{"id":"https://openalex.org/W4388739317","doi":"https://doi.org/10.1109/lra.2023.3333700","title":"Microphone Pair Training for Robust Sound Source Localization With Diverse Array Configurations","display_name":"Microphone Pair Training for Robust Sound Source Localization With Diverse Array Configurations","publication_year":2023,"publication_date":"2023-11-16","ids":{"openalex":"https://openalex.org/W4388739317","doi":"https://doi.org/10.1109/lra.2023.3333700"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2023.3333700","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3333700","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/A5048070637","display_name":"Inkyu An","orcid":"https://orcid.org/0000-0001-6812-1587"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Inkyu An","raw_affiliation_strings":["Integrated Intelligence Research Section, Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Integrated Intelligence Research Section, Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081376949","display_name":"Guoyuan An","orcid":"https://orcid.org/0009-0008-6233-757X"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Guoyuan An","raw_affiliation_strings":["School of Computing, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Computing, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412362","display_name":"Taeyoung Kim","orcid":"https://orcid.org/0000-0002-1894-6596"},"institutions":[{"id":"https://openalex.org/I4210140519","display_name":"Korean Association Of Science and Technology Studies","ror":"https://ror.org/04qh86j58","country_code":"KR","type":"other","lineage":["https://openalex.org/I4210140519"]},{"id":"https://openalex.org/I58716616","display_name":"Korea Institute of Science and Technology","ror":"https://ror.org/05kzfa883","country_code":"KR","type":"facility","lineage":["https://openalex.org/I27494661","https://openalex.org/I2801339556","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098","https://openalex.org/I4387152098","https://openalex.org/I58716616"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Taeyoung Kim","raw_affiliation_strings":["Center for Artificial Intelligence, Korea Institute of Science and Technology, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence, Korea Institute of Science and Technology, Seoul, South Korea","institution_ids":["https://openalex.org/I58716616","https://openalex.org/I4210140519"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078173428","display_name":"Sung\u2010Eui Yoon","orcid":"https://orcid.org/0000-0002-7123-1119"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sung-eui Yoon","raw_affiliation_strings":["School of Computing, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Computing, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5048070637"],"corresponding_institution_ids":["https://openalex.org/I142401562"],"apc_list":null,"apc_paid":null,"fwci":1.5848,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.84810911,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"9","issue":"1","first_page":"319","last_page":"326"},"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9955999851226807,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/multilateration","display_name":"Multilateration","score":0.9307996034622192},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7243992686271667},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.7063109278678894},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.6859523057937622},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5824437141418457},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5268118381500244},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5263187289237976},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.4692756235599518},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4101138114929199},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.378792941570282},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.24181094765663147},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.23399394750595093},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.1146940290927887},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08511409163475037},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.07528635859489441}],"concepts":[{"id":"https://openalex.org/C104037064","wikidata":"https://www.wikidata.org/wiki/Q1640884","display_name":"Multilateration","level":3,"score":0.9307996034622192},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7243992686271667},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7063109278678894},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.6859523057937622},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5824437141418457},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5268118381500244},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5263187289237976},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.4692756235599518},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4101138114929199},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.378792941570282},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.24181094765663147},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.23399394750595093},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.1146940290927887},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08511409163475037},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.07528635859489441},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2023.3333700","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3333700","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1560213421","https://openalex.org/W1578856370","https://openalex.org/W2046317813","https://openalex.org/W2093010905","https://openalex.org/W2100818340","https://openalex.org/W2101856597","https://openalex.org/W2103869314","https://openalex.org/W2113638573","https://openalex.org/W2132605602","https://openalex.org/W2168772505","https://openalex.org/W2411093439","https://openalex.org/W2772736377","https://openalex.org/W2810934215","https://openalex.org/W3105684258","https://openalex.org/W3117498573","https://openalex.org/W3198730349","https://openalex.org/W3205596865","https://openalex.org/W3212225065","https://openalex.org/W4385245566","https://openalex.org/W4394669361","https://openalex.org/W6630830844","https://openalex.org/W6684683330","https://openalex.org/W6760529994","https://openalex.org/W6790690058","https://openalex.org/W6796679619","https://openalex.org/W6797065961"],"related_works":["https://openalex.org/W2288274698","https://openalex.org/W4385361701","https://openalex.org/W2068968550","https://openalex.org/W2770231486","https://openalex.org/W2187684650","https://openalex.org/W2159296145","https://openalex.org/W1879255185","https://openalex.org/W2188292175","https://openalex.org/W4386900535","https://openalex.org/W1983991597"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,100,108,194],"novel":[3],"sound":[4,133,150],"source":[5],"localization":[6],"method":[7,197],"that":[8],"leverages":[9],"microphone":[10,36,56,185],"pair":[11,57],"training,":[12,58],"designed":[13,64],"to":[14,76,87,117,142,178],"deliver":[15],"robust":[16,199],"performance":[17,200],"in":[18,123],"various":[19,33,82,121,132],"real-world":[20,83],"environments.":[21],"Existing":[22],"deep":[23],"learning":[24],"(DL)-based":[25],"approaches":[26],"face":[27],"scalability":[28],"issues":[29],"when":[30],"dealing":[31],"with":[32,162],"types":[34,209],"of":[35,93,146,149,182,210],"arrays.":[37,211],"To":[38],"address":[39],"these":[40],"issues,":[41],"our":[42,74,140,157,173,196],"approach":[43,141,174],"has":[44],"been":[45],"structured":[46],"into":[47],"two":[48,202],"training":[49,71,137,168],"steps:":[50],"the":[51,60,90,144,166,183],"first":[52,70,167],"step":[53,62,72,138],"focuses":[54],"on":[55,152],"while":[59],"second":[61,136],"is":[63],"for":[65],"array":[66,191],"geometry-aware":[67],"training.":[68],"The":[69,135],"enables":[73,139],"model":[75,98],"learn":[77,119],"from":[78,120],"multiple":[79,124],"datasets":[80],"covering":[81],"situations,":[84],"allowing":[85],"it":[86,116],"robustly":[88],"estimate":[89,143],"time":[91],"difference":[92],"arrival":[94,147],"(TDoA).":[95],"Our":[96],"robust-TDoA":[97,158],"incorporates":[99],"Mel":[101],"scale":[102],"learnable":[103],"filter":[104],"bank":[105],"(MLFB)":[106],"and":[107,131],"hierarchical":[109],"frequency-to-time":[110],"attention":[111],"network":[112],"(HiFTA-net).":[113],"This":[114],"allows":[115],"effectively":[118],"situations":[122],"datasets,":[125],"including":[126],"those":[127],"involving":[128],"simultaneous":[129],"sources":[130],"events.":[134],"direction":[145],"(DoA)":[148],"based":[151],"TDoA":[153],"information":[154,181],"computed":[155],"by":[156],"model,":[159],"which":[160,187],"begins":[161],"parameters":[163],"acquired":[164],"during":[165],"step.":[169],"During":[170],"this":[171],"process,":[172],"can":[175,188],"be":[176],"trained":[177],"accommodate":[179],"geometry":[180],"target":[184],"array,":[186],"span":[189],"diverse":[190],"types.":[192],"As":[193],"result,":[195],"demonstrates":[198],"across":[201],"DoA":[203],"estimation":[204],"tasks":[205],"using":[206],"three":[207],"different":[208]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}