{"id":"https://openalex.org/W3041102365","doi":"https://doi.org/10.1002/aisy.202000050","title":"Robot Audition and Computational Auditory Scene Analysis","display_name":"Robot Audition and Computational Auditory Scene Analysis","publication_year":2020,"publication_date":"2020-07-08","ids":{"openalex":"https://openalex.org/W3041102365","doi":"https://doi.org/10.1002/aisy.202000050","mag":"3041102365"},"language":"en","primary_location":{"id":"doi:10.1002/aisy.202000050","is_oa":true,"landing_page_url":"https://doi.org/10.1002/aisy.202000050","pdf_url":null,"source":{"id":"https://openalex.org/S4210212817","display_name":"Advanced Intelligent Systems","issn_l":"2640-4567","issn":["2640-4567"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advanced Intelligent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1002/aisy.202000050","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Kazuhiro Nakadai","raw_affiliation_strings":["Department of Systems and Control Engineering School of Engineering Tokyo Institute of Technology  2-12-1 Ookayama Meguro Tokyo 152\u20138552 Japan","Research Division Honda Research Institute Japan Co., Ltd.  8-1 Honcho Wako Saitama 351\u20130188 Japan"],"raw_orcid":"https://orcid.org/0000-0002-6134-4558","affiliations":[{"raw_affiliation_string":"Department of Systems and Control Engineering School of Engineering Tokyo Institute of Technology  2-12-1 Ookayama Meguro Tokyo 152\u20138552 Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Research Division Honda Research Institute Japan Co., Ltd.  8-1 Honcho Wako Saitama 351\u20130188 Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"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/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi G. Okuno","raw_affiliation_strings":["Graduate Program for Embodiment Informatics Waseda University  2-4-12 Lambdax Bldg. 301, O-kubo Shinjuku-ku Tokyo 169-0072 Japan","Graduate Program for Embodiment Informatics, Waseda University, 2-4-12 Lambdax Bldg. 301, O-kubo, Shinjuku-ku, Tokyo, 169-0072 Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Program for Embodiment Informatics Waseda University  2-4-12 Lambdax Bldg. 301, O-kubo Shinjuku-ku Tokyo 169-0072 Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Graduate Program for Embodiment Informatics, Waseda University, 2-4-12 Lambdax Bldg. 301, O-kubo, Shinjuku-ku, Tokyo, 169-0072 Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5091708408"],"corresponding_institution_ids":["https://openalex.org/I114531698","https://openalex.org/I1283473643"],"apc_list":{"value":2750,"currency":"USD","value_usd":3190},"apc_paid":{"value":2750,"currency":"USD","value_usd":3190},"fwci":1.5972,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.83022686,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"2","issue":"9","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10534","display_name":"Structural Health Monitoring Techniques","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7117481827735901},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6983330249786377},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5368860960006714},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5011403560638428},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4962025284767151},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46296313405036926},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.45849716663360596},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4454876184463501},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4250103831291199},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4175987243652344},{"id":"https://openalex.org/keywords/computational-auditory-scene-analysis","display_name":"Computational auditory scene analysis","score":0.41328057646751404},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1132403314113617},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.07963401079177856}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7117481827735901},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6983330249786377},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5368860960006714},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5011403560638428},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4962025284767151},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46296313405036926},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.45849716663360596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4454876184463501},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4250103831291199},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4175987243652344},{"id":"https://openalex.org/C73208851","wikidata":"https://www.wikidata.org/wiki/Q5157303","display_name":"Computational auditory scene analysis","level":2,"score":0.41328057646751404},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1132403314113617},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.07963401079177856},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1002/aisy.202000050","is_oa":true,"landing_page_url":"https://doi.org/10.1002/aisy.202000050","pdf_url":null,"source":{"id":"https://openalex.org/S4210212817","display_name":"Advanced Intelligent Systems","issn_l":"2640-4567","issn":["2640-4567"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advanced Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:2cfd6d3613b24eb4baf627f17f4cbe5a","is_oa":true,"landing_page_url":"https://doaj.org/article/2cfd6d3613b24eb4baf627f17f4cbe5a","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":"Advanced Intelligent Systems, Vol 2, Iss 9, Pp n/a-n/a (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1002/aisy.202000050","is_oa":true,"landing_page_url":"https://doi.org/10.1002/aisy.202000050","pdf_url":null,"source":{"id":"https://openalex.org/S4210212817","display_name":"Advanced Intelligent Systems","issn_l":"2640-4567","issn":["2640-4567"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advanced Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1525423297","display_name":"Systematization of Drone Audition Capable of Listening to Sounds in Real World Environments","funder_award_id":"19H00750","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G2098959732","display_name":"Construction of multimodal ecological scene analysis for bird behavior analysis","funder_award_id":"20H00475","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":21,"referenced_works":["https://openalex.org/W1996160878","https://openalex.org/W2002457774","https://openalex.org/W2017835752","https://openalex.org/W2026257980","https://openalex.org/W2046317813","https://openalex.org/W2069432516","https://openalex.org/W2075360134","https://openalex.org/W2081753968","https://openalex.org/W2159956319","https://openalex.org/W2416573875","https://openalex.org/W2592087066","https://openalex.org/W2592600618","https://openalex.org/W2598490835","https://openalex.org/W2766086962","https://openalex.org/W2768041052","https://openalex.org/W2774341174","https://openalex.org/W2909218286","https://openalex.org/W2933305660","https://openalex.org/W2998774371","https://openalex.org/W3011650175","https://openalex.org/W4256399001"],"related_works":["https://openalex.org/W2475724061","https://openalex.org/W2773393136","https://openalex.org/W2174706483","https://openalex.org/W419536403","https://openalex.org/W2506280730","https://openalex.org/W2997121352","https://openalex.org/W2366328218","https://openalex.org/W2509366663","https://openalex.org/W4243944146","https://openalex.org/W2385004494"],"abstract_inverted_index":{"Robot":[0],"audition":[1,102,114,129],"aims":[2],"at":[3],"developing":[4],"robot's":[5],"ears":[6],"that":[7,13,139],"work":[8],"in":[9,119],"the":[10,61,87,120,132],"real":[11,121],"world,":[12],"is,":[14,140],"machine":[15],"listening":[16],"of":[17,63,77,89,100,108,134,142],"multiple":[18,49],"sound":[19],"sources.":[20],"Its":[21],"critical":[22,44],"problem":[23],"is":[24,125],"noise.":[25],"Speech":[26],"interfaces":[27,65],"have":[28,56],"become":[29],"more":[30,33],"familiar":[31],"and":[32,37,48,66,98,115],"indispensable":[34],"as":[35,92],"smartphones":[36],"artificial":[38],"intelligence":[39],"(AI)":[40],"speakers":[41],"spread.":[42],"Their":[43],"problems":[45],"are":[46,103],"noise":[47,75,93],"simultaneous":[50],"speakers.":[51],"Recently":[52],"two":[53],"technological":[54],"advances":[55],"contributed":[57],"to":[58,131],"significantly":[59],"improve":[60],"performance":[62,88],"speech":[64,79],"robot":[67,101,113,128],"audition.":[68],"Emerging":[69],"deep":[70],"learning":[71],"technology":[72],"has":[73,85],"improved":[74,86],"robustness":[76],"automatic":[78],"recognition,":[80],"whereas":[81],"microphone":[82],"array":[83],"processing":[84],"preprocessing":[90],"such":[91],"reduction.":[94],"Herein,":[95],"an":[96,109],"overview":[97],"history":[99],"provided":[104],"together":[105],"with":[106],"introduction":[107],"open\u2010source":[110],"software":[111],"for":[112],"its":[116],"wide":[117],"applications":[118],"world.":[122],"Also,":[123],"it":[124],"discussed":[126],"how":[127],"contributes":[130],"development":[133],"computational":[135],"auditory":[136,144],"scene":[137],"analysis,":[138],"understanding":[141],"real\u2010world":[143],"environments.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
