{"id":"https://openalex.org/W3160649118","doi":"https://doi.org/10.1109/icassp39728.2021.9413695","title":"Data-Efficient Framework for Real-World Multiple Sound Source 2d Localization","display_name":"Data-Efficient Framework for Real-World Multiple Sound Source 2d Localization","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160649118","doi":"https://doi.org/10.1109/icassp39728.2021.9413695","mag":"3160649118"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413695","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5013053478","display_name":"Guillaume Le Moing","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I2746051580","display_name":"Universit\u00e9 Paris Sciences et Lettres","ror":"https://ror.org/013cjyk83","country_code":"FR","type":"education","lineage":["https://openalex.org/I2746051580"]},{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["FR","JP"],"is_corresponding":false,"raw_author_name":"Guillaume Le Moing","raw_affiliation_strings":["IBM Research, Tokyo, Japan","Inria, \u00c9cole normale sup\u00e9rieure, CNRS, PSL Research University, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Tokyo, Japan","institution_ids":["https://openalex.org/I4210145865"]},{"raw_affiliation_string":"Inria, \u00c9cole normale sup\u00e9rieure, CNRS, PSL Research University, Paris, France","institution_ids":["https://openalex.org/I2746051580","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053801369","display_name":"Phongtharin Vinayavekhin","orcid":"https://orcid.org/0009-0003-8050-6422"},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Phongtharin Vinayavekhin","raw_affiliation_strings":["IBM Research, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Tokyo, Japan","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084500947","display_name":"Don Joven Agravante","orcid":"https://orcid.org/0000-0002-9974-7635"},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Don Joven Agravante","raw_affiliation_strings":["IBM Research, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Tokyo, Japan","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107232188","display_name":"Tadanobu Inoue","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tadanobu Inoue","raw_affiliation_strings":["IBM Research, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Tokyo, Japan","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045206765","display_name":"Jayakorn Vongkulbhisal","orcid":"https://orcid.org/0000-0002-9764-7382"},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jayakorn Vongkulbhisal","raw_affiliation_strings":["IBM Research, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Tokyo, Japan","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101843778","display_name":"Asim Munawar","orcid":"https://orcid.org/0000-0002-9101-9545"},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Asim Munawar","raw_affiliation_strings":["IBM Research, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Tokyo, Japan","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013412274","display_name":"Ryuki Tachibana","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryuki Tachibana","raw_affiliation_strings":["IBM Research, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Tokyo, Japan","institution_ids":["https://openalex.org/I4210145865"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3163,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.889603,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3425","last_page":"3429"},"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":0.9994000196456909,"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":0.9962000250816345,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7983402013778687},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.6644601821899414},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5853342413902283},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5631111860275269},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.4857216477394104},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4802411198616028},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.47381889820098877},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45033177733421326},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4412946403026581},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3732697069644928},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12223127484321594}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7983402013778687},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.6644601821899414},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5853342413902283},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5631111860275269},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.4857216477394104},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4802411198616028},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.47381889820098877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45033177733421326},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4412946403026581},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3732697069644928},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12223127484321594},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413695","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W603908379","https://openalex.org/W1731081199","https://openalex.org/W1971920230","https://openalex.org/W2089800227","https://openalex.org/W2099471712","https://openalex.org/W2104094955","https://openalex.org/W2149900846","https://openalex.org/W2509065397","https://openalex.org/W2551990143","https://openalex.org/W2592109325","https://openalex.org/W2605102758","https://openalex.org/W2663904211","https://openalex.org/W2701869962","https://openalex.org/W2747805921","https://openalex.org/W2763188033","https://openalex.org/W2768802724","https://openalex.org/W2884822476","https://openalex.org/W2885782501","https://openalex.org/W2888842465","https://openalex.org/W2891627435","https://openalex.org/W2903040254","https://openalex.org/W2937324313","https://openalex.org/W2939036887","https://openalex.org/W2963073217","https://openalex.org/W2963107255","https://openalex.org/W2963873275","https://openalex.org/W2975836787","https://openalex.org/W3015469592","https://openalex.org/W3098357269","https://openalex.org/W3125848009","https://openalex.org/W4320013936","https://openalex.org/W6618372016","https://openalex.org/W6637618735","https://openalex.org/W6746090280","https://openalex.org/W6746249881","https://openalex.org/W6753511437","https://openalex.org/W6756604915"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W2900122540","https://openalex.org/W4240587264","https://openalex.org/W2043735059","https://openalex.org/W2041060376","https://openalex.org/W3119734852","https://openalex.org/W2011776247"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"have":[3],"recently":[4],"led":[5],"to":[6,25,41,54,61,78,87,92,126,137,150],"promising":[7],"results":[8],"for":[9,67],"the":[10,62,73,79,94,107,115,130,135],"task":[11,74],"of":[12,22,29,82],"multiple":[13],"sound":[14],"source":[15],"localization.":[16],"Yet,":[17],"they":[18],"require":[19],"a":[20,27,121],"lot":[21],"training":[23,45],"data":[24,52,141],"cover":[26],"variety":[28],"acoustic":[30,39],"conditions":[31],"and":[32,98],"micro-phone":[33],"array":[34,70,145],"layouts.":[35,84],"One":[36],"can":[37],"leverage":[38],"simulators":[40],"inexpensively":[42],"generate":[43],"labeled":[44],"data.":[46,117],"However,":[47],"models":[48],"trained":[49,139],"on":[50],"synthetic":[51,97],"tend":[53],"perform":[55],"poorly":[56],"with":[57,140],"real-world":[58],"recordings":[59],"due":[60,77],"domain":[63],"mismatch.":[64],"Moreover,":[65],"learning":[66,90],"different":[68],"microphone":[69,144],"layouts":[71,146,152],"makes":[72],"more":[75],"complicated":[76],"infinite":[80],"number":[81],"possible":[83],"We":[85],"propose":[86,120],"use":[88],"adversarial":[89],"methods":[91],"close":[93],"gap":[95],"between":[96],"real":[99,116],"do-mains.":[100],"Our":[101],"novel":[102,122],"ensemble-discrimination":[103],"method":[104],"significantly":[105],"improves":[106],"localization":[108,131],"performance":[109],"without":[110],"requiring":[111],"any":[112],"label":[113],"from":[114,142],"Furthermore,":[118],"we":[119],"explicit":[123],"transformation":[124],"layer":[125],"be":[127,138],"embedded":[128],"in":[129],"architecture.":[132],"It":[133],"enables":[134],"model":[136],"specific":[143],"while":[147],"generalizing":[148],"well":[149],"unseen":[151],"during":[153],"inference.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}