{"id":"https://openalex.org/W3036682224","doi":"https://doi.org/10.1109/icccs49078.2020.9118426","title":"A Generalized Denoising Method with an Optimized Loss Function for Automated Bird Sound Recognition","display_name":"A Generalized Denoising Method with an Optimized Loss Function for Automated Bird Sound Recognition","publication_year":2020,"publication_date":"2020-05-01","ids":{"openalex":"https://openalex.org/W3036682224","doi":"https://doi.org/10.1109/icccs49078.2020.9118426","mag":"3036682224"},"language":"en","primary_location":{"id":"doi:10.1109/icccs49078.2020.9118426","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccs49078.2020.9118426","pdf_url":null,"source":{"id":"https://openalex.org/S4306498617","display_name":"2020 5th International Conference on Computer and Communication Systems (ICCCS)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 5th International Conference on Computer and Communication Systems (ICCCS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10072/399268","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004719790","display_name":"Huangqiang Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I31683504","display_name":"Beijing Forestry University","ror":"https://ror.org/04xv2pc41","country_code":"CN","type":"education","lineage":["https://openalex.org/I1327237609","https://openalex.org/I31683504","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Huangqiang Fang","raw_affiliation_strings":["School of Information Science and Technology, Beijing Forestry University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Beijing Forestry University, Beijing, China","institution_ids":["https://openalex.org/I31683504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100720970","display_name":"Yulin He","orcid":"https://orcid.org/0000-0003-1380-1088"},"institutions":[{"id":"https://openalex.org/I31683504","display_name":"Beijing Forestry University","ror":"https://ror.org/04xv2pc41","country_code":"CN","type":"education","lineage":["https://openalex.org/I1327237609","https://openalex.org/I31683504","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yulin He","raw_affiliation_strings":["School of Information Science and Technology, Beijing Forestry University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Beijing Forestry University, Beijing, China","institution_ids":["https://openalex.org/I31683504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038629343","display_name":"Wanyang Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I31683504","display_name":"Beijing Forestry University","ror":"https://ror.org/04xv2pc41","country_code":"CN","type":"education","lineage":["https://openalex.org/I1327237609","https://openalex.org/I31683504","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanyang Xu","raw_affiliation_strings":["School of Information Science and Technology, Beijing Forestry University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Beijing Forestry University, Beijing, China","institution_ids":["https://openalex.org/I31683504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100704964","display_name":"Yanyan Xu","orcid":"https://orcid.org/0000-0001-7174-6588"},"institutions":[{"id":"https://openalex.org/I31683504","display_name":"Beijing Forestry University","ror":"https://ror.org/04xv2pc41","country_code":"CN","type":"education","lineage":["https://openalex.org/I1327237609","https://openalex.org/I31683504","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanyan Xu","raw_affiliation_strings":["School of Information Science and Technology, Beijing Forestry University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Beijing Forestry University, Beijing, China","institution_ids":["https://openalex.org/I31683504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102845007","display_name":"Dengfeng Ke","orcid":"https://orcid.org/0000-0001-8459-0412"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dengfeng Ke","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037325282","display_name":"Kaile Su","orcid":"https://orcid.org/0000-0001-6741-9699"},"institutions":[{"id":"https://openalex.org/I11701301","display_name":"Griffith University","ror":"https://ror.org/02sc3r913","country_code":"AU","type":"education","lineage":["https://openalex.org/I11701301"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Kaile Su","raw_affiliation_strings":["Institute for Integrated and Intelligent Systems Griffith University, Nathan, Australia"],"affiliations":[{"raw_affiliation_string":"Institute for Integrated and Intelligent Systems Griffith University, Nathan, Australia","institution_ids":["https://openalex.org/I11701301"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5004719790"],"corresponding_institution_ids":["https://openalex.org/I31683504"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"240","last_page":"245"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9991999864578247,"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/T10860","display_name":"Speech and Audio Processing","score":0.9983999729156494,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.8087224960327148},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6254711747169495},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5993282794952393},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5981829166412354},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5899099111557007},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5622234344482422},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5314235687255859},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.5209890007972717},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4899124503135681},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.4779248833656311},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.45814698934555054},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4479026794433594},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37818431854248047},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2972896099090576},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.17004826664924622},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1160336434841156},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1074582040309906},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08350345492362976}],"concepts":[{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.8087224960327148},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6254711747169495},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5993282794952393},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5981829166412354},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5899099111557007},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5622234344482422},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5314235687255859},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.5209890007972717},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4899124503135681},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4779248833656311},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.45814698934555054},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4479026794433594},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37818431854248047},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2972896099090576},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.17004826664924622},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1160336434841156},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1074582040309906},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08350345492362976},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icccs49078.2020.9118426","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccs49078.2020.9118426","pdf_url":null,"source":{"id":"https://openalex.org/S4306498617","display_name":"2020 5th International Conference on Computer and Communication Systems (ICCCS)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 5th International Conference on Computer and Communication Systems (ICCCS)","raw_type":"proceedings-article"},{"id":"pmh:oai:research-repository.griffith.edu.au:10072/399268","is_oa":true,"landing_page_url":"http://hdl.handle.net/10072/399268","pdf_url":null,"source":{"id":"https://openalex.org/S4306402548","display_name":"Griffith Research Online (Griffith University, Queensland, Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I11701301","host_organization_name":"Griffith University","host_organization_lineage":["https://openalex.org/I11701301"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference output"}],"best_oa_location":{"id":"pmh:oai:research-repository.griffith.edu.au:10072/399268","is_oa":true,"landing_page_url":"http://hdl.handle.net/10072/399268","pdf_url":null,"source":{"id":"https://openalex.org/S4306402548","display_name":"Griffith Research Online (Griffith University, Queensland, Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I11701301","host_organization_name":"Griffith University","host_organization_lineage":["https://openalex.org/I11701301"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference output"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1965147617","https://openalex.org/W1967818247","https://openalex.org/W1968274390","https://openalex.org/W2011972438","https://openalex.org/W2019432531","https://openalex.org/W2048747935","https://openalex.org/W2069943693","https://openalex.org/W2072814159","https://openalex.org/W2088328344","https://openalex.org/W2096733369","https://openalex.org/W2108606783","https://openalex.org/W2141411743","https://openalex.org/W2149241068","https://openalex.org/W2149396430","https://openalex.org/W2221409856","https://openalex.org/W2295124130","https://openalex.org/W2395999201","https://openalex.org/W2607308654","https://openalex.org/W2735501586","https://openalex.org/W2766040302","https://openalex.org/W2784076614","https://openalex.org/W2938078275","https://openalex.org/W3099206234","https://openalex.org/W6655248001"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W4293226380","https://openalex.org/W2037549926","https://openalex.org/W2345479200","https://openalex.org/W2102148524","https://openalex.org/W2183306018","https://openalex.org/W2849310602","https://openalex.org/W3006008237","https://openalex.org/W4321487865","https://openalex.org/W2419146053"],"abstract_inverted_index":{"In":[0,60],"natural":[1],"environments,":[2],"bird":[3,17,58],"sounds":[4],"are":[5,130],"often":[6],"accompanied":[7],"by":[8,163,184,186],"background":[9],"noise,":[10],"so":[11],"denoising":[12,36,67,168],"becomes":[13],"crucial":[14],"to":[15,22,42,45,90,96,106],"automated":[16],"sound":[18],"recognition.":[19],"Recently,":[20],"thanks":[21],"neural":[23,136],"network":[24,137],"embeddings,":[25],"the":[26,47,53,85,98,102,107,119,124,133,140,153,158,166,171,175,191],"deep":[27,71],"clustering":[28],"method":[29,68,169],"has":[30],"achieved":[31],"better":[32],"performances":[33],"than":[34],"traditional":[35],"methods,":[37,40],"like":[38],"filter-based":[39],"due":[41],"its":[43],"ability":[44],"solve":[46],"problem":[48],"when":[49],"noise":[50],"is":[51],"in":[52,170],"same":[54,108],"frequency":[55],"range":[56],"as":[57],"sounds.":[59],"this":[61],"paper,":[62],"we":[63,83],"propose":[64],"a":[65,92],"generalized":[66],"based":[69],"on":[70,132],"clustering,":[72],"which":[73,115],"can":[74,116],"process":[75],"more":[76],"complex":[77],"recordings":[78],"with":[79,101,148,165,190],"less":[80],"distortion.":[81],"Also,":[82],"optimize":[84],"original":[86,192],"affinity":[87,193],"loss":[88,94,150,194],"function":[89,95,195],"get":[91],"novel":[93],"ensure":[97],"embedding":[99],"vectors":[100],"minimum":[103],"distance":[104],"belong":[105],"source,":[109],"named":[110],"Joint":[111],"Center":[112],"Loss":[113],"(JCL),":[114],"both":[117],"increase":[118],"inter-class":[120],"variance":[121,126],"and":[122,139,174],"decrease":[123],"intra-class":[125],"of":[127],"embeddings.":[128],"Experiments":[129],"conducted":[131],"gated":[134],"convolutional":[135],"architecture":[138,146],"bidirectional":[141],"long":[142],"short":[143],"term":[144],"memory":[145],"respectively":[147],"different":[149],"functions.":[151],"Given":[152],"signal-noise":[154],"ratio":[155],"being":[156],"-3dB,":[157],"recognition":[159],"accuracy":[160],"increases":[161,182],"relatively":[162,183],"9.5%":[164],"proposed":[167],"best":[172],"case,":[173],"Relative":[176],"Root":[177],"Mean":[178],"Square":[179],"Error":[180],"(RRMSE)":[181],"14.2%":[185],"using":[187],"JCL,":[188],"compared":[189],"AL.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}