{"id":"https://openalex.org/W1608667326","doi":"https://doi.org/10.21437/interspeech.2015-111","title":"Integrating online i-vector extractor with information bottleneck based speaker diarization system","display_name":"Integrating online i-vector extractor with information bottleneck based speaker diarization system","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W1608667326","doi":"https://doi.org/10.21437/interspeech.2015-111","mag":"1608667326"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-111","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://infoscience.epfl.ch/record/209082/files/Madikeri_INTERSPEECH2015_2015.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084521938","display_name":"Srikanth Madikeri","orcid":"https://orcid.org/0000-0002-4361-784X"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Srikanth Madikeri","raw_affiliation_strings":["Idiap Research Institute, Martigny-Combe, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny-Combe, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039529498","display_name":"Ivan Himawan","orcid":"https://orcid.org/0000-0003-3848-244X"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ivan Himawan","raw_affiliation_strings":["Idiap Research Institute, Martigny-Combe, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny-Combe, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076409146","display_name":"Petr Motl\u00ed\u010dek","orcid":"https://orcid.org/0000-0001-6467-1119"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Petr Motlicek","raw_affiliation_strings":["Idiap Research Institute, Martigny-Combe, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny-Combe, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027284390","display_name":"Marc Ferr\u00e0s","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Marc Ferras","raw_affiliation_strings":["IDIAP research institute"],"affiliations":[{"raw_affiliation_string":"IDIAP research institute","institution_ids":["https://openalex.org/I7495430"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.745,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":27,"citation_normalized_percentile":{"value":0.838954,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":92,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"3105","last_page":"3109"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998,"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":0.9998,"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":0.9951,"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":0.9933,"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":0.84540826},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.74241656},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.73276794},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6901124}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.84540826},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.77827036},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.74241656},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.73276794},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6993984},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6901124},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.65965915},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.58583903},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.45762336},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44828877},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44268686},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.33764255},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-111","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/209082","pdf_url":"https://infoscience.epfl.ch/record/209082/files/Madikeri_INTERSPEECH2015_2015.pdf","source":{"id":"https://openalex.org/S4306400488","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"http://publications.idiap.ch/index.php/publications/showcite/Madikeri_Idiap-RR-20-2015","pdf_url":"https://publications.idiap.ch/attachments/reports/2015/Madikeri_Idiap-RR-20-2015.pdf","source":{"id":"https://openalex.org/S4306400488","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/record/209102/files/Madikeri_Idiap-RR-20-2015.pdf","pdf_url":"https://infoscience.epfl.ch/record/209102/files/Madikeri_Idiap-RR-20-2015.pdf","source":{"id":"https://openalex.org/S4306400488","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/209082","pdf_url":"https://infoscience.epfl.ch/record/209082/files/Madikeri_INTERSPEECH2015_2015.pdf","source":{"id":"https://openalex.org/S4306400488","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":21,"referenced_works":["https://openalex.org/W142991516","https://openalex.org/W1524333225","https://openalex.org/W1595613095","https://openalex.org/W1787748203","https://openalex.org/W1873003601","https://openalex.org/W1996198360","https://openalex.org/W2015633636","https://openalex.org/W2079623482","https://openalex.org/W2081074144","https://openalex.org/W2098726438","https://openalex.org/W2106015547","https://openalex.org/W2106780157","https://openalex.org/W2119203697","https://openalex.org/W2121812409","https://openalex.org/W2150769028","https://openalex.org/W2153994037","https://openalex.org/W2156255174","https://openalex.org/W2289985966","https://openalex.org/W2338994564","https://openalex.org/W2400584454","https://openalex.org/W567546468"],"related_works":["https://openalex.org/W4247736853","https://openalex.org/W3119288895","https://openalex.org/W2206035908","https://openalex.org/W2185075503","https://openalex.org/W2175373321","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W1992908141","https://openalex.org/W1963976507","https://openalex.org/W1493012537"],"abstract_inverted_index":{"Conventional":[0],"approaches":[1],"to":[2,36,53,79,131],"speaker":[3,31,42],"diarization":[4,32,61,88],"use":[5],"short-term":[6],"features":[7,59,82,105,130],"such":[8,15,136],"as":[9,16,39,56,104,128,137],"Mel":[10],"Frequency":[11],"Cepstral":[12],"Co-efficients":[13],"(MFCC).Features":[14],"i-vectors":[17,29,64],"have":[18],"been":[19,34],"used":[20,55,103,127],"on":[21,110,143,157],"longer":[22],"segments":[23],"(minimum":[24],"2.5":[25],"seconds":[26],"of":[27,69,89,97,100,118,150],"speech).Using":[28],"for":[30,60,84],"has":[33],"shown":[35],"be":[37,54],"beneficial":[38],"it":[40],"models":[41,91],"information":[43],"explicitly.In":[44],"this":[45],"paper,":[46],"the":[47,107,111,121,144,158],"i-vector":[48],"modelling":[49],"technique":[50],"is":[51,155],"adapted":[52],"short":[57,67],"term":[58],"by":[62],"estimating":[63],"over":[65,94],"a":[66,76,95],"window":[68,96],"MFCCs.The":[70],"Information":[71],"Bottleneck":[72],"(IB)":[73],"approach":[74],"provides":[75],"convenient":[77],"platform":[78],"integrate":[80],"multiple":[81],"together":[83],"fast":[85],"and":[86,102,139],"accurate":[87],"speech.Speaker":[90],"are":[92,126,141],"estimated":[93],"10":[98],"frames":[99],"speech":[101],"in":[106,120,152],"IB":[108],"system.Experiments":[109],"NIST":[112],"RT":[113,159],"datasets":[114],"show":[115],"absolute":[116,153],"improvements":[117],"3.9%":[119],"best":[122,146],"case":[123,147],"when":[124],"ivectors":[125],"auxiliary":[129],"MFCC.Further,":[132],"discriminative":[133],"training":[134],"algorithms":[135],"LDA":[138],"PLDA":[140],"applied":[142],"i-vectors.A":[145],"performance":[148],"improvement":[149],"5%":[151],"terms":[154],"obtained":[156],"datasets.":[160]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W1608667326","counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":3}],"updated_date":"2025-04-20T23:29:15.681587","created_date":"2016-06-24"}