{"id":"https://openalex.org/W2963565199","doi":"https://doi.org/10.1109/apsipa.2017.8282024","title":"Deep speaker verification: Do we need end to end?","display_name":"Deep speaker verification: Do we need end to end?","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2963565199","doi":"https://doi.org/10.1109/apsipa.2017.8282024","mag":"2963565199"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2017.8282024","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282024","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100391494","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-6992-7950"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050701255","display_name":"Lantian Li","orcid":"https://orcid.org/0000-0003-4274-7930"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lantian Li","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056437232","display_name":"Zhiyuan Tang","orcid":"https://orcid.org/0000-0002-3786-7690"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Tang","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084318285","display_name":"Thomas Fang Zheng","orcid":"https://orcid.org/0000-0002-0249-4767"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Thomas Fang Zheng","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":null,"first_page":"177","last_page":"181"},"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/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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/T10860","display_name":"Speech 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/end-to-end-principle","display_name":"End-to-end principle","score":0.8607957363128662},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.789610743522644},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.693535327911377},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6875029802322388},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.6618391871452332},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.539030134677887},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45976370573043823},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45847585797309875},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4408855736255646},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4301791489124298},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40424537658691406},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32933950424194336},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.2204756736755371}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8607957363128662},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.789610743522644},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.693535327911377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6875029802322388},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.6618391871452332},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.539030134677887},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45976370573043823},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45847585797309875},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4408855736255646},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4301791489124298},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40424537658691406},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32933950424194336},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2204756736755371},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipa.2017.8282024","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282024","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1589137271","https://openalex.org/W1936725236","https://openalex.org/W2039057510","https://openalex.org/W2041823554","https://openalex.org/W2046056978","https://openalex.org/W2070176749","https://openalex.org/W2092160942","https://openalex.org/W2107638917","https://openalex.org/W2114925438","https://openalex.org/W2118393783","https://openalex.org/W2129244720","https://openalex.org/W2150769028","https://openalex.org/W2154278880","https://openalex.org/W2183016404","https://openalex.org/W2508048623","https://openalex.org/W2584329820","https://openalex.org/W2587150483","https://openalex.org/W2612434969","https://openalex.org/W2962832278","https://openalex.org/W2964058423","https://openalex.org/W3151878189","https://openalex.org/W6631362777","https://openalex.org/W6667507107","https://openalex.org/W6677884823","https://openalex.org/W6737575990","https://openalex.org/W6738831005"],"related_works":["https://openalex.org/W3179968364","https://openalex.org/W2972909277","https://openalex.org/W4380906377","https://openalex.org/W2587150483","https://openalex.org/W2972441390","https://openalex.org/W3108238911","https://openalex.org/W3198162144","https://openalex.org/W3048601286","https://openalex.org/W2972892026","https://openalex.org/W2965925734"],"abstract_inverted_index":{"End-to-end":[0],"learning":[1,47,77,135,160,174],"treats":[2],"the":[3,27,45,61,101,109,131,149,158,163,172],"entire":[4],"system":[5,21],"as":[6],"a":[7,20,75,82,138,145,168],"whole":[8],"adaptable":[9],"black":[10],"box,":[11],"which,":[12],"if":[13],"sufficient":[14],"data":[15,179],"are":[16,50],"available,":[17],"may":[18],"learn":[19],"that":[22,57,157],"works":[23],"very":[24],"well":[25,124],"for":[26,171],"target":[28],"task.":[29,141],"This":[30,166],"principle":[31],"has":[32],"recently":[33],"been":[34,114,123],"applied":[35],"to":[36,67,86,100,184],"several":[37],"prototype":[38],"research":[39],"on":[40,96,137,144],"speaker":[41],"verification":[42],"(SV),":[43],"where":[44],"feature":[46,70,76,134,159,173],"and":[48,79,117,133,152,180],"classifier":[49,84],"learned":[51],"together":[52],"with":[53,60,178],"an":[54],"objective":[55],"function":[56],"is":[58,69,167],"consistent":[59],"evaluation":[62],"metric.":[63],"An":[64],"opposite":[65],"approach":[66,161],"end-to-end":[68,132,164],"learning,":[71],"which":[72],"firstly":[73],"trains":[74],"model,":[78],"then":[80],"constructs":[81],"back-end":[83],"separately":[85],"perform":[87],"SV.":[88],"Recently,":[89],"both":[90],"approaches":[91,111,136],"achieved":[92],"significant":[93],"performance":[94],"gains":[95],"SV,":[97],"mainly":[98],"attributed":[99],"smart":[102],"utilization":[103],"of":[104],"deep":[105],"neural":[106],"networks.":[107],"However,":[108],"two":[110],"have":[112,121],"not":[113,122],"carefully":[115],"compared,":[116],"their":[118],"respective":[119],"advantages":[120],"discussed.":[125],"In":[126],"this":[127],"paper,":[128],"we":[129],"compare":[130],"text-independent":[139],"SV":[140],"Our":[142],"experiments":[143],"dataset":[146],"sampled":[147],"from":[148],"Fisher":[150],"database":[151],"involving":[153],"5,000":[154],"speakers":[155],"demonstrated":[156],"outperformed":[162],"approach.":[165],"strong":[169],"support":[170],"approach,":[175],"at":[176],"least":[177],"computation":[181],"resources":[182],"similar":[183],"ours.":[185]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}