{"id":"https://openalex.org/W4224932505","doi":"https://doi.org/10.1109/icassp43922.2022.9747845","title":"Spherical Convolutional Recurrent Neural Network for Real-Time Sound Source Tracking","display_name":"Spherical Convolutional Recurrent Neural Network for Real-Time Sound Source Tracking","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224932505","doi":"https://doi.org/10.1109/icassp43922.2022.9747845"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747845","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747845","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5021923092","display_name":"Tianle Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]},{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["CN","JP"],"is_corresponding":false,"raw_author_name":"Tianle Zhong","raw_affiliation_strings":["The University of Electro-Communications,Graduate School of Informatics,Tokyo,Japan","University of Electronic Science and Technology of China, Chengdu, China","Graduate School of Informatics, The University of Electro-Communications, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications,Graduate School of Informatics,Tokyo,Japan","institution_ids":["https://openalex.org/I20529979"]},{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"Graduate School of Informatics, The University of Electro-Communications, Tokyo, Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054116710","display_name":"Israel Mendoza Velazquez","orcid":null},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Israel Mendoza Velazquez","raw_affiliation_strings":["The University of Electro-Communications,Graduate School of Informatics,Tokyo,Japan","Graduate School of Informatics, The University of Electro-Communications, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications,Graduate School of Informatics,Tokyo,Japan","institution_ids":["https://openalex.org/I20529979"]},{"raw_affiliation_string":"Graduate School of Informatics, The University of Electro-Communications, Tokyo, Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088179161","display_name":"Yi Ren","orcid":"https://orcid.org/0000-0001-9889-5460"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yi Ren","raw_affiliation_strings":["The University of Electro-Communications,Graduate School of Informatics,Tokyo,Japan","Graduate School of Informatics, The University of Electro-Communications, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications,Graduate School of Informatics,Tokyo,Japan","institution_ids":["https://openalex.org/I20529979"]},{"raw_affiliation_string":"Graduate School of Informatics, The University of Electro-Communications, Tokyo, Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060011108","display_name":"H\u00e9ctor Manuel P\u00e9rez Meana","orcid":null},"institutions":[{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Hector Manuel Perez Meana","raw_affiliation_strings":["National Polytechnic Institute of Mexico,ESIME Culhuacán,Mexico City,Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Polytechnic Institute of Mexico,ESIME Culhuacán,Mexico City,Mexico","institution_ids":["https://openalex.org/I59361560"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002515983","display_name":"Yoichi Haneda","orcid":"https://orcid.org/0000-0001-8477-6575"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoichi Haneda","raw_affiliation_strings":["The University of Electro-Communications,Graduate School of Informatics,Tokyo,Japan","Graduate School of Informatics, The University of Electro-Communications, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications,Graduate School of Informatics,Tokyo,Japan","institution_ids":["https://openalex.org/I20529979"]},{"raw_affiliation_string":"Graduate School of Informatics, The University of Electro-Communications, Tokyo, Japan","institution_ids":["https://openalex.org/I20529979"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5063","last_page":"5067"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9976000189781189,"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":0.9955999851226807,"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":0.8414695262908936},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7622458934783936},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5407052636146545},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.5181166529655457},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.49665242433547974},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49096420407295227},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4599636197090149},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4446639120578766},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4442829191684723},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32368898391723633},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.1083483099937439},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.10754290223121643},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.07770231366157532}],"concepts":[{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.8414695262908936},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7622458934783936},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5407052636146545},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.5181166529655457},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.49665242433547974},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49096420407295227},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4599636197090149},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4446639120578766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4442829191684723},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32368898391723633},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.1083483099937439},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.10754290223121643},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.07770231366157532},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747845","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747845","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":28,"referenced_works":["https://openalex.org/W126779258","https://openalex.org/W1494198834","https://openalex.org/W1976579441","https://openalex.org/W1989368986","https://openalex.org/W2046317813","https://openalex.org/W2064675550","https://openalex.org/W2113638573","https://openalex.org/W2174451236","https://openalex.org/W2561817999","https://openalex.org/W2611943505","https://openalex.org/W2772736377","https://openalex.org/W2898187790","https://openalex.org/W2898268964","https://openalex.org/W2917254586","https://openalex.org/W2940285530","https://openalex.org/W2963598163","https://openalex.org/W2964321699","https://openalex.org/W2964342924","https://openalex.org/W3034751264","https://openalex.org/W3104196160","https://openalex.org/W3104757150","https://openalex.org/W3108495681","https://openalex.org/W4200576194","https://openalex.org/W6605165268","https://openalex.org/W6676344012","https://openalex.org/W6720006811","https://openalex.org/W6746809379","https://openalex.org/W6769516661"],"related_works":["https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W1847088711","https://openalex.org/W4225394202","https://openalex.org/W3036642985","https://openalex.org/W3032952384","https://openalex.org/W2964335273","https://openalex.org/W2982145560","https://openalex.org/W2969450769","https://openalex.org/W2326447594"],"abstract_inverted_index":{"Neural":[0],"networks":[1,72],"have":[2],"been":[3],"widely":[4],"applied":[5],"in":[6],"direction-of-arrival":[7],"(DOA)":[8],"estimation":[9,54],"and":[10,55,75,87,103],"source":[11,52],"tracking":[12,56],"systems.":[13],"In":[14],"this":[15],"paper,":[16],"we":[17],"introduce":[18],"a":[19,28,62],"spherical":[20,30],"convolutional":[21,31,70],"recurrent":[22],"neural":[23,32,71],"network":[24,100],"that":[25,66],"utilizes":[26],"Deepsphere,":[27],"graph-based":[29],"network,":[33],"employing":[34],"the":[35,77,82,88],"steered":[36],"response":[37],"power":[38,43],"with":[39],"phase":[40],"transform":[41],"(SRP-PHAT)":[42],"maps":[44],"as":[45],"input":[46],"features":[47],"for":[48],"real-time":[49],"robust":[50],"sound":[51],"DOA":[53],"applications.":[57],"The":[58,95],"proposed":[59,99],"method":[60,74],"achieves":[61],"performance":[63],"similar":[64],"to":[65],"of":[67,98],"state-of-the-art":[68],"3D":[69],"(3D-CNNs)":[73],"reduces":[76],"processing":[78],"time":[79],"by":[80,85,92],"88.6%,":[81],"parameter":[83],"count":[84],"85.5%,":[86],"training":[89],"memory":[90],"usage":[91],"54.0%":[93],"respectively.":[94],"shallow":[96],"structure":[97],"demonstrates":[101],"effectiveness":[102],"efficiency.":[104]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}