{"id":"https://openalex.org/W2949811029","doi":"https://doi.org/10.1109/taslp.2019.2915322","title":"Time-Contrastive Learning Based Deep Bottleneck Features for Text-Dependent Speaker Verification","display_name":"Time-Contrastive Learning Based Deep Bottleneck Features for Text-Dependent Speaker Verification","publication_year":2019,"publication_date":"2019-05-08","ids":{"openalex":"https://openalex.org/W2949811029","doi":"https://doi.org/10.1109/taslp.2019.2915322","mag":"2949811029"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2019.2915322","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2915322","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1905.04554","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002627413","display_name":"Achintya Kumar Sarkar","orcid":"https://orcid.org/0000-0002-9870-3980"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Achintya Kumar Sarkar","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Aalborg, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090108098","display_name":"Zheng\u2010Hua Tan","orcid":"https://orcid.org/0000-0001-6856-8928"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Zheng-Hua Tan","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Aalborg, Denmark"],"raw_orcid":"https://orcid.org/0000-0001-6856-8928","affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100662192","display_name":"Hao Tang","orcid":"https://orcid.org/0000-0002-6877-0226"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Tang","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020263683","display_name":"Suwon Shon","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suwon Shon","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Glass","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3885,"has_fulltext":true,"cited_by_count":32,"citation_normalized_percentile":{"value":0.93918102,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"27","issue":"8","first_page":"1267","last_page":"1279"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9990000128746033,"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":0.9977999925613403,"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":0.7160621285438538},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6956383585929871},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.6749459505081177},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49160274863243103},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4630596339702606},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44787129759788513},{"id":"https://openalex.org/keywords/contrastive-analysis","display_name":"Contrastive analysis","score":0.42889365553855896},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.2722206115722656},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17348405718803406}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7160621285438538},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6956383585929871},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.6749459505081177},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49160274863243103},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4630596339702606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44787129759788513},{"id":"https://openalex.org/C2777629044","wikidata":"https://www.wikidata.org/wiki/Q614959","display_name":"Contrastive analysis","level":2,"score":0.42889365553855896},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2722206115722656},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17348405718803406},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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":[{"id":"doi:10.1109/taslp.2019.2915322","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2915322","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1905.04554","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.04554","pdf_url":"https://arxiv.org/pdf/1905.04554","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:pure.atira.dk:publications/09344e3e-6545-4d0f-9684-2e0e5c217594","is_oa":true,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=85066748638&partnerID=8YFLogxK","pdf_url":"https://vbn.aau.dk/ws/files/316025783/Time_Contrastive_Learning_and_Phone_Discrimination_Based_Bottleneck_Features_for_Text_Dependent_Speaker_Verification.pdf","source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sarkar, A K, Tan, Z-H, Tang, H, Shon, S & Glass, J 2019, 'Time-Contrastive Learning Based Deep Bottleneck Features for Text-Dependent Speaker Verification', IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 27, no. 8, 8708955, pp. 1267-1279. https://doi.org/10.1109/TASLP.2019.2915322","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pure.atira.dk:openaire/09344e3e-6545-4d0f-9684-2e0e5c217594","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/09344e3e-6545-4d0f-9684-2e0e5c217594","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sarkar, A K, Tan, Z-H, Tang, H, Shon, S & Glass, J 2019, 'Time-Contrastive Learning Based Deep Bottleneck Features for Text-Dependent Speaker Verification', IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 27, no. 8, 8708955, pp. 1267-1279. https://doi.org/10.1109/TASLP.2019.2915322","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1905.04554","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.04554","pdf_url":"https://arxiv.org/pdf/1905.04554","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6800000071525574}],"awards":[{"id":"https://openalex.org/G6604660569","display_name":null,"funder_award_id":"1335-00162","funder_id":"https://openalex.org/F4320322928","funder_display_name":"Danmarks Frie Forskningsfond"}],"funders":[{"id":"https://openalex.org/F4320322928","display_name":"Danmarks Frie Forskningsfond","ror":"https://ror.org/02sptwz63"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":84,"referenced_works":["https://openalex.org/W35490052","https://openalex.org/W128628490","https://openalex.org/W1006777433","https://openalex.org/W1528954144","https://openalex.org/W1586405805","https://openalex.org/W1699156674","https://openalex.org/W1959608418","https://openalex.org/W1996512145","https://openalex.org/W2041823554","https://openalex.org/W2046056978","https://openalex.org/W2049633694","https://openalex.org/W2090861223","https://openalex.org/W2099471712","https://openalex.org/W2115008841","https://openalex.org/W2125534887","https://openalex.org/W2127218421","https://openalex.org/W2137075158","https://openalex.org/W2145038566","https://openalex.org/W2147768505","https://openalex.org/W2148091317","https://openalex.org/W2148154194","https://openalex.org/W2150769028","https://openalex.org/W2154278880","https://openalex.org/W2160815625","https://openalex.org/W2181607856","https://openalex.org/W2183016404","https://openalex.org/W2184045248","https://openalex.org/W2187089797","https://openalex.org/W2292259253","https://openalex.org/W2293234034","https://openalex.org/W2395069802","https://openalex.org/W2397236868","https://openalex.org/W2397474108","https://openalex.org/W2398971481","https://openalex.org/W2404292690","https://openalex.org/W2518048674","https://openalex.org/W2550599163","https://openalex.org/W2556930864","https://openalex.org/W2564171085","https://openalex.org/W2584329820","https://openalex.org/W2730658205","https://openalex.org/W2741480356","https://openalex.org/W2746457594","https://openalex.org/W2749173541","https://openalex.org/W2750822272","https://openalex.org/W2758785877","https://openalex.org/W2785415724","https://openalex.org/W2786902352","https://openalex.org/W2793459270","https://openalex.org/W2801581493","https://openalex.org/W2888897023","https://openalex.org/W2888911591","https://openalex.org/W2949811029","https://openalex.org/W2962778323","https://openalex.org/W2962914040","https://openalex.org/W2963618559","https://openalex.org/W2963762683","https://openalex.org/W3127686677","https://openalex.org/W3137695714","https://openalex.org/W3145164839","https://openalex.org/W4246070010","https://openalex.org/W4320013936","https://openalex.org/W4391602018","https://openalex.org/W4394643385","https://openalex.org/W6605273041","https://openalex.org/W6635268374","https://openalex.org/W6637411023","https://openalex.org/W6640963894","https://openalex.org/W6678914141","https://openalex.org/W6686045668","https://openalex.org/W6696984064","https://openalex.org/W6712094196","https://openalex.org/W6712467859","https://openalex.org/W6712618806","https://openalex.org/W6712620166","https://openalex.org/W6713629195","https://openalex.org/W6713634518","https://openalex.org/W6729977899","https://openalex.org/W6739720703","https://openalex.org/W6742802039","https://openalex.org/W6743680795","https://openalex.org/W6745117592","https://openalex.org/W6763485134","https://openalex.org/W6864613063"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W2748922771","https://openalex.org/W1987128138","https://openalex.org/W2140022733"],"abstract_inverted_index":{"There":[0],"are":[1,122,127,230],"a":[2,35,45,85,100,104,149],"number":[3,106],"of":[4,8,29,55,60,75,107,143,177,200,208,263,276,295],"studies":[5],"about":[6],"extraction":[7,90],"bottleneck":[9],"(BN)":[10],"features":[11,191,211,214,249,282],"from":[12,183,216],"deep":[13],"neural":[14],"networks":[15],"(DNNs)":[16],"trained":[17,129,173],"to":[18,51,116,130,138,154,158,285],"discriminate":[19,131],"speakers,":[20,219],"pass-phrases,":[21,220],"and":[22,69,119,212,228,250,255,278,298],"triphone":[23],"states":[24],"for":[25,58,79],"improving":[26],"the":[27,53,73,136,140,159,166,184,189,198,201,244,269,273,292],"performance":[28,199,257,275,294],"text-dependent":[30],"speaker":[31],"verification":[32],"(TD-SV).":[33],"However,":[34],"moderate":[36],"success":[37],"has":[38,72],"been":[39],"achieved.":[40],"A":[41],"recent":[42],"study":[43,291],"presented":[44],"time":[46],"contrastive":[47],"learning":[48],"(TCL)":[49],"concept":[50],"explore":[52],"non-stationarity":[54,67],"brain":[56,61],"signals":[57,64],"classification":[59],"states.":[62],"Speech":[63],"have":[65],"similar":[66],"property,":[68],"TCL":[70,86,203],"further":[71,290],"advantage":[74],"having":[76],"no":[77],"need":[78],"labeled":[80],"data.":[81],"We":[82,196,289],"therefore":[83],"present":[84],"based":[87],"BN":[88,204,213,253,266,281,299],"feature":[89,205],"method.":[91],"The":[92,170],"method":[93,271],"uniformly":[94],"partitions":[95],"each":[96],"speech":[97,133,175,236],"utterance":[98,114],"in":[99,112],"training":[101],"dataset":[102],"into":[103],"predefined":[105],"multi-frame":[108],"segments.":[109,160],"Each":[110],"segment":[111],"an":[113],"corresponds":[115],"one":[117],"class,":[118],"class":[120,156],"labels":[121,157,227],"shared":[123],"across":[124],"utterances.":[125],"DNNs":[126,217],"then":[128],"all":[132],"frames":[134],"among":[135],"classes":[137],"exploit":[139],"temporal":[141],"structure":[142],"speech.":[144],"In":[145],"addition,":[146],"we":[147],"propose":[148],"segment-based":[150],"unsupervised":[151],"clustering":[152,270],"algorithm":[153],"re-assign":[155],"TD-SV":[161,185,274,293],"experiments":[162],"were":[163,172,181],"conducted":[164],"on":[165,259],"RedDots":[167],"challenge":[168],"database.":[169],"TCL-DNNs":[171],"using":[174],"data":[176],"fixed":[178],"pass-phrases":[179],"that":[180,243],"excluded":[182],"evaluation":[186],"set,":[187],"so":[188],"learned":[190],"can":[192],"be":[193],"considered":[194],"phrase-independent.":[195],"compare":[197],"proposed":[202,245],"with":[206,261,283],"those":[207,262],"short-time":[209],"cepstral":[210,248,297],"extracted":[215],"discriminating":[218],"speaker+pass-phrase,":[221],"as":[222,224],"well":[223],"monophones":[225],"whose":[226],"boundaries":[229],"generated":[231],"by":[232],"three":[233],"different":[234],"automatic":[235],"recognition":[237],"(ASR)":[238],"systems.":[239],"Experimental":[240],"results":[241],"show":[242],"TCL-BN":[246,277],"outperforms":[247],"speaker+pass-phrase":[251],"discriminant":[252],"features,":[254],"its":[256],"is":[258],"par":[260],"ASR":[264,279],"derived":[265,280],"features.":[267,300],"Moreover,":[268],"improves":[272],"respect":[284],"their":[286],"standalone":[287],"counterparts.":[288],"fusing":[296]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2020-11-23T00:00:00"}