On the design of deep priors for unsupervised audio restoration

Vivek Sivaraman Narayanaswamy, Jayaraman J. Thiagarajan, Andreas Spanias

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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.

Original languageEnglish (US)
Title of host publication22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021
PublisherInternational Speech Communication Association
Pages2858-2862
Number of pages5
ISBN (Electronic)9781713836902
DOIs
StatePublished - 2021
Event22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021 - Brno, Czech Republic
Duration: Aug 30 2021Sep 3 2021

Publication series

NameProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Volume4
ISSN (Print)2308-457X
ISSN (Electronic)1990-9772

Conference

Conference22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021
Country/TerritoryCzech Republic
CityBrno
Period8/30/219/3/21

Keywords

  • Deep audio priors
  • Denoising
  • Inpainting
  • Source separation
  • Unsupervised audio restoration

ASJC Scopus subject areas

  • Language and Linguistics
  • Human-Computer Interaction
  • Signal Processing
  • Software
  • Modeling and Simulation

Fingerprint

Dive into the research topics of 'On the design of deep priors for unsupervised audio restoration'. Together they form a unique fingerprint.

Cite this