{"id":"https://openalex.org/W2994125460","doi":"https://doi.org/10.1109/access.2019.2957572","title":"Investigation of Different CNN-Based Models for Improved Bird Sound Classification","display_name":"Investigation of Different CNN-Based Models for Improved Bird Sound Classification","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2994125460","doi":"https://doi.org/10.1109/access.2019.2957572","mag":"2994125460"},"language":"en","primary_location":{"id":"doi:10.1109/access.2019.2957572","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2957572","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08922774.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/ielx7/6287639/8600701/08922774.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103226632","display_name":"Jie Xie","orcid":"https://orcid.org/0000-0002-7707-9963"},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Xie","raw_affiliation_strings":["Jiangsu Key Laboratory of Advanced Food Manufacturing Equipment and Technology, Jiangnan University, Wuxi, China","Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Jiangnan University, Wuxi, China","School of Internet of Things Engineering, Jiangnan University, Wuxi, China"],"raw_orcid":"https://orcid.org/0000-0002-7707-9963","affiliations":[{"raw_affiliation_string":"Jiangsu Key Laboratory of Advanced Food Manufacturing Equipment and Technology, Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]},{"raw_affiliation_string":"Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]},{"raw_affiliation_string":"School of Internet of Things Engineering, Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047911644","display_name":"Kai Hu","orcid":"https://orcid.org/0000-0002-3521-4178"},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Hu","raw_affiliation_strings":["Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Jiangnan University, Wuxi, China","School of Internet of Things Engineering, Jiangnan University, Wuxi, China"],"raw_orcid":"https://orcid.org/0000-0002-3521-4178","affiliations":[{"raw_affiliation_string":"Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]},{"raw_affiliation_string":"School of Internet of Things Engineering, Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049415642","display_name":"Mingying Zhu","orcid":"https://orcid.org/0000-0002-3423-074X"},"institutions":[{"id":"https://openalex.org/I153718931","display_name":"University of Ottawa","ror":"https://ror.org/03c4mmv16","country_code":"CA","type":"education","lineage":["https://openalex.org/I153718931"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mingying Zhu","raw_affiliation_strings":["Department of Economics, University of Ottawa, Ottawa, Canada"],"raw_orcid":"https://orcid.org/0000-0002-3423-074X","affiliations":[{"raw_affiliation_string":"Department of Economics, University of Ottawa, Ottawa, Canada","institution_ids":["https://openalex.org/I153718931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054542502","display_name":"Jinghu Yu","orcid":"https://orcid.org/0000-0002-3763-2509"},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinghu Yu","raw_affiliation_strings":["Jiangsu Key Laboratory of Advanced Food Manufacturing Equipment and Technology, Jiangnan University, Wuxi, China","School of Mechanical Engineering, Jiangnan University, Wuxi, China"],"raw_orcid":"https://orcid.org/0000-0002-3763-2509","affiliations":[{"raw_affiliation_string":"Jiangsu Key Laboratory of Advanced Food Manufacturing Equipment and Technology, Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]},{"raw_affiliation_string":"School of Mechanical Engineering, Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011899228","display_name":"Qibing Zhu","orcid":"https://orcid.org/0000-0001-5685-5786"},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qibing Zhu","raw_affiliation_strings":["Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Jiangnan University, Wuxi, China","School of Internet of Things Engineering, Jiangnan University, Wuxi, China"],"raw_orcid":"https://orcid.org/0000-0001-5685-5786","affiliations":[{"raw_affiliation_string":"Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]},{"raw_affiliation_string":"School of Internet of Things Engineering, Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":8.9467,"has_fulltext":true,"cited_by_count":143,"citation_normalized_percentile":{"value":0.98780488,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"7","issue":null,"first_page":"175353","last_page":"175361"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9998000264167786,"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9940999746322632,"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/T10659","display_name":"Marine animal studies overview","score":0.9836000204086304,"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/spectrogram","display_name":"Spectrogram","score":0.9311599731445312},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.7727223038673401},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7049143314361572},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6914055943489075},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5566427111625671},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5051549077033997},{"id":"https://openalex.org/keywords/bioacoustics","display_name":"Bioacoustics","score":0.502737283706665},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.43147003650665283},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.41028040647506714},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3828095495700836},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3389960825443268},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.12396278977394104},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10961025953292847},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08209797739982605}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9311599731445312},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7727223038673401},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7049143314361572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6914055943489075},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5566427111625671},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5051549077033997},{"id":"https://openalex.org/C34951282","wikidata":"https://www.wikidata.org/wiki/Q864191","display_name":"Bioacoustics","level":2,"score":0.502737283706665},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.43147003650665283},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.41028040647506714},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3828095495700836},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3389960825443268},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.12396278977394104},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10961025953292847},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08209797739982605},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2019.2957572","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2957572","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08922774.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:4d8696d0a0554a81a79c5c410f071547","is_oa":true,"landing_page_url":"https://doaj.org/article/4d8696d0a0554a81a79c5c410f071547","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 7, Pp 175353-175361 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2019.2957572","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2957572","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08922774.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15","score":0.699999988079071}],"awards":[{"id":"https://openalex.org/G1474490597","display_name":null,"funder_award_id":"111 Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1781994891","display_name":null,"funder_award_id":"JUSRP11924","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G1910376577","display_name":null,"funder_award_id":"61902154","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6288555622","display_name":null,"funder_award_id":"BK2019043526","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G6409886023","display_name":null,"funder_award_id":"2019-06","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321605","display_name":"Government of Jiangsu Province","ror":"https://ror.org/004svx814"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327912","display_name":"Higher Education Discipline Innovation Project","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2994125460.pdf","grobid_xml":"https://content.openalex.org/works/W2994125460.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1066076866","https://openalex.org/W1686810756","https://openalex.org/W1964972829","https://openalex.org/W1986582462","https://openalex.org/W1989133314","https://openalex.org/W2058412220","https://openalex.org/W2060588724","https://openalex.org/W2067179326","https://openalex.org/W2069943693","https://openalex.org/W2127135195","https://openalex.org/W2256010752","https://openalex.org/W2300976478","https://openalex.org/W2552032035","https://openalex.org/W2581706890","https://openalex.org/W2680737492","https://openalex.org/W2731031236","https://openalex.org/W2774728799","https://openalex.org/W2896911561","https://openalex.org/W2900263579","https://openalex.org/W2921717508","https://openalex.org/W2937047963","https://openalex.org/W2938726981","https://openalex.org/W2942893872","https://openalex.org/W2944806726","https://openalex.org/W2945370849","https://openalex.org/W2947483988","https://openalex.org/W2962711843","https://openalex.org/W2963162200","https://openalex.org/W2964355201","https://openalex.org/W3102534672","https://openalex.org/W6637373629","https://openalex.org/W6761692111"],"related_works":["https://openalex.org/W3170167497","https://openalex.org/W2089315226","https://openalex.org/W4252208810","https://openalex.org/W1975881626","https://openalex.org/W2942893872","https://openalex.org/W2006097237","https://openalex.org/W4386758235","https://openalex.org/W2470608223","https://openalex.org/W2249987663","https://openalex.org/W2065606036"],"abstract_inverted_index":{"Automatic":[0],"bird":[1,62,99,134,141],"sound":[2,63],"classification":[3,40,53,64,154],"plays":[4],"an":[5],"important":[6],"role":[7],"in":[8,16],"monitoring":[9,30],"and":[10,20,44,55,115,167],"further":[11,60],"protecting":[12],"biodiversity.":[13],"Recent":[14],"advances":[15],"acoustic":[17,107],"sensor":[18],"networks":[19],"deep":[21,37,73,84,126,147],"learning":[22,38,74,85,127,148],"techniques":[23],"provide":[24],"a":[25,124,162,168],"novel":[26],"way":[27],"for":[28,42,87],"continuously":[29],"birds.":[31,46],"Previous":[32],"studies":[33],"have":[34],"proposed":[35],"various":[36],"based":[39,113,117],"frameworks":[41],"recognizing":[43],"classifying":[45,139],"In":[47,119],"this":[48],"study,":[49],"we":[50,67],"compare":[51],"different":[52,77,83,106,122,125],"models":[54,149],"selectively":[56],"fuse":[57],"them":[58],"to":[59,104,121,132],"improve":[61],"performance.":[65,155],"Specifically,":[66],"not":[68],"only":[69],"use":[70],"the":[71,89,153],"same":[72],"architecture":[75],"with":[76],"inputs":[78],"but":[79],"also":[80],"employ":[81],"two":[82],"architectures":[86],"constructing":[88],"fused":[90,158],"model.":[91],"Three":[92],"types":[93],"of":[94,98,109,165,171],"time-frequency":[95],"representations":[96],"(TFRs)":[97],"sounds":[100],"are":[101],"investigated":[102],"aiming":[103],"characterize":[105],"components":[108],"birds:":[110],"Mel-spectrogram,":[111],"harmonic-component":[112],"spectrogram,":[114],"percussive-component":[116],"spectrogram.":[118],"addition":[120],"TFRs,":[123],"architecture,":[128],"SubSpectralNet,":[129],"is":[130],"employed":[131],"classify":[133],"sounds.":[135],"Experimental":[136],"results":[137],"on":[138],"43":[140],"species":[142],"show":[143],"that":[144],"fusing":[145],"selected":[146],"can":[150,160],"effectively":[151],"increase":[152],"Our":[156],"best":[157],"model":[159],"achieve":[161],"balanced":[163],"accuracy":[164],"86.31%":[166],"weighted":[169],"F1-score":[170],"93.31%.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":30},{"year":2024,"cited_by_count":25},{"year":2023,"cited_by_count":37},{"year":2022,"cited_by_count":23},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":5}],"updated_date":"2026-06-20T22:02:38.213706","created_date":"2025-10-10T00:00:00"}
