TY - GEN
T1 - On the design of deep priors for unsupervised audio restoration
AU - Narayanaswamy, Vivek Sivaraman
AU - Thiagarajan, Jayaraman J.
AU - Spanias, Andreas
N1 - Funding Information:
This work was performed under the auspices of the U.S. Department of Energy by the Lawrence Livermore National Laboratory under Contract No. DE-AC52-07NA27344, Lawrence Livermore National Security, LLC (LLNL-CONF-821312). The views and opinions of the authors do not necessarily reflect those of the U.S. government or Lawrence Livermore National Security, LLC neither of whom nor any of their employees make any endorsements, express or implied warranties or representations or assume any legal liability or responsibility for the accuracy, completeness, or usefulness of the information contained herein.
Publisher Copyright:
Copyright © 2021 ISCA.
PY - 2021
Y1 - 2021
N2 - 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.
AB - 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.
KW - Deep audio priors
KW - Denoising
KW - Inpainting
KW - Source separation
KW - Unsupervised audio restoration
UR - http://www.scopus.com/inward/record.url?scp=85119185984&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85119185984&partnerID=8YFLogxK
U2 - 10.21437/Interspeech.2021-1890
DO - 10.21437/Interspeech.2021-1890
M3 - Conference contribution
AN - SCOPUS:85119185984
T3 - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
SP - 2858
EP - 2862
BT - 22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021
PB - International Speech Communication Association
T2 - 22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021
Y2 - 30 August 2021 through 3 September 2021
ER -