{"id":"https://openalex.org/W4407899867","doi":"https://doi.org/10.1109/lsp.2025.3545005","title":"Segment Anything for Visual Bird Sound Denoising","display_name":"Segment Anything for Visual Bird Sound Denoising","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4407899867","doi":"https://doi.org/10.1109/lsp.2025.3545005"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2025.3545005","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3545005","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"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 Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Chenxi Zhou","orcid":"https://orcid.org/0009-0006-1295-7215"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenxi Zhou","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0006-1295-7215","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061252955","display_name":"Tianjiao Wan","orcid":"https://orcid.org/0000-0002-2423-4982"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianjiao Wan","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013340793","display_name":"Kele Xu","orcid":"https://orcid.org/0000-0001-5997-5169"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kele Xu","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-5997-5169","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058476148","display_name":"Peng Qiao","orcid":"https://orcid.org/0000-0001-6752-7892"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Qiao","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-6752-7892","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051680867","display_name":"Yong Dou","orcid":"https://orcid.org/0000-0002-1256-8934"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Dou","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-1256-8934","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.9378,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.69326146,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"32","issue":null,"first_page":"1076","last_page":"1080"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.996999979019165,"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"}},"topics":[{"id":"https://openalex.org/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.996999979019165,"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"}},{"id":"https://openalex.org/T10895","display_name":"Species Distribution and Climate Change","score":0.978600025177002,"subfield":{"id":"https://openalex.org/subfields/2302","display_name":"Ecological Modeling"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10659","display_name":"Marine animal studies overview","score":0.9312000274658203,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.669889509677887},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5949236154556274},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4861166477203369},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.48401376605033875},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.46518081426620483},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.41460856795310974},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3865951895713806},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2988103926181793},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13236480951309204}],"concepts":[{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.669889509677887},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5949236154556274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4861166477203369},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.48401376605033875},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.46518081426620483},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.41460856795310974},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3865951895713806},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2988103926181793},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13236480951309204},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2025.3545005","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3545005","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"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 Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","score":0.49000000953674316,"id":"https://metadata.un.org/sdg/13"}],"awards":[{"id":"https://openalex.org/G3961492198","display_name":null,"funder_award_id":"2023ZD0121101","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"}],"funders":[{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2078528584","https://openalex.org/W2128653836","https://openalex.org/W2145991046","https://openalex.org/W2153894152","https://openalex.org/W2405774341","https://openalex.org/W2414102402","https://openalex.org/W2565639579","https://openalex.org/W2884436604","https://openalex.org/W2923260971","https://openalex.org/W2943554574","https://openalex.org/W2944046714","https://openalex.org/W2962914239","https://openalex.org/W2963037989","https://openalex.org/W2963341071","https://openalex.org/W2963453742","https://openalex.org/W2963881378","https://openalex.org/W2972466499","https://openalex.org/W2991361823","https://openalex.org/W3015199127","https://openalex.org/W3025800305","https://openalex.org/W3036682224","https://openalex.org/W3109998321","https://openalex.org/W3196342474","https://openalex.org/W3196974791","https://openalex.org/W3206996142","https://openalex.org/W3212933375","https://openalex.org/W3214429548","https://openalex.org/W4214893857","https://openalex.org/W4312815172","https://openalex.org/W4319300024","https://openalex.org/W4384080217","https://openalex.org/W4385822269","https://openalex.org/W4388293246","https://openalex.org/W4390874575","https://openalex.org/W4391109864","https://openalex.org/W4391743083","https://openalex.org/W4393150367","https://openalex.org/W4393156082","https://openalex.org/W4402112494","https://openalex.org/W4405934446","https://openalex.org/W6632507843","https://openalex.org/W6784333009","https://openalex.org/W6852880106"],"related_works":["https://openalex.org/W2909726438","https://openalex.org/W2067046791","https://openalex.org/W2909888262","https://openalex.org/W2025747832","https://openalex.org/W3020957235","https://openalex.org/W2056769785","https://openalex.org/W611303608","https://openalex.org/W3034789145","https://openalex.org/W4367628250","https://openalex.org/W4388819787"],"abstract_inverted_index":{"Current":[0],"audio":[1,61,86,168],"denoising":[2,62,87,169],"methods":[3,50],"perform":[4],"well":[5],"with":[6,11,42],"synthetic":[7],"noise":[8],"but":[9],"struggle":[10],"complex":[12],"natural":[13,21],"noise,":[14],"especially":[15],"for":[16,72,175],"bird":[17,35,46,81,118,180],"sounds,":[18,47],"which":[19,164],"contain":[20],"environmental":[22],"sounds":[23,119],"such":[24],"as":[25,88],"wind":[26],"and":[27,44,98,102,141,178],"rain,":[28],"making":[29],"it":[30],"challenging":[31],"to":[32,105,110,149],"extract":[33],"clean":[34,117],"sounds.":[36],"This":[37],"issue":[38],"becomes":[39],"more":[40],"pronounced":[41],"short":[43],"faint":[45],"where":[48],"existing":[49],"are":[51,121],"less":[52],"effective.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57,99],"introduceBudSAM,":[58],"a":[59,89,136,142,172],"novel":[60],"model":[63],"that":[64,120],"incorporates":[65,100],"theSegment":[66],"Anything":[67],"Model":[68],"(SAM),":[69],"originally":[70],"designed":[71],"image":[73],"segmentation":[74,90,96],"task,":[75,91,170],"into":[76],"the":[77,107,116,132,153,157,161],"field":[78],"of":[79,156],"visual":[80],"sound":[82,181],"denoising.":[83],"By":[84],"treating":[85],"BudSAM":[92,159],"utilizes":[93],"SAM's":[94],"powerful":[95],"capabilities":[97],"BCE":[101],"Dice":[103],"losses":[104],"enhance":[106],"model's":[108],"ability":[109],"segment":[111],"weak":[112],"signals,":[113],"effectively":[114],"isolating":[115],"often":[122],"masked":[123],"by":[124],"background":[125],"noise.":[126],"Our":[127],"method":[128],"is":[129],"evaluated":[130],"on":[131],"BirdSoundsDenoising":[133],"dataset,":[134],"achieving":[135],"4.0%":[137],"improvement":[138],"in":[139,146,167],"IoU":[140],"0.77":[143],"dB":[144],"increase":[145],"SDR":[147],"compared":[148],"state-of-the-art":[150],"methods.":[151],"To":[152],"best":[154],"knowledge":[155],"authors,":[158],"marks":[160],"first":[162],"attempt":[163],"employs":[165],"SAM":[166],"offering":[171],"promising":[173],"direction":[174],"future":[176],"research":[177],"real-world":[179],"processing":[182],"tasks.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}
