{"id":"https://openalex.org/W4321020644","doi":"https://doi.org/10.1109/sii55687.2023.10039198","title":"Extracting Bird Vocalizations from a Complex Natural Soundscape in Forests Using Robot Audition Techniques","display_name":"Extracting Bird Vocalizations from a Complex Natural Soundscape in Forests Using Robot Audition Techniques","publication_year":2023,"publication_date":"2023-01-17","ids":{"openalex":"https://openalex.org/W4321020644","doi":"https://doi.org/10.1109/sii55687.2023.10039198"},"language":"en","primary_location":{"id":"doi:10.1109/sii55687.2023.10039198","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/sii55687.2023.10039198","pdf_url":null,"source":{"id":"https://openalex.org/S4363605654","display_name":"2023 IEEE/SICE International Symposium on System Integration (SII)","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":"2023 IEEE/SICE International Symposium on System Integration (SII)","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/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 Informatics, Nagoya University, Furo-cho, Chikusa-ku,Nagoya,Japan,464-8601"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Furo-cho, Chikusa-ku,Nagoya,Japan,464-8601","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086319025","display_name":"Shinji Sumitani","orcid":"https://orcid.org/0000-0003-3711-8603"},"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":"Shinji Sumitani","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University, Furo-cho, Chikusa-ku,Nagoya,Japan,464-8601"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Furo-cho, Chikusa-ku,Nagoya,Japan,464-8601","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022909863","display_name":"Zachary T. Harlow","orcid":"https://orcid.org/0000-0002-9573-7835"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zachary Harlow","raw_affiliation_strings":["University of California, Berkeley, Blue Oak Ranch Reserve, University of California,Berkeley,CA,USA,95132"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Blue Oak Ranch Reserve, University of California,Berkeley,CA,USA,95132","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084268295","display_name":"Shiho Matsubayashi","orcid":"https://orcid.org/0000-0002-2906-3166"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shiho Matsubayashi","raw_affiliation_strings":["Graduate School of Engineering Science, Osaka University,Osaka,Japan,560-8351"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering Science, Osaka University,Osaka,Japan,560-8351","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007424153","display_name":"Takaya Arita","orcid":"https://orcid.org/0000-0003-3688-2255"},"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":"Takaya Arita","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University, Furo-cho, Chikusa-ku,Nagoya,Japan,464-8601"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Furo-cho, Chikusa-ku,Nagoya,Japan,464-8601","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","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":["Tokyo Institute of Technology,Tokyo,Japan,152-8552"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology,Tokyo,Japan,152-8552","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005141184","display_name":"Hiroshi G. Okuno","orcid":"https://orcid.org/0000-0002-8704-4318"},"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":"Hiroshi G. Okuno","raw_affiliation_strings":["Kyoto University,Japan","Kyoto University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University,Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"29","issue":null,"first_page":"1","last_page":"6"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9933000206947327,"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":0.991599977016449,"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":0.7943631410598755},{"id":"https://openalex.org/keywords/soundscape","display_name":"Soundscape","score":0.7672992944717407},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.743999719619751},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6448014974594116},{"id":"https://openalex.org/keywords/bioacoustics","display_name":"Bioacoustics","score":0.6282080411911011},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5948638916015625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5315214395523071},{"id":"https://openalex.org/keywords/natural-sounds","display_name":"Natural sounds","score":0.5161565542221069},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.48048749566078186},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.41299134492874146},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37834715843200684},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.32215288281440735},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1514986753463745},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.143524169921875},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13386526703834534}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7943631410598755},{"id":"https://openalex.org/C142795923","wikidata":"https://www.wikidata.org/wiki/Q1358257","display_name":"Soundscape","level":3,"score":0.7672992944717407},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.743999719619751},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6448014974594116},{"id":"https://openalex.org/C34951282","wikidata":"https://www.wikidata.org/wiki/Q864191","display_name":"Bioacoustics","level":2,"score":0.6282080411911011},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5948638916015625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5315214395523071},{"id":"https://openalex.org/C2780646970","wikidata":"https://www.wikidata.org/wiki/Q6980787","display_name":"Natural sounds","level":2,"score":0.5161565542221069},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.48048749566078186},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.41299134492874146},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37834715843200684},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.32215288281440735},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1514986753463745},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.143524169921875},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13386526703834534},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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":1,"locations":[{"id":"doi:10.1109/sii55687.2023.10039198","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/sii55687.2023.10039198","pdf_url":null,"source":{"id":"https://openalex.org/S4363605654","display_name":"2023 IEEE/SICE International Symposium on System Integration (SII)","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":"2023 IEEE/SICE International Symposium on System Integration (SII)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15"}],"awards":[{"id":"https://openalex.org/G2129663337","display_name":"Monitoring Birdsong Communication with Sound Localization Techniques","funder_award_id":"19K15865","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7907346843","display_name":"Issues raised by open source in the legalization of AI and Robots","funder_award_id":"22K12210","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1606496075","https://openalex.org/W1997780152","https://openalex.org/W2020300735","https://openalex.org/W2113638573","https://openalex.org/W2114455599","https://openalex.org/W2152321507","https://openalex.org/W2520870210","https://openalex.org/W2563550206","https://openalex.org/W2592600618","https://openalex.org/W2596834449","https://openalex.org/W2600486037","https://openalex.org/W2757154355","https://openalex.org/W2774341174","https://openalex.org/W2888051270","https://openalex.org/W2889326414","https://openalex.org/W2938726981","https://openalex.org/W2943014698","https://openalex.org/W3011196403","https://openalex.org/W3021792075","https://openalex.org/W3035761178","https://openalex.org/W3093377669","https://openalex.org/W3125380646","https://openalex.org/W3153870698","https://openalex.org/W4308947931","https://openalex.org/W6761818968","https://openalex.org/W6798133626","https://openalex.org/W7008274290"],"related_works":["https://openalex.org/W2985581529","https://openalex.org/W3170167497","https://openalex.org/W2287491756","https://openalex.org/W2089315226","https://openalex.org/W4252208810","https://openalex.org/W1975881626","https://openalex.org/W2904690188","https://openalex.org/W4389082281","https://openalex.org/W4389279216","https://openalex.org/W2784529403"],"abstract_inverted_index":{"Songbirds":[0],"are":[1],"important":[2],"targets":[3],"of":[4,38,46,67,88,96],"bioacoustic":[5],"and":[6,21,28,54,60],"ecoacoustic":[7],"research.":[8],"We":[9,83],"propose":[10],"a":[11,51,55,79,93,99],"simple":[12],"method":[13,41,91],"to":[14,35,58,92],"extract":[15,59],"bird":[16,74],"vocalizations":[17],"from":[18,78],"many":[19],"localized":[20],"separated":[22,62],"sounds":[23],"using":[24],"robot":[25],"audition":[26],"techniques":[27],"report":[29],"its":[30],"evaluation":[31],"by":[32],"applying":[33,89],"it":[34],"field":[36,68],"recordings":[37],"birdsongs.":[39],"The":[40],"utilizes":[42],"latent":[43],"space":[44],"representations":[45],"the":[47,90],"spectrogram":[48],"based":[49],"on":[50],"variational":[52],"autoencoder":[53],"distance":[56],"measure":[57],"classify":[61],"songs.":[63],"A":[64],"preliminary":[65],"analysis":[66],"recording":[69],"in":[70],"California":[71],"successfully":[72],"extracted":[73],"vocalizations,":[75],"including":[76],"ones":[77],"considerably":[80],"distant":[81],"bird.":[82],"also":[84],"illustrate":[85],"an":[86],"example":[87],"2D":[94],"localization":[95],"birdsongs":[97],"during":[98],"playback":[100],"experiment.":[101]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
