{"id":"https://openalex.org/W2985562188","doi":"https://doi.org/10.1109/icca.2019.8899739","title":"Robust Sound Localization of Sound Sources using Deep Convolution Network","display_name":"Robust Sound Localization of Sound Sources using Deep Convolution Network","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2985562188","doi":"https://doi.org/10.1109/icca.2019.8899739","mag":"2985562188"},"language":"en","primary_location":{"id":"doi:10.1109/icca.2019.8899739","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icca.2019.8899739","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 15th International Conference on Control and Automation (ICCA)","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/A5110647529","display_name":"Jianing Tong","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"J. J. Tong","raw_affiliation_strings":["National University of Singapore,Department of Mechanical Engineering","Department of Mechanical Engineering, National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Mechanical Engineering","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Department of Mechanical Engineering, National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056723921","display_name":"Yunfeng Zhang","orcid":"https://orcid.org/0000-0002-3630-9232"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Y. F. Zhang","raw_affiliation_strings":["National University of Singapore,Department of Mechanical Engineering","Department of Mechanical Engineering, National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Mechanical Engineering","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Department of Mechanical Engineering, National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1669,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.46825735,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"196","last_page":"200"},"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/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9830999970436096,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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":0.8057131171226501},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.7339081764221191},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.72469162940979},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6871576309204102},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.616229236125946},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6103017330169678},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6019735932350159},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5551321506500244},{"id":"https://openalex.org/keywords/multilateration","display_name":"Multilateration","score":0.5232633352279663},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.49862098693847656},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.496963769197464},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.4670119881629944},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.452253133058548},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.42080923914909363},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4198065996170044},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.41747209429740906},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41209664940834045},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.2740342617034912},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.12326991558074951},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.11602917313575745}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8057131171226501},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.7339081764221191},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.72469162940979},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6871576309204102},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.616229236125946},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6103017330169678},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6019735932350159},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5551321506500244},{"id":"https://openalex.org/C104037064","wikidata":"https://www.wikidata.org/wiki/Q1640884","display_name":"Multilateration","level":3,"score":0.5232633352279663},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.49862098693847656},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.496963769197464},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.4670119881629944},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.452253133058548},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.42080923914909363},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4198065996170044},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.41747209429740906},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41209664940834045},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.2740342617034912},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.12326991558074951},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.11602917313575745},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icca.2019.8899739","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icca.2019.8899739","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 15th International Conference on Control and Automation (ICCA)","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":7,"referenced_works":["https://openalex.org/W1603075283","https://openalex.org/W2403149086","https://openalex.org/W2586642235","https://openalex.org/W2663904211","https://openalex.org/W2772736377","https://openalex.org/W2803501587","https://openalex.org/W3105684258"],"related_works":["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/W2188292175","https://openalex.org/W4386900535","https://openalex.org/W1983991597"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,88],"sound":[4,174],"source":[5,175],"localization":[6,42],"(SSL)":[7],"approach":[8,92],"based":[9,20,90],"on":[10,21,172],"Deep":[11],"Convolutional":[12],"Neural":[13],"Network":[14],"(CNN).":[15],"Conventional":[16],"SSL":[17],"methods,":[18],"either":[19],"the":[22,73,95,101,109,113,117,124,144,159],"time":[23],"delay":[24],"of":[25,65,103,134],"arrival":[26],"(TDOA)":[27],"or":[28],"Subspace":[29],"such":[30],"as":[31,76,176],"Multiple":[32],"Signal":[33],"Classification":[34],"(MUSIC),":[35],"often":[36],"fail":[37],"in":[38,49,123],"scenarios":[39],"where":[40],"real-time":[41],"is":[43,67,147],"required.":[44],"To":[45],"resolve":[46],"this":[47,63,84,135],"limitation,":[48],"recent":[50],"years,":[51],"researchers":[52],"have":[53,168],"been":[54],"using":[55],"feature-based":[56,139,182],"neural":[57,183],"networks":[58],"to":[59,93,106,127,178],"locate":[60],"sounds.":[61],"However,":[62],"type":[64],"network":[66],"not":[68],"ideal":[69],"and":[70,131,149,181],"suffers":[71,153],"from":[72,120,154,158,162],"same":[74],"limitation":[75],"feature":[77,98],"extraction":[78,99],"must":[79],"be":[80],"done":[81],"prior.":[82],"In":[83],"paper,":[85],"we":[86],"propose":[87],"non-feature":[89],"learning":[91,140],"bypass":[94],"need":[96],"for":[97,112],"through":[100],"use":[102],"convolutional":[104],"layers":[105],"directly":[107],"learn":[108],"features":[110,160],"responsible":[111],"non-linear":[114],"mapping":[115],"between":[116],"raw":[118],"signals":[119],"each":[121],"microphone":[122,125],"array":[126],"their":[128],"respective":[129],"directions":[130],"locations.":[132],"Advantages":[133],"method":[136],"over":[137],"conventional":[138,179],"approaches":[141],"are":[142],"that":[143],"computational":[145],"cost":[146],"reduced,":[148],"it":[150],"no":[151],"longer":[152],"low":[155],"accuracy":[156,171],"arises":[157],"derived":[161],"traditional":[163],"methods.":[164],"Primarily":[165],"experimental":[166],"results":[167],"shown":[169],"promising":[170],"locating":[173],"compared":[177],"methods":[180],"networks.":[184]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}