{"id":"https://openalex.org/W2586642235","doi":"https://doi.org/10.1109/slt.2016.7846325","title":"Discriminative multiple sound source localization based on deep neural networks using independent location model","display_name":"Discriminative multiple sound source localization based on deep neural networks using independent location model","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2586642235","doi":"https://doi.org/10.1109/slt.2016.7846325","mag":"2586642235"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2016.7846325","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5018403421","display_name":"Ryu Takeda","orcid":"https://orcid.org/0009-0007-0518-6245"},"institutions":[{"id":"https://openalex.org/I4210138169","display_name":"Osaka Research Institute of Industrial Science and Technology","ror":"https://ror.org/03r38cy24","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210138169"]},{"id":"https://openalex.org/I98285908","display_name":"Osaka University","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryu Takeda","raw_affiliation_strings":["The Institute of Scientific and Industrial Research, Osaka University, Ibaraki, Osaka, Japan"],"affiliations":[{"raw_affiliation_string":"The Institute of Scientific and Industrial Research, Osaka University, Ibaraki, Osaka, Japan","institution_ids":["https://openalex.org/I4210138169","https://openalex.org/I98285908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049614400","display_name":"Kazunori Komatani","orcid":"https://orcid.org/0000-0002-6052-600X"},"institutions":[{"id":"https://openalex.org/I4210138169","display_name":"Osaka Research Institute of Industrial Science and Technology","ror":"https://ror.org/03r38cy24","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210138169"]},{"id":"https://openalex.org/I98285908","display_name":"Osaka University","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazunori Komatani","raw_affiliation_strings":["The Institute of Scientific and Industrial Research, Osaka University, Ibaraki, Osaka, Japan"],"affiliations":[{"raw_affiliation_string":"The Institute of Scientific and Industrial Research, Osaka University, Ibaraki, Osaka, Japan","institution_ids":["https://openalex.org/I4210138169","https://openalex.org/I98285908"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.986,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":89,"citation_normalized_percentile":{"value":0.935496,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"12","issue":null,"first_page":"603","last_page":"609"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9999,"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":0.9999,"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":0.996,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9951,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.76033115},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.47225088},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep Neural Networks","score":0.4238439}],"concepts":[{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.8409797},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.76033115},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.75572413},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6698505},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.613649},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6023209},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.5947195},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.50535184},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.47642693},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.47225088},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4238439},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.41273263},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4044507},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3930105},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3906554},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3195345},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14653486},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.136253},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09615421},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2016.7846325","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.75,"display_name":"Reduced inequalities"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":26,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1643236172","https://openalex.org/W1936750108","https://openalex.org/W1989000345","https://openalex.org/W1998924366","https://openalex.org/W2002146237","https://openalex.org/W2024365188","https://openalex.org/W2024897398","https://openalex.org/W2074134755","https://openalex.org/W2101856597","https://openalex.org/W2111879728","https://openalex.org/W2113638573","https://openalex.org/W2121065047","https://openalex.org/W2128131274","https://openalex.org/W2130058948","https://openalex.org/W2130912818","https://openalex.org/W2131474463","https://openalex.org/W2136172079","https://openalex.org/W2140571699","https://openalex.org/W2141427791","https://openalex.org/W2143027228","https://openalex.org/W2146502635","https://openalex.org/W2162654459","https://openalex.org/W2403149086","https://openalex.org/W2613718673","https://openalex.org/W639708223"],"related_works":["https://openalex.org/W4283160672","https://openalex.org/W4247536566","https://openalex.org/W4241418540","https://openalex.org/W3119814709","https://openalex.org/W2965546495","https://openalex.org/W2725786787","https://openalex.org/W2404647514","https://openalex.org/W2018477250","https://openalex.org/W1667647204","https://openalex.org/W1508895727"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,61,79,140,145],"training":[3,74,137],"method":[4,138,143],"for":[5,42,111,121],"multiple":[6],"sound":[7,25,88],"source":[8],"localization":[9,35],"(SSL)":[10],"based":[11,130],"on":[12,131],"deep":[13],"neural":[14],"networks":[15,18],"(DNNs).":[16],"Such":[17],"function":[19],"as":[20,91],"posterior":[21],"probability":[22],"estimator":[23],"of":[24,29,71,81,87,147,152],"location":[26,109],"in":[27,68,150],"terms":[28,151],"position":[30],"labels":[31,72],"and":[32,73,77,93,114],"achieve":[33],"high":[34],"correctness.":[36,154],"Since":[37],"the":[38,69,112,122,128],"previous":[39],"DNNs'":[40],"configuration":[41],"SSL":[43,129,142],"handles":[44],"one-sound-source":[45],"cases,":[46],"it":[47,56],"should":[48],"be":[49],"extended":[50],"to":[51,54,57],"multiple-sound-source":[52],"cases":[53],"apply":[55],"real":[58],"environments.":[59],"However,":[60],"na\u00efve":[62],"design":[63],"causes":[64],"1)":[65],"an":[66,107,115],"increase":[67],"number":[70],"data":[75],"patterns":[76],"2)":[78],"lack":[80],"label":[82],"consistency":[83],"across":[84],"different":[85],"numbers":[86],"sources,":[89],"such":[90],"one":[92],"two-or-more-sound":[94],"cases.":[95],"These":[96],"two":[97],"problems":[98],"were":[99],"solved":[100],"using":[101],"our":[102,135],"proposed":[103,136],"method,":[104],"which":[105],"involves":[106],"independent":[108],"model":[110],"former":[113],"block-wise":[116],"consistent":[117],"labeling":[118],"with":[119],"ordering":[120],"latter.":[123],"Our":[124],"experiments":[125],"indicated":[126],"that":[127],"DNNs":[132],"trained":[133],"by":[134,144],"out-performed":[139],"conventional":[141],"maximum":[146],"18":[148],"points":[149],"block-level":[153]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2586642235","counts_by_year":[{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":5}],"updated_date":"2025-01-08T10:36:49.906578","created_date":"2017-02-17"}