{"id":"https://openalex.org/W2921013720","doi":"https://doi.org/10.1109/ai4i.2018.8665693","title":"Detection Sound Source Direction in 3D Space Using Convolutional Neural Networks","display_name":"Detection Sound Source Direction in 3D Space Using Convolutional Neural Networks","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2921013720","doi":"https://doi.org/10.1109/ai4i.2018.8665693","mag":"2921013720"},"language":"en","primary_location":{"id":"doi:10.1109/ai4i.2018.8665693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ai4i.2018.8665693","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 First International Conference on Artificial Intelligence for Industries (AI4I)","raw_type":"proceedings-article"},"type":"article","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/A5101505174","display_name":"Yue Xiao","orcid":"https://orcid.org/0000-0002-5138-9509"},"institutions":[{"id":"https://openalex.org/I177721651","display_name":"Oakland University","ror":"https://ror.org/01ythxj32","country_code":"US","type":"education","lineage":["https://openalex.org/I177721651"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiao Yue","raw_affiliation_strings":["Computer Science and Engineering Department, Oakland University, Rochester, MI, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering Department, Oakland University, Rochester, MI, USA","institution_ids":["https://openalex.org/I177721651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005828574","display_name":"Guangzhi Qu","orcid":"https://orcid.org/0000-0003-4047-9514"},"institutions":[{"id":"https://openalex.org/I177721651","display_name":"Oakland University","ror":"https://ror.org/01ythxj32","country_code":"US","type":"education","lineage":["https://openalex.org/I177721651"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guangzhi Qu","raw_affiliation_strings":["Computer Science and Engineering Department, Oakland University, Rochester, MI, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering Department, Oakland University, Rochester, MI, USA","institution_ids":["https://openalex.org/I177721651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100461634","display_name":"Bo Liu","orcid":"https://orcid.org/0000-0002-2393-117X"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Liu","raw_affiliation_strings":["Faculty of Information Technology, Beijing University of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102983664","display_name":"Anyi Liu","orcid":"https://orcid.org/0000-0002-6011-1998"},"institutions":[{"id":"https://openalex.org/I177721651","display_name":"Oakland University","ror":"https://ror.org/01ythxj32","country_code":"US","type":"education","lineage":["https://openalex.org/I177721651"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anyi Liu","raw_affiliation_strings":["Computer Science and Engineering Department, Oakland University, Rochester, MI, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering Department, Oakland University, Rochester, MI, USA","institution_ids":["https://openalex.org/I177721651"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101505174"],"corresponding_institution_ids":["https://openalex.org/I177721651"],"apc_list":null,"apc_paid":null,"fwci":0.4954,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.66372738,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"81","last_page":"84"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T11309","display_name":"Music and Audio Processing","score":0.9966999888420105,"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/T11698","display_name":"Underwater Acoustics Research","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7692434787750244},{"id":"https://openalex.org/keywords/multilateration","display_name":"Multilateration","score":0.7573566436767578},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7553908824920654},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.6927144527435303},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.6097043752670288},{"id":"https://openalex.org/keywords/direction-of-arrival","display_name":"Direction of arrival","score":0.5240347981452942},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42538702487945557},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38819530606269836},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35977593064308167},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3568724989891052},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3488565683364868},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14352253079414368},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06347224116325378}],"concepts":[{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7692434787750244},{"id":"https://openalex.org/C104037064","wikidata":"https://www.wikidata.org/wiki/Q1640884","display_name":"Multilateration","level":3,"score":0.7573566436767578},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7553908824920654},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.6927144527435303},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.6097043752670288},{"id":"https://openalex.org/C172051844","wikidata":"https://www.wikidata.org/wiki/Q5280438","display_name":"Direction of arrival","level":3,"score":0.5240347981452942},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42538702487945557},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38819530606269836},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35977593064308167},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3568724989891052},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3488565683364868},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14352253079414368},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06347224116325378},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C21822782","wikidata":"https://www.wikidata.org/wiki/Q131214","display_name":"Antenna (radio)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ai4i.2018.8665693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ai4i.2018.8665693","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 First International Conference on Artificial Intelligence for Industries (AI4I)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1603075283","https://openalex.org/W2037684811","https://openalex.org/W2046317813","https://openalex.org/W2117678320"],"related_works":["https://openalex.org/W4386900535","https://openalex.org/W2288274698","https://openalex.org/W4385361701","https://openalex.org/W4391643140","https://openalex.org/W2068968550","https://openalex.org/W2770231486","https://openalex.org/W2187684650","https://openalex.org/W2159296145","https://openalex.org/W3001418501","https://openalex.org/W2350404734"],"abstract_inverted_index":{"Sound":[0],"source":[1,18,32,51,114],"detection":[2,20,119],"and":[3,91,115],"localization":[4],"have":[5],"a":[6,34,54,81],"lot":[7],"of":[8,16,30,76,103],"practical":[9],"uses":[10],"in":[11,22,33,53,126],"many":[12],"industrial":[13],"settings.":[14],"Most":[15],"sound":[17,31,50,105,113,117],"direction":[19,52],"algorithms":[21],"literature":[23],"are":[24],"designed":[25],"to":[26,42,47,72],"identify":[27],"the":[28,49,62,121],"angle":[29],"2D":[35],"space.":[36,56],"In":[37,93],"this":[38,86,99],"work,":[39],"we":[40],"propose":[41],"use":[43],"convolutional":[44,82],"neural":[45,83],"networks":[46],"detect":[48],"3D":[55],"This":[57],"algorithm":[58,87],"is":[59],"based":[60],"on":[61,111],"generalized":[63],"cross":[64],"correlation":[65],"method":[66],"with":[67],"phase":[68],"transform":[69],"(GCC-PHAT)":[70],"[1]":[71],"derive":[73],"time":[74],"delay":[75],"arrival":[77],"(TDOA).":[78],"By":[79],"using":[80],"network":[84],"model,":[85],"can":[88],"be":[89],"applied":[90],"deployed.":[92],"addition,":[94],"by":[95],"modifying":[96],"GCC-PHAT":[97],"formula,":[98],"approach":[100],"also":[101],"works":[102],"multiple":[104,116],"sources":[106,118],"detection.":[107],"Simulation":[108],"experimental":[109],"results":[110],"single":[112],"show":[120],"proposed":[122],"system":[123],"could":[124],"work":[125],"most":[127],"situations.":[128]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}