{"id":"https://openalex.org/W2772734659","doi":"https://doi.org/10.1016/j.csl.2017.12.002","title":"Localizing speakers in multiple rooms by using Deep Neural Networks","display_name":"Localizing speakers in multiple rooms by using Deep Neural Networks","publication_year":2017,"publication_date":"2017-12-08","ids":{"openalex":"https://openalex.org/W2772734659","doi":"https://doi.org/10.1016/j.csl.2017.12.002","mag":"2772734659"},"language":"en","primary_location":{"id":"doi:10.1016/j.csl.2017.12.002","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.csl.2017.12.002","pdf_url":null,"source":{"id":"https://openalex.org/S91252481","display_name":"Computer Speech & Language","issn_l":"0885-2308","issn":["0885-2308","1095-8363"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Speech & Language","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.csl.2017.12.002","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009982837","display_name":"Fabio Vesperini","orcid":"https://orcid.org/0000-0001-7748-5454"},"institutions":[{"id":"https://openalex.org/I122534668","display_name":"Marche Polytechnic University","ror":"https://ror.org/00x69rs40","country_code":"IT","type":"education","lineage":["https://openalex.org/I122534668"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Fabio Vesperini","raw_affiliation_strings":["Department of Information Engineering, Universit\u00e0 Politecnica delle Marche, Via Brecce Bianche, Ancona 60131, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Universit\u00e0 Politecnica delle Marche, Via Brecce Bianche, Ancona 60131, Italy","institution_ids":["https://openalex.org/I122534668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043834809","display_name":"Paolo Vecchiotti","orcid":null},"institutions":[{"id":"https://openalex.org/I122534668","display_name":"Marche Polytechnic University","ror":"https://ror.org/00x69rs40","country_code":"IT","type":"education","lineage":["https://openalex.org/I122534668"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paolo Vecchiotti","raw_affiliation_strings":["Department of Information Engineering, Universit\u00e0 Politecnica delle Marche, Via Brecce Bianche, Ancona 60131, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Universit\u00e0 Politecnica delle Marche, Via Brecce Bianche, Ancona 60131, Italy","institution_ids":["https://openalex.org/I122534668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004777557","display_name":"Emanuele Principi","orcid":"https://orcid.org/0000-0002-2835-7277"},"institutions":[{"id":"https://openalex.org/I122534668","display_name":"Marche Polytechnic University","ror":"https://ror.org/00x69rs40","country_code":"IT","type":"education","lineage":["https://openalex.org/I122534668"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Emanuele Principi","raw_affiliation_strings":["Department of Information Engineering, Universit\u00e0 Politecnica delle Marche, Via Brecce Bianche, Ancona 60131, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Universit\u00e0 Politecnica delle Marche, Via Brecce Bianche, Ancona 60131, Italy","institution_ids":["https://openalex.org/I122534668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034253968","display_name":"Stefano Squartini","orcid":"https://orcid.org/0000-0001-9374-0128"},"institutions":[{"id":"https://openalex.org/I122534668","display_name":"Marche Polytechnic University","ror":"https://ror.org/00x69rs40","country_code":"IT","type":"education","lineage":["https://openalex.org/I122534668"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Stefano Squartini","raw_affiliation_strings":["Department of Information Engineering, Universit\u00e0 Politecnica delle Marche, Via Brecce Bianche, Ancona 60131, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Universit\u00e0 Politecnica delle Marche, Via Brecce Bianche, Ancona 60131, Italy","institution_ids":["https://openalex.org/I122534668"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004758092","display_name":"Francesco Piazza","orcid":"https://orcid.org/0000-0003-0205-3790"},"institutions":[{"id":"https://openalex.org/I122534668","display_name":"Marche Polytechnic University","ror":"https://ror.org/00x69rs40","country_code":"IT","type":"education","lineage":["https://openalex.org/I122534668"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco Piazza","raw_affiliation_strings":["Department of Information Engineering, Universit\u00e0 Politecnica delle Marche, Via Brecce Bianche, Ancona 60131, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Universit\u00e0 Politecnica delle Marche, Via Brecce Bianche, Ancona 60131, Italy","institution_ids":["https://openalex.org/I122534668"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5009982837"],"corresponding_institution_ids":["https://openalex.org/I122534668"],"apc_list":{"value":3400,"currency":"USD","value_usd":3400},"apc_paid":{"value":3400,"currency":"USD","value_usd":3400},"fwci":3.9961,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.94515842,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"49","issue":null,"first_page":"83","last_page":"106"},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9994000196456909,"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":0.9991000294685364,"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/computer-science","display_name":"Computer science","score":0.844589114189148},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.6489953398704529},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6189522743225098},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5926730632781982},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.5802751779556274},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5523409247398376},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5290486216545105},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.490658164024353},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.48811396956443787},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47317010164260864},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4726499617099762},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4579031467437744},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38497108221054077},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08433470129966736},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07832473516464233}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.844589114189148},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.6489953398704529},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6189522743225098},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5926730632781982},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.5802751779556274},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5523409247398376},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5290486216545105},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.490658164024353},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.48811396956443787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47317010164260864},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4726499617099762},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4579031467437744},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38497108221054077},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08433470129966736},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07832473516464233},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1016/j.csl.2017.12.002","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.csl.2017.12.002","pdf_url":null,"source":{"id":"https://openalex.org/S91252481","display_name":"Computer Speech & Language","issn_l":"0885-2308","issn":["0885-2308","1095-8363"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Speech & Language","raw_type":"journal-article"},{"id":"pmh:oai:iris.univpm.it:11566/252452","is_oa":false,"landing_page_url":"http://hdl.handle.net/11566/252452","pdf_url":null,"source":{"id":"https://openalex.org/S4306402571","display_name":"Universit\u00e0 Politecnica delle Marche (Universit\u00e0 Politecnica delle Marche)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122534668","host_organization_name":"Marche Polytechnic University","host_organization_lineage":["https://openalex.org/I122534668"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1016/j.csl.2017.12.002","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.csl.2017.12.002","pdf_url":null,"source":{"id":"https://openalex.org/S91252481","display_name":"Computer Speech & Language","issn_l":"0885-2308","issn":["0885-2308","1095-8363"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Speech & Language","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":91,"referenced_works":["https://openalex.org/W102482883","https://openalex.org/W1494037697","https://openalex.org/W1498436455","https://openalex.org/W1499000945","https://openalex.org/W1555217905","https://openalex.org/W1603075283","https://openalex.org/W1612048585","https://openalex.org/W1648602279","https://openalex.org/W1665214252","https://openalex.org/W1794286910","https://openalex.org/W1968438204","https://openalex.org/W1972873435","https://openalex.org/W1976178451","https://openalex.org/W1991742273","https://openalex.org/W1997137108","https://openalex.org/W2018383168","https://openalex.org/W2020107464","https://openalex.org/W2029625155","https://openalex.org/W2034040413","https://openalex.org/W2046317813","https://openalex.org/W2059203007","https://openalex.org/W2064675550","https://openalex.org/W2067518534","https://openalex.org/W2078528333","https://openalex.org/W2102266918","https://openalex.org/W2103519107","https://openalex.org/W2106925337","https://openalex.org/W2108905239","https://openalex.org/W2113638573","https://openalex.org/W2116101591","https://openalex.org/W2119932130","https://openalex.org/W2121684290","https://openalex.org/W2128847674","https://openalex.org/W2130357996","https://openalex.org/W2137185369","https://openalex.org/W2137867936","https://openalex.org/W2137983211","https://openalex.org/W2144354855","https://openalex.org/W2165698076","https://openalex.org/W2168221202","https://openalex.org/W2220333611","https://openalex.org/W2251255183","https://openalex.org/W2395947971","https://openalex.org/W2403149086","https://openalex.org/W2405014675","https://openalex.org/W2478526619","https://openalex.org/W2529065799","https://openalex.org/W2551314165","https://openalex.org/W2551990143","https://openalex.org/W2559997609","https://openalex.org/W2586642235","https://openalex.org/W2588917688","https://openalex.org/W2591443932","https://openalex.org/W2747805921","https://openalex.org/W2751926801","https://openalex.org/W2915722758","https://openalex.org/W2949117887","https://openalex.org/W3142707146","https://openalex.org/W3143835353","https://openalex.org/W3146803896","https://openalex.org/W4206633762","https://openalex.org/W4242446209","https://openalex.org/W6629457345","https://openalex.org/W6629907861","https://openalex.org/W6631190155","https://openalex.org/W6633442889","https://openalex.org/W6636126089","https://openalex.org/W6636327707","https://openalex.org/W6636810956","https://openalex.org/W6637242042","https://openalex.org/W6638667902","https://openalex.org/W6644159953","https://openalex.org/W6648110524","https://openalex.org/W6656954150","https://openalex.org/W6665546210","https://openalex.org/W6677062644","https://openalex.org/W6677696249","https://openalex.org/W6678162382","https://openalex.org/W6679157625","https://openalex.org/W6679160091","https://openalex.org/W6680448475","https://openalex.org/W6688755582","https://openalex.org/W6691326925","https://openalex.org/W6711938144","https://openalex.org/W6712697115","https://openalex.org/W6729810262","https://openalex.org/W6730135816","https://openalex.org/W6733276319","https://openalex.org/W6742846607","https://openalex.org/W6808122541","https://openalex.org/W6808848468"],"related_works":["https://openalex.org/W2076543106","https://openalex.org/W4322009192","https://openalex.org/W3192962470","https://openalex.org/W4320483926","https://openalex.org/W2019891950","https://openalex.org/W2085842814","https://openalex.org/W4286643620","https://openalex.org/W2523437662","https://openalex.org/W2559793074","https://openalex.org/W4387048144"],"abstract_inverted_index":{"In":[0,18,102,150],"the":[1,14,44,52,55,69,87,92,100,112,124,134,152,174,180,188,193,205,208,216,221,247,250],"field":[2],"of":[3,115,133,166,204,232],"human":[4],"speech":[5],"capturing":[6],"systems,":[7],"a":[8,21,104],"fundamental":[9],"role":[10],"is":[11,32,48,108,118,129],"played":[12],"by":[13,51,91,120,131,140],"source":[15],"localization":[16,157,197,227],"algorithms.":[17],"this":[19],"paper":[20],"Speaker":[22,184],"Localization":[23,185],"algorithm":[24,57,128,213],"(SLOC)":[25],"based":[26],"on":[27,220],"Deep":[28],"Neural":[29,76],"Networks":[30,77],"(DNN)":[31],"evaluated":[33,219],"and":[34,74,143,187,242,249],"compared":[35],"with":[36],"state-of-the":[37],"art":[38],"approaches.":[39],"The":[40,127],"speaker":[41,156,196],"position":[42],"in":[43,123,159,171,230],"room":[45,117],"under":[46],"analysis":[47,203],"directly":[49],"determined":[50],"DNN,":[53],"leading":[54],"proposed":[56,170,206],"to":[58,155,239],"be":[59],"fully":[60],"data-driven.":[61],"Two":[62],"different":[63],"neural":[64],"network":[65],"architectures":[66],"are":[67,94,178],"investigated:":[68],"Multi":[70],"Layer":[71],"Perceptron":[72],"(MLP)":[73],"Convolutional":[75],"(CNN).":[78],"GCC-PHAT":[79],"(Generalized":[80],"Cross":[81],"Correlation-PHAse":[82],"Transform)":[83],"Patterns,":[84],"computed":[85],"from":[86],"audio":[88],"signals":[89,146],"captured":[90],"microphone":[93,145],"used":[95],"as":[96],"input":[97],"features":[98],"for":[99,147,173,246],"DNN.":[101],"particular,":[103],"multi-room":[105],"case":[106],"study":[107],"dealt":[109],"with,":[110],"where":[111],"acoustic":[113],"scene":[114],"each":[116,148],"influenced":[119],"sounds":[121],"emitted":[122],"other":[125],"rooms.":[126,163],"tested":[130],"means":[132],"home":[135],"recorded":[136],"DIRHA":[137,222],"dataset,":[138,223],"characterized":[139],"multiple":[141],"wall":[142],"ceiling":[144],"room.":[149],"detail,":[151],"focus":[153],"goes":[154],"task":[158],"two":[160,168],"distinct":[161],"neighboring":[162],"As":[164],"term":[165],"comparison,":[167],"algorithms":[169],"literature":[172],"addressed":[175],"applicative":[176],"context":[177],"evaluated,":[179],"Crosspower":[181],"Spectrum":[182],"Phase":[183,194],"(CSP-SLOC)":[186],"Steered":[189],"Response":[190],"Power":[191],"using":[192],"Transform":[195],"(SRP-SLOC).":[198],"Besides":[199],"providing":[200,224],"an":[201,225],"extensive":[202],"method,":[207],"article":[209],"shows":[210],"how":[211],"DNN-based":[212],"significantly":[214],"outperforms":[215],"state-of-the-art":[217],"approaches":[218],"average":[226],"error,":[228],"expressed":[229],"terms":[231],"Root":[233],"Mean":[234],"Square":[235],"Error":[236],"(RMSE),":[237],"equal":[238],"324":[240],"mm":[241],"367":[243],"mm,":[244],"respectively,":[245],"Simulated":[248],"Real":[251],"subsets.":[252]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":7}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}