{"id":"https://openalex.org/W2909977939","doi":"https://doi.org/10.1109/iros.2018.8594070","title":"HARK-Bird-Box: A Portable Real-time Bird Song Scene Analysis System","display_name":"HARK-Bird-Box: A Portable Real-time Bird Song Scene Analysis System","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2909977939","doi":"https://doi.org/10.1109/iros.2018.8594070","mag":"2909977939"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2018.8594070","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2018.8594070","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","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":"https://openalex.org/A5013489463","display_name":"Ryosuke Kojima","orcid":"https://orcid.org/0000-0003-1095-8864"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryosuke Kojima","raw_affiliation_strings":["Department of Biomedical Data Intelligence, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Data Intelligence, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018649614","display_name":"Osamu Sugiyama","orcid":"https://orcid.org/0000-0003-0190-1321"},"institutions":[{"id":"https://openalex.org/I4210150196","display_name":"Kyoto University Hospital","ror":"https://ror.org/04k6gr834","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I4210150196"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Osamu Sugiyama","raw_affiliation_strings":["Preemptive Medicine & Lifestyle-Related Disease Research Center, Kyoto University Hospital, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Preemptive Medicine & Lifestyle-Related Disease Research Center, Kyoto University Hospital, Kyoto, Japan","institution_ids":["https://openalex.org/I4210150196"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049821201","display_name":"Kotaro Hoshiba","orcid":"https://orcid.org/0000-0002-9052-331X"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kotaro Hoshiba","raw_affiliation_strings":["Department of Systems and Control Engineering, Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems and Control Engineering, Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001027770","display_name":"Reiji Suzuki","orcid":"https://orcid.org/0000-0002-1953-2926"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Reiji Suzuki","raw_affiliation_strings":["Graduate School of Information Science, Nagoya University, Aichi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nagoya University, Aichi, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091708408","display_name":"Kazuhiro Nakadai","orcid":"https://orcid.org/0000-0002-6134-4558"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhiro Nakadai","raw_affiliation_strings":["Department of Systems and Control Engineering, Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems and Control Engineering, Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2497","last_page":"2502"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9998999834060669,"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":0.9998999834060669,"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":0.995199978351593,"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":0.9937000274658203,"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/software-portability","display_name":"Software portability","score":0.7630230188369751},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7351834774017334},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.654273509979248},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.6272776126861572},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5803495049476624},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5519716143608093},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5413678884506226},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5034927725791931},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.47978073358535767},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.42240387201309204},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.41672688722610474},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3692095875740051},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08585435152053833}],"concepts":[{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.7630230188369751},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7351834774017334},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.654273509979248},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.6272776126861572},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5803495049476624},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5519716143608093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5413678884506226},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5034927725791931},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.47978073358535767},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.42240387201309204},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.41672688722610474},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3692095875740051},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08585435152053833},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros.2018.8594070","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2018.8594070","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1572146192","https://openalex.org/W1606496075","https://openalex.org/W1974148107","https://openalex.org/W2021850176","https://openalex.org/W2036982758","https://openalex.org/W2072814159","https://openalex.org/W2074134755","https://openalex.org/W2108950108","https://openalex.org/W2113638573","https://openalex.org/W2116894522","https://openalex.org/W2217431788","https://openalex.org/W2293488548","https://openalex.org/W2567135925","https://openalex.org/W2594166949","https://openalex.org/W2594538140","https://openalex.org/W2624421568","https://openalex.org/W2757154355","https://openalex.org/W2774341174","https://openalex.org/W4300916540","https://openalex.org/W6731655843"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W2900122540","https://openalex.org/W4240587264","https://openalex.org/W2011788874","https://openalex.org/W2041060376","https://openalex.org/W2963983801","https://openalex.org/W3119734852"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"real-time":[3,27,60,160],"bird":[4,84,110,142,168],"song":[5,85,111,143,169],"scene":[6,144],"analysis.":[7,86,145],"Observation":[8],"of":[9,15,44,48,55,184],"animal":[10],"behavior":[11],"such":[12,49,64],"as":[13],"communication":[14],"wild":[16],"birds":[17],"would":[18],"be":[19],"aided":[20],"by":[21,91],"a":[22,26,50,65,69,103,109,115,127,133,138,150,159,167,172],"portable":[23],"device":[24,140],"implementing":[25],"system":[28,51,88,125,156],"that":[29],"can":[30],"localize":[31],"sound":[32,73],"sources,":[33,39],"measure":[34],"their":[35,38],"timing,":[36],"classify":[37],"and":[40,81,102,136,178,181],"visualize":[41],"these":[42,56],"factors":[43],"sources.":[45],"The":[46],"difficulty":[47],"is":[52,89],"an":[53,93,163],"integration":[54],"functions":[57],"considering":[58],"the":[59,154,182],"requirement.":[61],"To":[62],"realize":[63,158],"system,":[66],"we":[67,122],"propose":[68],"cascaded":[70],"approach,":[71],"cascading":[72],"source":[74,95],"detection,":[75],"localization,":[76],"separation,":[77],"feature":[78],"extraction,":[79],"classification,":[80],"visualization":[82],"for":[83,97,141,153],"Our":[87],"constructed":[90],"combining":[92],"open":[94],"software":[96],"robot":[98],"audition":[99],"called":[100],"HARK":[101],"deep":[104],"learning":[105],"library":[106],"to":[107,157],"implement":[108],"classifier":[112],"based":[113],"on":[114,126],"convolutional":[116],"neural":[117],"network":[118],"(CNN).":[119],"Considering":[120],"portability,":[121],"implemented":[123],"this":[124],"single-board":[128],"computer,":[129],"Jetson":[130],"TX2,":[131],"with":[132,166],"microphone":[134],"array":[135],"developed":[137],"prototype":[139],"A":[146],"preliminary":[147],"experiment":[148,165],"confirms":[149],"computational":[151],"time":[152,179],"whole":[155],"system.":[161],"Also,":[162],"additional":[164],"dataset":[170],"revealed":[171],"trade-off":[173],"relationship":[174],"between":[175],"classification":[176],"accuracy":[177],"consuming":[180],"effectiveness":[183],"our":[185],"classifier.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
