{"id":"https://openalex.org/W4384080217","doi":"https://doi.org/10.1109/access.2023.3294476","title":"DeepLabV3+ Vision Transformer for Visual Bird Sound Denoising","display_name":"DeepLabV3+ Vision Transformer for Visual Bird Sound Denoising","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4384080217","doi":"https://doi.org/10.1109/access.2023.3294476"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3294476","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3294476","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10179217.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10179217.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018132970","display_name":"Junhui Li","orcid":"https://orcid.org/0009-0000-9974-6141"},"institutions":[{"id":"https://openalex.org/I114117164","display_name":"University of Science and Technology Liaoning","ror":"https://ror.org/03grx7119","country_code":"CN","type":"education","lineage":["https://openalex.org/I114117164"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junhui Li","raw_affiliation_strings":["Department of Mathematics, School of Science, University of Science and Technology Liaoning (USTL), Liaoning, Anshan, China"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics, School of Science, University of Science and Technology Liaoning (USTL), Liaoning, Anshan, China","institution_ids":["https://openalex.org/I114117164"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100383535","display_name":"Pu Wang","orcid":"https://orcid.org/0009-0004-6980-0943"},"institutions":[{"id":"https://openalex.org/I114117164","display_name":"University of Science and Technology Liaoning","ror":"https://ror.org/03grx7119","country_code":"CN","type":"education","lineage":["https://openalex.org/I114117164"]},{"id":"https://openalex.org/I19772626","display_name":"Yeshiva University","ror":"https://ror.org/045x93337","country_code":"US","type":"education","lineage":["https://openalex.org/I19772626"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Pu Wang","raw_affiliation_strings":["Department of Artificial Intelligence and Computer Science, Yeshiva University, New York City, NY, USA","Department of Mathematics, School of Science, University of Science and Technology, Anshan, Liaoning, China"],"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence and Computer Science, Yeshiva University, New York City, NY, USA","institution_ids":["https://openalex.org/I19772626"]},{"raw_affiliation_string":"Department of Mathematics, School of Science, University of Science and Technology, Anshan, Liaoning, China","institution_ids":["https://openalex.org/I114117164"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079460371","display_name":"Youshan Zhang","orcid":"https://orcid.org/0000-0002-0074-0979"},"institutions":[{"id":"https://openalex.org/I114117164","display_name":"University of Science and Technology Liaoning","ror":"https://ror.org/03grx7119","country_code":"CN","type":"education","lineage":["https://openalex.org/I114117164"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youshan Zhang","raw_affiliation_strings":["Department of Mathematics, School of Science, University of Science and Technology Liaoning (USTL), Liaoning, Anshan, China"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics, School of Science, University of Science and Technology Liaoning (USTL), Liaoning, Anshan, China","institution_ids":["https://openalex.org/I114117164"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5018132970"],"corresponding_institution_ids":["https://openalex.org/I114117164"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.8258,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.86128144,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"11","issue":null,"first_page":"92540","last_page":"92549"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9908999800682068,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7706617116928101},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.6740613579750061},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6527000665664673},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.48777204751968384},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46112626791000366},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.44609126448631287},{"id":"https://openalex.org/keywords/video-denoising","display_name":"Video denoising","score":0.4394891560077667},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4369659721851349},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.42728936672210693},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.41277679800987244},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3844040334224701},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.1355254054069519},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10780006647109985}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7706617116928101},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.6740613579750061},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6527000665664673},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.48777204751968384},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46112626791000366},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.44609126448631287},{"id":"https://openalex.org/C30814859","wikidata":"https://www.wikidata.org/wiki/Q4119603","display_name":"Video denoising","level":5,"score":0.4394891560077667},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4369659721851349},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.42728936672210693},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.41277679800987244},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3844040334224701},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.1355254054069519},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10780006647109985},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C23431618","wikidata":"https://www.wikidata.org/wiki/Q1404672","display_name":"Multiview Video Coding","level":4,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2023.3294476","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3294476","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10179217.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:9a3f42eddf4146e4a557b99d168d77a9","is_oa":true,"landing_page_url":"https://doaj.org/article/9a3f42eddf4146e4a557b99d168d77a9","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 11, Pp 92540-92549 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3294476","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3294476","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10179217.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309686","display_name":"Yeshiva University","ror":"https://ror.org/045x93337"},{"id":"https://openalex.org/F4320310365","display_name":"Lehigh University","ror":"https://ror.org/012afjb06"},{"id":"https://openalex.org/F4320322872","display_name":"University of Science and Technology Liaoning","ror":"https://ror.org/03grx7119"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4384080217.pdf","grobid_xml":"https://content.openalex.org/works/W4384080217.grobid-xml"},"referenced_works_count":65,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2030212703","https://openalex.org/W2044893557","https://openalex.org/W2096779346","https://openalex.org/W2121973264","https://openalex.org/W2122979854","https://openalex.org/W2128402994","https://openalex.org/W2128653836","https://openalex.org/W2136738044","https://openalex.org/W2153894152","https://openalex.org/W2157562541","https://openalex.org/W2164007105","https://openalex.org/W2408744528","https://openalex.org/W2412782625","https://openalex.org/W2414102402","https://openalex.org/W2725252010","https://openalex.org/W2768531411","https://openalex.org/W2788241093","https://openalex.org/W2884585870","https://openalex.org/W2889442120","https://openalex.org/W2903516699","https://openalex.org/W2954198060","https://openalex.org/W2963453742","https://openalex.org/W2963881378","https://openalex.org/W2972443522","https://openalex.org/W2983446232","https://openalex.org/W2995679912","https://openalex.org/W2997775613","https://openalex.org/W3001152983","https://openalex.org/W3015654783","https://openalex.org/W3016447038","https://openalex.org/W3025800305","https://openalex.org/W3081108418","https://openalex.org/W3084306245","https://openalex.org/W3087443678","https://openalex.org/W3094040572","https://openalex.org/W3094550259","https://openalex.org/W3105563334","https://openalex.org/W3122264812","https://openalex.org/W3129077738","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3147966746","https://openalex.org/W3151130473","https://openalex.org/W3161950572","https://openalex.org/W3178192988","https://openalex.org/W3194513480","https://openalex.org/W3196050932","https://openalex.org/W3196974791","https://openalex.org/W3197734536","https://openalex.org/W3212933375","https://openalex.org/W4214893857","https://openalex.org/W4225288502","https://openalex.org/W4285258106","https://openalex.org/W4296425595","https://openalex.org/W4304809245","https://openalex.org/W4312726009","https://openalex.org/W4319300024","https://openalex.org/W6639824700","https://openalex.org/W6728226663","https://openalex.org/W6753100508","https://openalex.org/W6753412334","https://openalex.org/W6772996321","https://openalex.org/W6784310668","https://openalex.org/W6800062215"],"related_works":["https://openalex.org/W3119800349","https://openalex.org/W2092619848","https://openalex.org/W2483420468","https://openalex.org/W2111667101","https://openalex.org/W2012137123","https://openalex.org/W3200681261","https://openalex.org/W2340438796","https://openalex.org/W3105000828","https://openalex.org/W4312518509","https://openalex.org/W4307006490"],"abstract_inverted_index":{"Audio":[0],"denoising":[1,21,53,157],"is":[2,15,76,114],"a":[3,86,97,155],"task":[4],"to":[5,41,69,78,105,138],"improve":[6],"the":[7,20,28,42,108,117,143,151],"perceptual":[8],"quality":[9,29],"of":[10,22,30,45],"noisy":[11,23],"audio":[12,31,52,141],"signals.":[13],"There":[14],"still":[16,39],"residual":[17],"noise":[18,47,132],"after":[19],"signals,":[24],"which":[25,120,136],"will":[26],"affect":[27],"data.":[32],"Traditional":[33],"and":[34,62,100,123],"deep":[35,63],"learning-based":[36],"methods":[37],"are":[38],"limited":[40,77],"manual":[43],"addition":[44],"artificial":[46],"or":[48],"low-frequency":[49],"noise.":[50,109],"Recently,":[51],"has":[54,154],"been":[55,67],"transformed":[56],"into":[57],"an":[58],"image":[59,80],"segmentation":[60,81],"problem,":[61],"neural":[64],"networks":[65],"have":[66],"applied":[68],"solve":[70],"this":[71],"problem.":[72],"However,":[73],"its":[74],"performance":[75,158],"shallow":[79],"models.":[82],"This":[83],"paper":[84],"proposes":[85],"novel":[87],"vision":[88],"transformer":[89,99],"model":[90,113,128,153],"for":[91],"visual":[92],"bird":[93],"sound":[94],"denoising,":[95],"combining":[96],"pyramid":[98,118],"DeepLabV3+":[101],"network":[102],"(named":[103],"PtDeepLab)":[104],"filter":[106],"out":[107],"The":[110,126],"proposed":[111,152],"PtDeepLab":[112,127],"based":[115],"on":[116],"transformer,":[119],"generates":[121],"long-range":[122],"multi-scale":[124],"representations.":[125],"can":[129],"achieve":[130],"intuitive":[131],"reduction":[133],"in":[134],"audio,":[135],"helps":[137],"separate":[139],"clean":[140],"from":[142],"mixture":[144],"signal.":[145],"Extensive":[146],"experimental":[147],"results":[148],"showed":[149],"that":[150],"better":[156],"than":[159],"state-of-the-art":[160],"methods.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-02-28T09:26:25.869077","created_date":"2025-10-10T00:00:00"}