
- [On the Design of Deep Priors for Unsupervised Audio Restoration](https://mlsanity.com/paper/2104.07161/) (2021)

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

- [Generative Semantic Communication: Diffusion Models Beyond Bit Recovery](https://mlsanity.com/paper/2306.04321/) (2023)
- [AERO: Audio Super Resolution in the Spectral Domain](https://mlsanity.com/paper/2211.12232/) (2022)

## Abstract (arXiv)

Convolutional neural networks contain strong priors for generating natural looking images [1]. These priors enable image denoising, super resolution, and inpainting in an unsupervised manner. Previous attempts to demonstrate similar ideas in audio, namely deep audio priors, (i) use hand picked architectures such as harmonic convolutions, (ii) only work with spectrogram input, and (iii) have been used mostly for eliminating Gaussian noise [2]. In this work we show that existing SOTA architectures for audio source separation contain deep priors even when working with the raw waveform. Deep priors can be discovered by training a neural network to generate a single corrupted signal when given white noise as input. A network with relevant deep priors is likely to generate a cleaner version of the signal before converging on the corrupted signal. We demonstrate this restoration effect with several corruptions: background noise, reverberations, and a gap in the signal (audio inpainting).