A transfer deep residual shrinkage network for bird sound recognition

Bird sound recognition has important applications in bird monitoring and ecological protection. However, in complicated environments, noise and insufficient sample data are the major factors affecting recognition accuracy. We proposed a bird sound recognition method based on a developed transfer dee...

Full description

Saved in:
Bibliographic Details
Published in:Electronic research archive Vol. 33; no. 7; pp. 4135 - 4150
Main Authors: Chen, Xiao, Zeng, Zhaoyou, Xu, Tong
Format: Journal Article
Language:English
Published: AIMS Press 01.07.2025
Subjects:
audio signal processing
bioacoustics
bird sound recognition
deep learning
deep residual shrinkage network
ecological monitoring
machine learning
transfer learning
ISSN:2688-1594, 2688-1594
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Bird sound recognition has important applications in bird monitoring and ecological protection. However, in complicated environments, noise and insufficient sample data are the major factors affecting recognition accuracy. We proposed a bird sound recognition method based on a developed transfer deep residual shrinkage network. First, a deep residual shrinkage network with noise resistance was constructed based on the structural characteristics of the residual shrinkage module, multi-scale operations, and the characteristics of bird sound Mel spectrograms. Then, the deep residual shrinkage network was pre-trained using a bird sound dataset, applying an unfreezing fine-tuning strategy, to mitigate the impact of insufficient training data. A transfer learning alleviated the problem of data scarcity by utilizing pre-trained models, while the deep residual shrinkage network enhanced the performance of the model in a noisy environment by optimizing the network structure. Experimental results showed that this method achieves high recognition accuracy under noise and small data sets. It has advantages over the compared methods and is suitable for ecological monitoring fields such as bird population monitoring. The method has good application prospects.
AbstractList Bird sound recognition has important applications in bird monitoring and ecological protection. However, in complicated environments, noise and insufficient sample data are the major factors affecting recognition accuracy. We proposed a bird sound recognition method based on a developed transfer deep residual shrinkage network. First, a deep residual shrinkage network with noise resistance was constructed based on the structural characteristics of the residual shrinkage module, multi-scale operations, and the characteristics of bird sound Mel spectrograms. Then, the deep residual shrinkage network was pre-trained using a bird sound dataset, applying an unfreezing fine-tuning strategy, to mitigate the impact of insufficient training data. A transfer learning alleviated the problem of data scarcity by utilizing pre-trained models, while the deep residual shrinkage network enhanced the performance of the model in a noisy environment by optimizing the network structure. Experimental results showed that this method achieves high recognition accuracy under noise and small data sets. It has advantages over the compared methods and is suitable for ecological monitoring fields such as bird population monitoring. The method has good application prospects.
Author Xu, Tong
Chen, Xiao
Zeng, Zhaoyou
Author_xml – sequence: 1
  givenname: Xiao
  surname: Chen
  fullname: Chen, Xiao
– sequence: 2
  givenname: Zhaoyou
  surname: Zeng
  fullname: Zeng, Zhaoyou
– sequence: 3
  givenname: Tong
  surname: Xu
  fullname: Xu, Tong
BookMark eNpNkE1LAzEURYNUsNau_APZy9R8N1mWUrVQcKPrIZO81LQ1KckU8d87WhFX7_K4HC7nGo1SToDQLSUzbri4h2JnjDBJtbxAY6a0bqg0YvQvX6FprTtCCNOUEKHGaLXAfbGpBijYAxxxgRr9yR5wfSsx7e0WcIL-I5c9DrngLhaPaz4lPzRd3qbYx5xu0GWwhwrT3ztBrw-rl-VTs3l-XC8Xm8Zyo_pGzQVQSkSgMhihg50ra70nBkzwZG4J1SCNp55JQxxTngvGQRHGO9kNe_kErc9cn-2uPZb4bstnm21sfx65bFtb-ugO0ArtvVVdZ-RcC9dR6xwBEVQgIWin-cC6O7NcybUWCH88Stpvoe0gtP0Vyr8AoSFqiw
Cites_doi 10.3934/mbe.2023860
10.18280/ts.390119
10.3969/j.issn.1000-386x.2014.01.040
10.1109/JSEN.2020.3030634
10.1117/1.JEI.31.4.043006
10.1109/TFUZZ.2017.2690222
10.1038/s41598-022-12121-8
10.1109/AISP48273.2020.9073584
10.1038/s41598-025-93758-z
10.7498/aps.63.184301
10.3934/era.2023011
10.1016/j.foreco.2007.01.080
10.1080/09349847.2015.1023913
10.3934/mbe.2023275
10.1002/cpe.7048
10.1117/1.JRS.16.026510
10.1145/3065386
10.7498/aps.67.20180561
10.3934/era.2025009
10.1109/ACCESS.2022.3142510
ContentType Journal Article
CorporateAuthor Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology, Nanjing University of Information Science and Technology, Nanjing 210044, China
School of Electronic and Information Engineering, Nanjing University of Information Science and Technology, Nanjing 210044, China
CorporateAuthor_xml – name: Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology, Nanjing University of Information Science and Technology, Nanjing 210044, China
– name: School of Electronic and Information Engineering, Nanjing University of Information Science and Technology, Nanjing 210044, China
DBID AAYXX
CITATION
DOA
DOI 10.3934/era.2025185
DatabaseName CrossRef
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
DatabaseTitleList
Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
Discipline Mathematics
EISSN 2688-1594
EndPage 4150
ExternalDocumentID oai_doaj_org_article_48dda6bb95784cb1acc0e4f6f0ff8c83
10_3934_era_2025185
GroupedDBID AAYXX
ABDBF
ALMA_UNASSIGNED_HOLDINGS
AMVHM
CITATION
GROUPED_DOAJ
IAO
ICD
ITC
RAN
TUS
M~E
ID FETCH-LOGICAL-a396t-674e1104f15f948fa76aadd09e9fd07a018e59d1d2590c26d3423e6023b5b0043
IEDL.DBID DOA
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001525496400003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2688-1594
IngestDate Tue Oct 14 19:09:27 EDT 2025
Sat Nov 29 07:44:54 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 7
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a396t-674e1104f15f948fa76aadd09e9fd07a018e59d1d2590c26d3423e6023b5b0043
OpenAccessLink https://doaj.org/article/48dda6bb95784cb1acc0e4f6f0ff8c83
PageCount 16
ParticipantIDs doaj_primary_oai_doaj_org_article_48dda6bb95784cb1acc0e4f6f0ff8c83
crossref_primary_10_3934_era_2025185
PublicationCentury 2000
PublicationDate 20250701
PublicationDateYYYYMMDD 2025-07-01
PublicationDate_xml – month: 07
  year: 2025
  text: 20250701
  day: 01
PublicationDecade 2020
PublicationTitle Electronic research archive
PublicationYear 2025
Publisher AIMS Press
Publisher_xml – name: AIMS Press
References key-10.3934/era.2025185-21
key-10.3934/era.2025185-22
key-10.3934/era.2025185-23
key-10.3934/era.2025185-24
key-10.3934/era.2025185-25
key-10.3934/era.2025185-26
key-10.3934/era.2025185-27
key-10.3934/era.2025185-10
key-10.3934/era.2025185-11
key-10.3934/era.2025185-12
key-10.3934/era.2025185-13
key-10.3934/era.2025185-14
key-10.3934/era.2025185-15
key-10.3934/era.2025185-16
key-10.3934/era.2025185-17
key-10.3934/era.2025185-18
key-10.3934/era.2025185-19
key-10.3934/era.2025185-9
key-10.3934/era.2025185-4
key-10.3934/era.2025185-3
key-10.3934/era.2025185-2
key-10.3934/era.2025185-1
key-10.3934/era.2025185-8
key-10.3934/era.2025185-7
key-10.3934/era.2025185-6
key-10.3934/era.2025185-5
key-10.3934/era.2025185-20
References_xml – ident: key-10.3934/era.2025185-1
  doi: 10.3934/mbe.2023860
– ident: key-10.3934/era.2025185-9
  doi: 10.18280/ts.390119
– ident: key-10.3934/era.2025185-10
  doi: 10.3969/j.issn.1000-386x.2014.01.040
– ident: key-10.3934/era.2025185-27
  doi: 10.1109/JSEN.2020.3030634
– ident: key-10.3934/era.2025185-3
  doi: 10.1117/1.JEI.31.4.043006
– ident: key-10.3934/era.2025185-22
  doi: 10.1109/TFUZZ.2017.2690222
– ident: key-10.3934/era.2025185-20
– ident: key-10.3934/era.2025185-24
  doi: 10.1038/s41598-022-12121-8
– ident: key-10.3934/era.2025185-13
– ident: key-10.3934/era.2025185-25
  doi: 10.1109/AISP48273.2020.9073584
– ident: key-10.3934/era.2025185-15
– ident: key-10.3934/era.2025185-7
– ident: key-10.3934/era.2025185-26
  doi: 10.1038/s41598-025-93758-z
– ident: key-10.3934/era.2025185-16
  doi: 10.7498/aps.63.184301
– ident: key-10.3934/era.2025185-23
  doi: 10.3934/era.2023011
– ident: key-10.3934/era.2025185-2
  doi: 10.1016/j.foreco.2007.01.080
– ident: key-10.3934/era.2025185-17
  doi: 10.1080/09349847.2015.1023913
– ident: key-10.3934/era.2025185-21
– ident: key-10.3934/era.2025185-12
  doi: 10.3934/mbe.2023275
– ident: key-10.3934/era.2025185-19
  doi: 10.1002/cpe.7048
– ident: key-10.3934/era.2025185-4
  doi: 10.1117/1.JRS.16.026510
– ident: key-10.3934/era.2025185-5
  doi: 10.1145/3065386
– ident: key-10.3934/era.2025185-18
  doi: 10.7498/aps.67.20180561
– ident: key-10.3934/era.2025185-11
  doi: 10.3934/era.2025009
– ident: key-10.3934/era.2025185-8
– ident: key-10.3934/era.2025185-6
  doi: 10.1109/ACCESS.2022.3142510
– ident: key-10.3934/era.2025185-14
SSID ssj0002810046
Score 2.296014
Snippet Bird sound recognition has important applications in bird monitoring and ecological protection. However, in complicated environments, noise and insufficient...
SourceID doaj
crossref
SourceType Open Website
Index Database
StartPage 4135
SubjectTerms audio signal processing
bioacoustics
bird sound recognition
deep learning
deep residual shrinkage network
ecological monitoring
machine learning
transfer learning
Title A transfer deep residual shrinkage network for bird sound recognition
URI https://doaj.org/article/48dda6bb95784cb1acc0e4f6f0ff8c83
Volume 33
WOSCitedRecordID wos001525496400003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2688-1594
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002810046
  issn: 2688-1594
  databaseCode: DOA
  dateStart: 20220101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV27TsMwFLVQxQAD4inKSx66RnUSP8eCWrFQMYDULfLjWpQhrdLA92M7ocrGwhpZkXWu7XOPdX0uQpOS-cJQF7SJlSSjhrhMl7rIEllqRqEULjWbEMulXK3U66DVV6wJ6-yBO-CmVDqnuTEqLC1qTa6tJUA998R7aWXy-SRCDcTUZ7oyik5ovHuQV6qSTqGJLkOBzWPX5AEFDZz6E6UsTtFJnwviWTeHM3QA9Tk6ftkbqe4u0HyG25RaQoMdwBYHdZyeT-HdRxNkZDgNcN1VcuOQfmKzbhzexVZJeF8atKkv0fti_vb0nPWdDwJQircZFxQCL1OfM6-o9FpwHQ4iokB5R4QmuQSmXO6CeCG24C76-AEP_GtY3IflFRrVmxquEWZMWCi4iahRQ5VkkgDkHiwrqRfFGE1-wai2ncFFFYRBxKwKmFU9ZmP0GIHaD4mu1OlDiFXVx6r6K1Y3__GTW3QU59SVzN6hUdt8wT06tN_tetc8pGXwAyiCucU
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+transfer+deep+residual+shrinkage+network+for+bird+sound+recognition&rft.jtitle=Electronic+research+archive&rft.au=Chen%2C+Xiao&rft.au=Zeng%2C+Zhaoyou&rft.au=Xu%2C+Tong&rft.date=2025-07-01&rft.issn=2688-1594&rft.eissn=2688-1594&rft.volume=33&rft.issue=7&rft.spage=4135&rft.epage=4150&rft_id=info:doi/10.3934%2Fera.2025185&rft.externalDBID=n%2Fa&rft.externalDocID=10_3934_era_2025185
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2688-1594&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2688-1594&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2688-1594&client=summon