{"id":"https://openalex.org/W2901404901","doi":"https://doi.org/10.21437/iberspeech.2018-48","title":"The Intelligent Voice System for the IberSPEECH-RTVE 2018 Speaker Diarization Challenge","display_name":"The Intelligent Voice System for the IberSPEECH-RTVE 2018 Speaker Diarization Challenge","publication_year":2018,"publication_date":"2018-11-19","ids":{"openalex":"https://openalex.org/W2901404901","doi":"https://doi.org/10.21437/iberspeech.2018-48","mag":"2901404901"},"language":"en","primary_location":{"id":"doi:10.21437/iberspeech.2018-48","is_oa":false,"landing_page_url":"https://doi.org/10.21437/iberspeech.2018-48","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":"preprint","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/A5003884748","display_name":"Abbas Khosravani","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Abbas Khosravani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044554092","display_name":"Cornelius Glackin","orcid":"https://orcid.org/0000-0001-5114-6403"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cornelius Glackin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076271433","display_name":"Naz\u0131m Dugan","orcid":"https://orcid.org/0000-0002-3620-6225"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nazim Dugan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054175637","display_name":"G\u00e9rard Chollet","orcid":"https://orcid.org/0000-0003-4245-146X"},"institutions":[{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4387153010","display_name":"T\u00e9l\u00e9com SudParis","ror":"https://ror.org/05xvk4r52","country_code":"FR","type":"education","lineage":["https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4387153010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"G\u00e9rard Chollet","raw_affiliation_strings":["ARMEDIA-SAMOVAR - ARMEDIA (TELECOM Sudparis\r\n 9 rue Charles Fourier\r\n 91011 EVRY - France)","TSP - EPH - D\u00e9partement Electronique et Physique (T\u00e9l\u00e9com SudParis - 9 rue Charles Fourier - 91011 \u00c9vry Cedex - France)","IP Paris - Institut Polytechnique de Paris (Route de Saclay, 91120 Palaiseau Cedex, France - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ARMEDIA-SAMOVAR - ARMEDIA (TELECOM Sudparis\r\n 9 rue Charles Fourier\r\n 91011 EVRY - France)","institution_ids":["https://openalex.org/I4387153010"]},{"raw_affiliation_string":"TSP - EPH - D\u00e9partement Electronique et Physique (T\u00e9l\u00e9com SudParis - 9 rue Charles Fourier - 91011 \u00c9vry Cedex - France)","institution_ids":["https://openalex.org/I4210145102","https://openalex.org/I4387153010"]},{"raw_affiliation_string":"IP Paris - Institut Polytechnique de Paris (Route de Saclay, 91120 Palaiseau Cedex, France - France)","institution_ids":["https://openalex.org/I4210145102"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012466886","display_name":"Nigel Cannings","orcid":"https://orcid.org/0000-0002-5279-3968"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nigel Cannings","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5003884748"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.169,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.6194132,"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":"231","last_page":"235"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.996999979019165,"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":0.9952999949455261,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.9507794380187988},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.783767580986023},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7205476760864258},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6986244916915894},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5937626957893372},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5904167294502258},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.576265811920166},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5407651662826538},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5193796753883362},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.46694910526275635},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40835580229759216},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08429533243179321},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07097411155700684}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9507794380187988},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.783767580986023},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7205476760864258},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6986244916915894},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5937626957893372},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5904167294502258},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.576265811920166},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5407651662826538},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5193796753883362},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.46694910526275635},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40835580229759216},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08429533243179321},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07097411155700684},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/iberspeech.2018-48","is_oa":false,"landing_page_url":"https://doi.org/10.21437/iberspeech.2018-48","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:HAL:hal-02287998v1","is_oa":false,"landing_page_url":"https://telecom-paris.hal.science/hal-02287998","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IberSPEECH 2018, Nov 2018, Barcelone, Spain. pp.231-235, ⟨10.21437/IberSPEECH.2018-48⟩","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1597208282","https://openalex.org/W1606894530","https://openalex.org/W2018642651","https://openalex.org/W2038101708","https://openalex.org/W2115599677","https://openalex.org/W2140807505","https://openalex.org/W2150769028","https://openalex.org/W2400584454","https://openalex.org/W2638067502","https://openalex.org/W2673722796","https://openalex.org/W2696967604","https://openalex.org/W2746241180","https://openalex.org/W2746574320","https://openalex.org/W2747238065","https://openalex.org/W2748488820","https://openalex.org/W3208240190"],"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/W1992908141","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,24,96,102,116,123],"Intelligent":[4],"Voice":[5],"(IV)":[6],"speaker":[7,13,20,31,34,54,75,83,97],"diarization":[8,14,21],"system":[9],"for":[10,57,86],"IberSPEECH-RTVE":[11],"2018":[12],"challenge.":[15],"We":[16,67,111],"developed":[17],"a":[18],"new":[19],"built":[22],"on":[23,62,71,115],"success":[25],"of":[26,104],"deep":[27,45],"neural":[28,46],"network":[29,47],"based":[30],"embeddings":[32,48,76],"in":[33],"verification":[35],"systems.":[36],"In":[37],"contrary":[38],"to":[39,77,94],"acoustic":[40],"features":[41],"such":[42],"as":[43,120,122],"MFCCs,":[44],"are":[49],"much":[50],"better":[51],"at":[52],"discerning":[53],"identities":[55],"especially":[56],"speech":[58],"acquired":[59],"without":[60],"constraint":[61],"recording":[63],"equipment":[64],"and":[65,81],"environment.":[66],"perform":[68],"spectral":[69],"clustering":[70],"our":[72],"proposed":[73],"CNNLSTM-based":[74],"find":[78],"homogeneous":[79],"segments":[80],"generate":[82],"log":[84],"likelihood":[85],"each":[87],"frame.":[88],"A":[89],"HMM":[90],"is":[91],"then":[92],"used":[93],"refine":[95],"posterior":[98],"probabilities":[99],"through":[100],"limiting":[101],"probability":[103],"switching":[105],"between":[106],"speakers":[107],"when":[108],"changing":[109],"frames.":[110],"present":[112],"results":[113],"obtained":[114],"development":[117],"set":[118,125],"(dev2)":[119],"well":[121],"evaluation":[124],"\u2026":[126]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-06T09:05:17.133730","created_date":"2025-10-10T00:00:00"}