{"id":"https://openalex.org/W2765334250","doi":"https://doi.org/10.23919/eusipco.2017.8081174","title":"Robust statistical processing of TDOA estimates for distant speaker diarization","display_name":"Robust statistical processing of TDOA estimates for distant speaker diarization","publication_year":2017,"publication_date":"2017-08-01","ids":{"openalex":"https://openalex.org/W2765334250","doi":"https://doi.org/10.23919/eusipco.2017.8081174","mag":"2765334250"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco.2017.8081174","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2017.8081174","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 25th 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/A5060097629","display_name":"Pablo Peso Parada","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pablo Peso Parada","raw_affiliation_strings":["Nuance Communication Inc., Burlington, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communication Inc., Burlington, USA","institution_ids":["https://openalex.org/I4210125787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108774400","display_name":"Dushyant Sharma","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dushyant Sharma","raw_affiliation_strings":["Nuance Communication Inc., Burlington, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communication Inc., Burlington, USA","institution_ids":["https://openalex.org/I4210125787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073284331","display_name":"Toon van Waterschoot","orcid":"https://orcid.org/0000-0002-6323-7350"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Toon van Waterschoot","raw_affiliation_strings":["ESAT-STADIUS, KU Leuven, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ESAT-STADIUS, KU Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016227729","display_name":"Patrick A. Naylor","orcid":"https://orcid.org/0000-0001-8546-8013"},"institutions":[{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Patrick A. Naylor","raw_affiliation_strings":["Imperial College, London, UK","Nuance Communication Inc., Burlington, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College, London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Nuance Communication Inc., Burlington, USA","institution_ids":["https://openalex.org/I4210125787"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5603,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66555207,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"382","issue":null,"first_page":"86","last_page":"90"},"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":0.9997000098228455,"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":0.9991999864578247,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/multilateration","display_name":"Multilateration","score":0.863131046295166},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7862069606781006},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7254683971405029},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.7174023985862732},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7044072151184082},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6492605209350586},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5145180225372314},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5049911141395569},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4643118381500244},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3728753328323364},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3203217685222626},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.10361790657043457},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07907167077064514}],"concepts":[{"id":"https://openalex.org/C104037064","wikidata":"https://www.wikidata.org/wiki/Q1640884","display_name":"Multilateration","level":3,"score":0.863131046295166},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7862069606781006},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7254683971405029},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7174023985862732},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7044072151184082},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6492605209350586},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5145180225372314},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5049911141395569},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4643118381500244},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3728753328323364},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3203217685222626},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.10361790657043457},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07907167077064514},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"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":2,"locations":[{"id":"doi:10.23919/eusipco.2017.8081174","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2017.8081174","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 25th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/609692","is_oa":false,"landing_page_url":"https://lirias.kuleuven.be/bitstream/123456789/609692/1/18-05.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EUSIPCO 2017, Kos, Greece, August 2017","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W138587896","https://openalex.org/W1499712254","https://openalex.org/W1506806321","https://openalex.org/W1562104307","https://openalex.org/W1963976507","https://openalex.org/W1965819578","https://openalex.org/W1991133427","https://openalex.org/W2005733316","https://openalex.org/W2009435671","https://openalex.org/W2046317813","https://openalex.org/W2081074144","https://openalex.org/W2096465424","https://openalex.org/W2117853077","https://openalex.org/W2118313846","https://openalex.org/W2129905273","https://openalex.org/W2130708324","https://openalex.org/W2138838039","https://openalex.org/W2148613904","https://openalex.org/W2159591770","https://openalex.org/W2168175751","https://openalex.org/W2170429532","https://openalex.org/W2171149164","https://openalex.org/W2181212125","https://openalex.org/W2290892587","https://openalex.org/W2297490458","https://openalex.org/W4232023503","https://openalex.org/W4233014035","https://openalex.org/W4296927107","https://openalex.org/W6629903641","https://openalex.org/W6677982106","https://openalex.org/W6697591417"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2188292175","https://openalex.org/W2385053527","https://openalex.org/W4386900535","https://openalex.org/W1197719229","https://openalex.org/W2381158726","https://openalex.org/W2552734076","https://openalex.org/W2162158162","https://openalex.org/W106647055","https://openalex.org/W1992796048"],"abstract_inverted_index":{"Speaker":[0],"diarization":[1,31],"systems":[2],"aim":[3],"to":[4,29,122,131],"segment":[5],"an":[6,132],"audio":[7],"signal":[8],"into":[9],"homogeneous":[10],"sections":[11],"with":[12,55,65],"only":[13,117],"one":[14],"active":[15],"speaker":[16,30,127],"and":[17,70,95,139],"answer":[18],"the":[19,66,83,86,93,142],"question":[20],"\"who":[21],"spoke":[22],"when?\"":[23],"We":[24,110],"present":[25],"a":[26,62],"novel":[27],"approach":[28],"exploiting":[32],"spatial":[33,118],"information":[34,101],"through":[35],"robust":[36,63],"statistical":[37],"modeling":[38,94],"of":[39,42,49,75,85,92],"Time":[40],"Difference":[41],"Arrival":[43],"(TDOA)":[44],"estimates":[45],"obtained":[46],"using":[47,136],"pairs":[48],"microphones.":[50],"The":[51],"TDOAs":[52],"are":[53],"modeled":[54],"Gaussian":[56],"Mixture":[57],"Models":[58],"(GMM)":[59],"trained":[60],"in":[61,126],"manner":[64],"expectation-conditional":[67],"maximization":[68],"algorithm":[69],"minorization-maximization":[71],"approach.":[72],"In":[73],"situations":[74],"multiple":[76],"microphone":[77,88,98],"deployment,":[78],"our":[79,113],"method":[80],"allows":[81],"for":[82,105],"selection":[84],"best":[87],"pair":[89],"as":[90],"part":[91],"supports":[96],"ad-hoc":[97],"placement.":[99],"Such":[100],"can":[102],"be":[103],"useful":[104],"subsequent":[106],"speech":[107],"processing":[108],"algorithms.":[109],"show":[111],"that":[112],"method,":[114],"which":[115],"uses":[116],"information,":[119],"achieves":[120],"up":[121],"36.1%":[123],"relative":[124],"reduction":[125],"error":[128],"time":[129],"compared":[130],"open":[133],"source":[134],"toolkit":[135],"TDOA":[137],"features":[138],"tested":[140],"on":[141],"NIST":[143],"RT05":[144],"multiparty":[145],"meeting":[146],"database.":[147]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}