{"id":"https://openalex.org/W2903098622","doi":"https://doi.org/10.23919/eusipco.2018.8553461","title":"Deep Neural Networks for Joint Voice Activity Detection and Speaker Localization","display_name":"Deep Neural Networks for Joint Voice Activity Detection and Speaker Localization","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2903098622","doi":"https://doi.org/10.23919/eusipco.2018.8553461","mag":"2903098622"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco.2018.8553461","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2018.8553461","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 26th European Signal Processing Conference (EUSIPCO)","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/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":true,"raw_author_name":"Paolo Vecchiotti","raw_affiliation_strings":["Department of Information Engineering, Universit\u00e1 Politecnica delle Marche, Ancona, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Universit\u00e1 Politecnica delle Marche, Ancona, 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\u00e1 Politecnica delle Marche, Ancona, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Universit\u00e1 Politecnica delle Marche, Ancona, 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\u00e1 Politecnica delle Marche, Ancona, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Universit\u00e1 Politecnica delle Marche, Ancona, 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\u00e1 Politecnica delle Marche, Ancona, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Universit\u00e1 Politecnica delle Marche, Ancona, Italy","institution_ids":["https://openalex.org/I122534668"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5043834809"],"corresponding_institution_ids":["https://openalex.org/I122534668"],"apc_list":null,"apc_paid":null,"fwci":0.4954,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.65331831,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1567","last_page":"1571"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9991000294685364,"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":0.8124486207962036},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6884673833847046},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6367987394332886},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6333168148994446},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6162865161895752},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6076087951660156},{"id":"https://openalex.org/keywords/cascade","display_name":"Cascade","score":0.5674160718917847},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5142176151275635},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47342875599861145},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.452620267868042},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.44119447469711304},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.4176226258277893},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3418339490890503},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09678956866264343},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08654224872589111}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8124486207962036},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6884673833847046},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6367987394332886},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6333168148994446},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6162865161895752},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6076087951660156},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.5674160718917847},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5142176151275635},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47342875599861145},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.452620267868042},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.44119447469711304},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4176226258277893},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3418339490890503},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09678956866264343},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08654224872589111},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C42360764","wikidata":"https://www.wikidata.org/wiki/Q83588","display_name":"Chemical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco.2018.8553461","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2018.8553461","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 26th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1499000945","https://openalex.org/W1522301498","https://openalex.org/W2044063703","https://openalex.org/W2070504334","https://openalex.org/W2130357996","https://openalex.org/W2134871056","https://openalex.org/W2135131618","https://openalex.org/W2163343350","https://openalex.org/W2220333611","https://openalex.org/W2251255183","https://openalex.org/W2261950180","https://openalex.org/W2513836842","https://openalex.org/W2551314165","https://openalex.org/W2615100522","https://openalex.org/W2747805921","https://openalex.org/W2751926801","https://openalex.org/W2765962757","https://openalex.org/W2771922328","https://openalex.org/W2772734659","https://openalex.org/W2772736377","https://openalex.org/W2778159588","https://openalex.org/W2962708126","https://openalex.org/W2964121744","https://openalex.org/W6629907861","https://openalex.org/W6631190155","https://openalex.org/W6679816324","https://openalex.org/W6691326925","https://openalex.org/W6742846607"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2168417340","https://openalex.org/W4229451372"],"abstract_inverted_index":{"Detecting":[0],"the":[1,18,76,82,124,147,157,177,183,193,200],"presence":[2],"of":[3,43,61,68,126,167],"speakers":[4],"and":[5,32,63,96,109,133,199],"suitably":[6],"localize":[7],"them":[8],"in":[9,17,85,139,205],"indoor":[10],"environments":[11],"undoubtedly":[12],"represent":[13],"two":[14],"important":[15],"tasks":[16],"speech":[19,94,168,197],"processing":[20],"community.":[21],"Several":[22],"algorithms":[23],"have":[24,71],"been":[25,72],"proposed":[26,114,158],"for":[27,92],"Voice":[28],"Activity":[29],"Detection":[30],"(VAD)":[31],"Speaker":[33],"LOCalization":[34],"(SLOC)":[35],"so":[36],"far,":[37],"while":[38],"their":[39],"accomplishment":[40],"by":[41,66,123,191],"means":[42,67],"a":[44,88,119,127,151,163],"joint":[45,93,194],"integrated":[46],"model":[47,121,195],"has":[48],"not":[49],"received":[50],"much":[51],"attention.":[52],"In":[53],"particular,":[54],"no":[55],"studies":[56],"focused":[57],"on":[58,100],"cooperative":[59],"exploitation":[60],"VAD":[62,132],"SLOC":[64,203],"information":[65],"machine":[69],"learning":[70],"conducted,":[73],"up":[74],"to":[75,161,173,176],"authors'":[77,141],"knowledge.":[78],"That":[79],"is":[80,116,187],"why":[81],"authors":[83],"propose":[84],"this":[86],"work":[87],"data":[89],"driven":[90],"approach":[91],"detection":[95,170],"speaker":[97],"localization,":[98],"relying":[99],"Convolutional":[101],"Neural":[102],"Network":[103],"(CNN)":[104],"which":[105],"simultaneously":[106],"process":[107],"LogMel":[108],"GCC-PHAT":[110],"Patterns":[111],"features.":[112],"The":[113],"algorithm":[115],"compared":[117,175],"with":[118],"two-stage":[120],"composed":[122],"cascade":[125],"neural":[128,202],"network":[129],"(NN)":[130],"based":[131,136,180],"an":[134],"NN":[135,179],"SLOC,":[137],"discussed":[138],"previous":[140],"contributions.":[142],"Computer":[143],"simulations,":[144],"accomplished":[145],"against":[146],"DIRHA":[148],"dataset":[149],"addressing":[150],"multi-room":[152],"acoustic":[153],"environment,":[154],"show":[155],"that":[156],"method":[159],"allows":[160],"achieve":[162],"remarkable":[164],"relative":[165],"reduction":[166],"activity":[169],"error":[171],"equal":[172],"33%":[174],"original":[178],"VAD.":[181],"Moreover,":[182],"overall":[184],"localization":[185],"accuracy":[186],"improved":[188],"as":[189,196],"well,":[190],"employing":[192],"detector":[198],"standard":[201],"system":[204],"cascade.":[206]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}