{"id":"https://openalex.org/W2561787614","doi":"https://doi.org/10.1109/iros.2016.7759213","title":"Semi-automatic bird song analysis by spatial-cue-based integration of sound source detection, localization, separation, and identification","display_name":"Semi-automatic bird song analysis by spatial-cue-based integration of sound source detection, localization, separation, and identification","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W2561787614","doi":"https://doi.org/10.1109/iros.2016.7759213","mag":"2561787614"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2016.7759213","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2016.7759213","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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/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":"Ryosuke Kojima","raw_affiliation_strings":["Graduate School of Information Science and Engineering, Tokyo Institute of Technology, Tokyo, JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Engineering, Tokyo Institute of Technology, Tokyo, JAPAN","institution_ids":["https://openalex.org/I114531698"]}]},{"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/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":"Osamu Sugiyama","raw_affiliation_strings":["Graduate School of Information Science and Engineering, Tokyo Institute of Technology, Tokyo, JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and 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, Nagoya, Aichi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nagoya University, Nagoya, Aichi, Japan","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"]},{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhiro Nakadai","raw_affiliation_strings":["Graduate School of Information Science and Engineering, Tokyo Institute of Technology, Tokyo, JAPAN","Honda Research Institute Japan Co., Ltd., Saitama, JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Engineering, Tokyo Institute of Technology, Tokyo, JAPAN","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Honda Research Institute Japan Co., Ltd., Saitama, JAPAN","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101701618","display_name":"Charles Taylor","orcid":"https://orcid.org/0000-0002-5202-3445"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles E. Taylor","raw_affiliation_strings":["Department of Ecology and Evolutionary Biology, UCLA, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Ecology and Evolutionary Biology, UCLA, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1287","last_page":"1292"},"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":0.9950000047683716,"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":0.9930999875068665,"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/annotation","display_name":"Annotation","score":0.8208432197570801},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7733731865882874},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6922723650932312},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6918699145317078},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.540737509727478},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5312083959579468},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5275561213493347},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.49909377098083496},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4802848994731903},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4536064565181732},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.45078837871551514},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3686016798019409},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3598622679710388},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33713191747665405},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.2998218536376953}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.8208432197570801},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7733731865882874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6922723650932312},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6918699145317078},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.540737509727478},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5312083959579468},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5275561213493347},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.49909377098083496},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4802848994731903},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4536064565181732},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.45078837871551514},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3686016798019409},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3598622679710388},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33713191747665405},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.2998218536376953},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","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},{"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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros.2016.7759213","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2016.7759213","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50504066","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100812396","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G5300062852","display_name":null,"funder_award_id":"24220006","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1977834503","https://openalex.org/W2021850176","https://openalex.org/W2074134755","https://openalex.org/W2081074144","https://openalex.org/W2084533374","https://openalex.org/W2097089247","https://openalex.org/W2102381657","https://openalex.org/W2107456423","https://openalex.org/W2111609778","https://openalex.org/W2113638573","https://openalex.org/W2151316819","https://openalex.org/W2159333554","https://openalex.org/W2161386519","https://openalex.org/W2210729135"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W1608003482","https://openalex.org/W2903040254","https://openalex.org/W2074134755","https://openalex.org/W4226449293","https://openalex.org/W2943743938","https://openalex.org/W2129566906","https://openalex.org/W2117408192","https://openalex.org/W2169872459"],"abstract_inverted_index":{"This":[0,36],"paper":[1],"addresses":[2],"bird":[3,197],"song":[4],"analysis":[5],"based":[6,212],"on":[7,144,213],"semi-automatic":[8,184],"annotation.":[9,71],"Research":[10],"in":[11,41,65,127],"animal":[12],"behavior,":[13],"especially":[14],"with":[15,194],"birds,":[16],"would":[17],"be":[18,48],"aided":[19,138],"by":[20,139],"automated":[21,97],"(or":[22],"semiautomated)":[23],"systems":[24],"that":[25,95,135,160,170,187,203],"can":[26],"localize":[27],"sounds,":[28],"measure":[29],"their":[30,34],"timing,":[31],"and":[32,53,108],"identify":[33],"source.":[35],"is":[37,74,137],"difficult":[38],"to":[39,124],"achieve":[40],"real":[42],"environments":[43],"where":[44],"several":[45],"birds":[46],"may":[47,83,171],"singing":[49],"from":[50,61,99,130,199],"different":[51],"locations":[52],"at":[54],"the":[55,62,66,131,200],"same":[56],"time.":[57],"Analysis":[58],"of":[59,177,196],"recordings":[60,195],"wild":[63,201],"has":[64,158],"past":[67],"typically":[68,116,165],"required":[69],"manual":[70],"Such":[72],"annotation":[73,185],"not":[75],"always":[76],"accurate":[77],"or":[78,87],"even":[79],"consistent,":[80],"as":[81],"it":[82],"vary":[84],"both":[85],"within":[86,151],"between":[88],"observers.":[89],"Here":[90],"we":[91],"propose":[92],"a":[93,141,152,167,173,183,210],"system":[94,208],"uses":[96],"methods":[98,164],"robot":[100,111,215],"audition,":[101],"including":[102],"sound":[103],"source":[104],"detection,":[105],"localization,":[106],"separation":[107],"identification.":[109],"In":[110],"audition":[112],"these":[113],"technologies":[114],"have":[115,181],"been":[117,159],"studied":[118],"separately;":[119],"combining":[120,148],"them":[121],"often":[122],"leads":[123],"poor":[125],"performance":[126],"real-time":[128],"application":[129],"wild.":[132],"We":[133,180],"suggest":[134],"integration":[136],"placing":[140],"primary":[142],"focus":[143],"spatial":[145],"cues,":[146],"then":[147],"other":[149],"features":[150],"Bayesian":[153],"framework.":[154],"A":[155],"second":[156],"problem":[157],"supervised":[161],"machine":[162],"learning":[163],"requires":[166,188],"pre-trained":[168],"model":[169],"require":[172],"large":[174],"training":[175],"set":[176],"annotated":[178],"labels.":[179],"employed":[182],"approach":[186],"much":[189],"less":[190],"pre-annotation.":[191],"Preliminary":[192],"experiments":[193],"songs":[198],"revealed":[202],"for":[204],"identification":[205],"accuracy":[206],"our":[207],"outperformed":[209],"method":[211],"conventional":[214],"audition.":[216]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4}],"updated_date":"2026-07-16T05:54:29.318815","created_date":"2025-10-10T00:00:00"}