{"id":"https://openalex.org/W2975836787","doi":"https://doi.org/10.1109/mmsp.2019.8901685","title":"Learning Multiple Sound Source 2D Localization","display_name":"Learning Multiple Sound Source 2D Localization","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W2975836787","doi":"https://doi.org/10.1109/mmsp.2019.8901685","mag":"2975836787"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp.2019.8901685","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2019.8901685","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 21st International Workshop on Multimedia Signal Processing (MMSP)","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/I190752583","display_name":"ParisTech","ror":"https://ror.org/05c2qg481","country_code":"FR","type":"education","lineage":["https://openalex.org/I190752583"]},{"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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Guillaume Le Moing","raw_affiliation_strings":["MINES ParisTech - PSL Research University,Paris,France","MINES ParisTech - PSL Research University, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MINES ParisTech - PSL Research University,Paris,France","institution_ids":["https://openalex.org/I2746051580"]},{"raw_affiliation_string":"MINES ParisTech - PSL Research University, Paris, France","institution_ids":["https://openalex.org/I2746051580","https://openalex.org/I190752583"]}]},{"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","IBM Research, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research,Tokyo,Japan","institution_ids":["https://openalex.org/I4210145865"]},{"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","IBM Research, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research,Tokyo,Japan","institution_ids":["https://openalex.org/I4210145865"]},{"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","IBM Research, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research,Tokyo,Japan","institution_ids":["https://openalex.org/I4210145865"]},{"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","IBM Research, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research,Tokyo,Japan","institution_ids":["https://openalex.org/I4210145865"]},{"raw_affiliation_string":"IBM Research, Tokyo, Japan","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"middle","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","IBM Research, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research,Tokyo,Japan","institution_ids":["https://openalex.org/I4210145865"]},{"raw_affiliation_string":"IBM Research, Tokyo, Japan","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"last","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","IBM Research, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research,Tokyo,Japan","institution_ids":["https://openalex.org/I4210145865"]},{"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":0.8345,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.73601558,"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":"1","last_page":"6"},"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":0.9988999962806702,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.995199978351593,"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/acoustic-source-localization","display_name":"Acoustic source localization","score":0.7672631740570068},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.764427900314331},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5920222401618958},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5647947788238525},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5532941222190857},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5496467351913452},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5061632990837097},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5026769638061523},{"id":"https://openalex.org/keywords/cartesian-coordinate-system","display_name":"Cartesian coordinate system","score":0.46074071526527405},{"id":"https://openalex.org/keywords/sound-localization","display_name":"Sound localization","score":0.456235408782959},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.4218958020210266},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.42097195982933044},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3288730978965759},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26379328966140747},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09832552075386047},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09049820899963379}],"concepts":[{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.7672631740570068},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.764427900314331},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5920222401618958},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5647947788238525},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5532941222190857},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5496467351913452},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5061632990837097},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5026769638061523},{"id":"https://openalex.org/C16038011","wikidata":"https://www.wikidata.org/wiki/Q62912","display_name":"Cartesian coordinate system","level":2,"score":0.46074071526527405},{"id":"https://openalex.org/C68236139","wikidata":"https://www.wikidata.org/wiki/Q765652","display_name":"Sound localization","level":2,"score":0.456235408782959},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.4218958020210266},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.42097195982933044},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3288730978965759},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26379328966140747},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09832552075386047},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09049820899963379},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp.2019.8901685","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2019.8901685","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 21st International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2010080563","https://openalex.org/W2149900846","https://openalex.org/W2551990143","https://openalex.org/W2586642235","https://openalex.org/W2747805921","https://openalex.org/W2763188033","https://openalex.org/W2768802724","https://openalex.org/W2771922328","https://openalex.org/W2772736377","https://openalex.org/W2810087991","https://openalex.org/W2810934215","https://openalex.org/W2884822476","https://openalex.org/W2888842465","https://openalex.org/W2903498065","https://openalex.org/W2963037989","https://openalex.org/W2964342924","https://openalex.org/W3105684258","https://openalex.org/W3125848009","https://openalex.org/W6746576432"],"related_works":["https://openalex.org/W3011070339","https://openalex.org/W2098651198","https://openalex.org/W2108013559","https://openalex.org/W2288611238","https://openalex.org/W1485388545","https://openalex.org/W1981446207","https://openalex.org/W2349923422","https://openalex.org/W2998173332","https://openalex.org/W2317500761","https://openalex.org/W3008382217"],"abstract_inverted_index":{"In":[0,55],"this":[1,38,113],"paper,":[2],"we":[3,16,40,57],"propose":[4,46,59],"novel":[5,61],"deep":[6],"learning":[7],"based":[8],"algorithms":[9],"for":[10,112],"multiple":[11,25,34,76],"sound":[12,26],"source":[13,77],"localization.":[14],"Specifically,":[15],"aim":[17],"to":[18,51,82],"find":[19],"the":[20,53,66,108],"2D":[21],"Cartesian":[22],"coordinates":[23],"of":[24],"sources":[27],"in":[28],"an":[29,42],"enclosed":[30],"environment":[31],"by":[32],"using":[33],"microphone":[35],"arrays.":[36],"To":[37],"end,":[39],"use":[41],"encoding-decoding":[43],"architecture":[44],"and":[45,84,96],"two":[47,60],"improvements":[48],"on":[49,74,93],"it":[50],"accomplish":[52],"task.":[54],"addition,":[56],"also":[58],"localization":[62,87],"representations":[63],"which":[64,79],"increase":[65],"accuracy.":[67],"Lastly,":[68],"new":[69],"metrics":[70],"are":[71],"developed":[72],"relying":[73],"resolution-based":[75],"association":[78],"enables":[80],"us":[81],"evaluate":[83],"compare":[85],"different":[86],"approaches.":[88],"We":[89],"tested":[90],"our":[91,104],"method":[92,105],"both":[94],"synthetic":[95],"real":[97],"world":[98],"data.":[99],"The":[100],"results":[101],"show":[102],"that":[103],"improves":[106],"upon":[107],"previous":[109],"baseline":[110],"approach":[111],"problem.":[114]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
