A Survey of Audio Enhancement Algorithms for Music, Speech, Bioacoustics, Biomedical, Industrial, and Environmental Sounds by Image U-Net

<p dir="ltr">The recent surge in the use of Deep Neural Networks (DNNs) has also made its mark in the field of Audio Enhancement (AE), providing much better quality than the classical methods. Although, there are dedicated audio processing DNNs, yet, many recent models of AE have uti...

Full description

Saved in:
Bibliographic Details
Main Author: Sania Gul (18272227) (author)
Other Authors: Muhammad Salman Khan (7202543) (author)
Published: 2023
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513545574547456
author Sania Gul (18272227)
author2 Muhammad Salman Khan (7202543)
author2_role author
author_facet Sania Gul (18272227)
Muhammad Salman Khan (7202543)
author_role author
dc.creator.none.fl_str_mv Sania Gul (18272227)
Muhammad Salman Khan (7202543)
dc.date.none.fl_str_mv 2023-12-27T15:00:00Z
dc.identifier.none.fl_str_mv 10.1109/access.2023.3344813
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/A_Survey_of_Audio_Enhancement_Algorithms_for_Music_Speech_Bioacoustics_Biomedical_Industrial_and_Environmental_Sounds_by_Image_U-Net/29445581
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Information and computing sciences
Artificial intelligence
Machine learning
CNNs
image processing deep neural networks
pre-trained networks
spectrogram
U-Net
Convolutional neural networks
Time-domain analysis
Speech enhancement
Spectrogram
Recurrent neural networks
Music
Image processing
Artificial neural networks
dc.title.none.fl_str_mv A Survey of Audio Enhancement Algorithms for Music, Speech, Bioacoustics, Biomedical, Industrial, and Environmental Sounds by Image U-Net
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">The recent surge in the use of Deep Neural Networks (DNNs) has also made its mark in the field of Audio Enhancement (AE), providing much better quality than the classical methods. Although, there are dedicated audio processing DNNs, yet, many recent models of AE have utilized U-Net: a DNN based on Convolutional Neural Network (CNN), fundamentally developed for image segmentation. It is found that the useful features hidden in the time domain are highlighted when the audio signal is converted to a spectrogram, which can be treated as an image. In this article, we will review the recent work, utilizing U-Nets for different AE applications. Different than other published reviews, this review focuses entirely on AE techniques based on image U-Nets. We will discuss the need for AE, U-Net comparison to other DNNs, the benefits of converting the audio to 2D, input representations that are useful for different AE applications, the architecture of vanilla U-Net and the pre-trained models, variations in vanilla architecture incorporated in different E models, and the state-of-the-art AE algorithms based on U-Net in various applications. Apart from speech and music, this article discusses a wide range of audio signals e.g. environmental, biomedical, bioacoustics, and industrial sounds, not covered collectively in a single article in previously published studies. The article ends with the discussion of colored spectrograms in future AE applications.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/deed.en" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2023.3344813" target="_blank">https://dx.doi.org/10.1109/access.2023.3344813</a></p>
eu_rights_str_mv openAccess
id Manara2_ac8bd2f35c16e243adf065dc34473389
identifier_str_mv 10.1109/access.2023.3344813
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/29445581
publishDate 2023
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling A Survey of Audio Enhancement Algorithms for Music, Speech, Bioacoustics, Biomedical, Industrial, and Environmental Sounds by Image U-NetSania Gul (18272227)Muhammad Salman Khan (7202543)Information and computing sciencesArtificial intelligenceMachine learningCNNsimage processing deep neural networkspre-trained networksspectrogramU-NetConvolutional neural networksTime-domain analysisSpeech enhancementSpectrogramRecurrent neural networksMusicImage processingArtificial neural networks<p dir="ltr">The recent surge in the use of Deep Neural Networks (DNNs) has also made its mark in the field of Audio Enhancement (AE), providing much better quality than the classical methods. Although, there are dedicated audio processing DNNs, yet, many recent models of AE have utilized U-Net: a DNN based on Convolutional Neural Network (CNN), fundamentally developed for image segmentation. It is found that the useful features hidden in the time domain are highlighted when the audio signal is converted to a spectrogram, which can be treated as an image. In this article, we will review the recent work, utilizing U-Nets for different AE applications. Different than other published reviews, this review focuses entirely on AE techniques based on image U-Nets. We will discuss the need for AE, U-Net comparison to other DNNs, the benefits of converting the audio to 2D, input representations that are useful for different AE applications, the architecture of vanilla U-Net and the pre-trained models, variations in vanilla architecture incorporated in different E models, and the state-of-the-art AE algorithms based on U-Net in various applications. Apart from speech and music, this article discusses a wide range of audio signals e.g. environmental, biomedical, bioacoustics, and industrial sounds, not covered collectively in a single article in previously published studies. The article ends with the discussion of colored spectrograms in future AE applications.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/deed.en" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2023.3344813" target="_blank">https://dx.doi.org/10.1109/access.2023.3344813</a></p>2023-12-27T15:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/access.2023.3344813https://figshare.com/articles/journal_contribution/A_Survey_of_Audio_Enhancement_Algorithms_for_Music_Speech_Bioacoustics_Biomedical_Industrial_and_Environmental_Sounds_by_Image_U-Net/29445581CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/294455812023-12-27T15:00:00Z
spellingShingle A Survey of Audio Enhancement Algorithms for Music, Speech, Bioacoustics, Biomedical, Industrial, and Environmental Sounds by Image U-Net
Sania Gul (18272227)
Information and computing sciences
Artificial intelligence
Machine learning
CNNs
image processing deep neural networks
pre-trained networks
spectrogram
U-Net
Convolutional neural networks
Time-domain analysis
Speech enhancement
Spectrogram
Recurrent neural networks
Music
Image processing
Artificial neural networks
status_str publishedVersion
title A Survey of Audio Enhancement Algorithms for Music, Speech, Bioacoustics, Biomedical, Industrial, and Environmental Sounds by Image U-Net
title_full A Survey of Audio Enhancement Algorithms for Music, Speech, Bioacoustics, Biomedical, Industrial, and Environmental Sounds by Image U-Net
title_fullStr A Survey of Audio Enhancement Algorithms for Music, Speech, Bioacoustics, Biomedical, Industrial, and Environmental Sounds by Image U-Net
title_full_unstemmed A Survey of Audio Enhancement Algorithms for Music, Speech, Bioacoustics, Biomedical, Industrial, and Environmental Sounds by Image U-Net
title_short A Survey of Audio Enhancement Algorithms for Music, Speech, Bioacoustics, Biomedical, Industrial, and Environmental Sounds by Image U-Net
title_sort A Survey of Audio Enhancement Algorithms for Music, Speech, Bioacoustics, Biomedical, Industrial, and Environmental Sounds by Image U-Net
topic Information and computing sciences
Artificial intelligence
Machine learning
CNNs
image processing deep neural networks
pre-trained networks
spectrogram
U-Net
Convolutional neural networks
Time-domain analysis
Speech enhancement
Spectrogram
Recurrent neural networks
Music
Image processing
Artificial neural networks