{"id":"https://openalex.org/W2901049122","doi":"https://doi.org/10.21437/iberspeech.2018-40","title":"UPC Multimodal Speaker Diarization System for the 2018 Albayzin Challenge","display_name":"UPC Multimodal Speaker Diarization System for the 2018 Albayzin Challenge","publication_year":2018,"publication_date":"2018-11-19","ids":{"openalex":"https://openalex.org/W2901049122","doi":"https://doi.org/10.21437/iberspeech.2018-40","mag":"2901049122"},"language":"en","primary_location":{"id":"doi:10.21437/iberspeech.2018-40","is_oa":false,"landing_page_url":"https://doi.org/10.21437/iberspeech.2018-40","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IberSPEECH 2018","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/2117/127821","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018737231","display_name":"Miquel \u00c0ngel India Massana","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miquel Angel India Massana","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077611654","display_name":"Itziar Sagastiberri","orcid":"https://orcid.org/0000-0002-6442-9178"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Itziar Sagastiberri","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Catalunya (UPC)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Catalunya (UPC)","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042702363","display_name":"Pon\u00e7 Palau","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pon\u00e7 Palau","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016347476","display_name":"Elisa Sayrol","orcid":null},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Elisa Sayrol","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Catalunya (UPC)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Catalunya (UPC)","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023556571","display_name":"Josep Ramon Morros","orcid":"https://orcid.org/0000-0002-1395-487X"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Josep Ramon Morros","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Catalunya (UPC)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Catalunya (UPC)","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025633053","display_name":"Javier Hernando","orcid":"https://orcid.org/0000-0002-1730-8154"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Javier Hernando","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Catalunya (UPC)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Catalunya (UPC)","institution_ids":["https://openalex.org/I9617848"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1663,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.47774229,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"199","last_page":"203"},"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/T11448","display_name":"Face recognition and analysis","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9980999827384949,"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/computer-science","display_name":"Computer science","score":0.7547845840454102},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7522482872009277},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6301840543746948},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.6123422384262085},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.6112836003303528},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5546591281890869},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5432322025299072},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.524566650390625},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.47120732069015503},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.46939510107040405},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4343612492084503},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41389167308807373},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4119541049003601}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7547845840454102},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7522482872009277},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6301840543746948},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.6123422384262085},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.6112836003303528},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5546591281890869},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5432322025299072},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.524566650390625},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.47120732069015503},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.46939510107040405},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4343612492084503},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41389167308807373},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4119541049003601},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/iberspeech.2018-40","is_oa":false,"landing_page_url":"https://doi.org/10.21437/iberspeech.2018-40","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IberSPEECH 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:upcommons.upc.edu:2117/127821","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/127821","pdf_url":null,"source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:upcommons.upc.edu:2117/127821","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/127821","pdf_url":null,"source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2709078255","display_name":null,"funder_award_id":"TEC2016-75976-R","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G3375958958","display_name":null,"funder_award_id":"TEC2015-69266-P","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"}],"funders":[{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2097470427","https://openalex.org/W2115252128","https://openalex.org/W2118877769","https://openalex.org/W2130103520","https://openalex.org/W2150769028","https://openalex.org/W2161969291","https://openalex.org/W2194775991","https://openalex.org/W2293867557","https://openalex.org/W2404921859","https://openalex.org/W2406500670","https://openalex.org/W2808631503","https://openalex.org/W2917367398","https://openalex.org/W3040777582","https://openalex.org/W3099206234"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"This":[0,18],"paper":[1],"presents":[2],"the":[3,8,14,24,27,31,64,90,96,111,129,147,155,162,174,178,181,190],"UPC":[4],"system":[5,186],"proposed":[6,185],"for":[7,158],"Multimodal":[9],"Speaker":[10],"Diarization":[11],"task":[12],"of":[13,66,161,164,180],"2018":[15],"Albayzin":[16],"Challenge.":[17],"approach":[19],"works":[20],"by":[21,42,103,153],"processing":[22],"individually":[23],"speech":[25,32,80],"and":[26,69],"image":[28],"signal.":[29],"In":[30],"domain,":[33],"speaker":[34,84],"diarization":[35],"is":[36,55,75,120,151,171,187],"performed":[37],"using":[38,86,122,134],"identity":[39],"embeddings":[40],"created":[41],"a":[43,99,104,117,123,135],"triplet":[44,53,138],"loss":[45,61,139],"DNN":[46,54],"that":[47,62,165],"uses":[48],"i-vectors":[49],"as":[50],"input.":[51],"The":[52,184],"trained":[56,133],"with":[57,82,173],"an":[58],"additional":[59],"regularization":[60],"minimizes":[63],"variance":[65],"both":[67],"positive":[68],"negative":[70],"distances.":[71],"A":[72],"sliding":[73],"windows":[74],"then":[76],"used":[77,109],"to":[78],"compare":[79],"segments":[81],"enrollment":[83,182],"targets":[85],"cosine":[87],"distance":[88],"between":[89],"embeddings.":[91],"To":[92],"detect":[93],"identities":[94],"from":[95,141,177],"face":[97,100,105,116,148],"modality,":[98],"detector":[101],"followed":[102],"tracker":[106],"has":[107],"been":[108],"on":[110,128,189],"videos.":[112],"For":[113,144],"each":[114,145,159],"cropped":[115],"feature":[118,149,169],"vector":[119,150,170],"obtained":[121,152,157],"Deep":[124],"Neural":[125],"Network":[126],"based":[127],"ResNet":[130],"34":[131],"architecture,":[132],"metric":[136],"learning":[137],"(available":[140],"dlib":[142],"library).":[143],"track":[146],"averaging":[154],"features":[156,175],"one":[160],"frames":[163],"track.":[166],"Then,":[167],"this":[168],"compared":[172],"extracted":[176],"images":[179],"identities.":[183],"evaluated":[188],"RTVE2018":[191],"database.":[192]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
