{"id":"https://openalex.org/W2787051072","doi":"https://doi.org/10.1109/asru.2017.8268989","title":"End-to-end text-independent speaker verification with flexibility in utterance duration","display_name":"End-to-end text-independent speaker verification with flexibility in utterance duration","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2787051072","doi":"https://doi.org/10.1109/asru.2017.8268989","mag":"2787051072"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2017.8268989","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268989","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5005304261","display_name":"Chunlei Zhang","orcid":"https://orcid.org/0000-0002-3851-2357"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chunlei Zhang","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, TX","Microsoft Corporation, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, TX","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084879161","display_name":"Kazuhito Koishida","orcid":"https://orcid.org/0000-0002-3111-5375"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kazuhito Koishida","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"584","last_page":"590"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9980000257492065,"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":0.7272793054580688},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.688834011554718},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6108765602111816},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.5475209951400757},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.5063024759292603},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.48532456159591675},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42438939213752747},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3368898630142212},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28122013807296753},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15871760249137878}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7272793054580688},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.688834011554718},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6108765602111816},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.5475209951400757},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.5063024759292603},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.48532456159591675},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42438939213752747},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3368898630142212},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28122013807296753},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15871760249137878},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2017.8268989","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268989","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W2039057510","https://openalex.org/W2041823554","https://openalex.org/W2046056978","https://openalex.org/W2057888214","https://openalex.org/W2064364374","https://openalex.org/W2096733369","https://openalex.org/W2107638917","https://openalex.org/W2114925438","https://openalex.org/W2143694533","https://openalex.org/W2147147599","https://openalex.org/W2150769028","https://openalex.org/W2159736522","https://openalex.org/W2179352600","https://openalex.org/W2319316830","https://openalex.org/W2396385162","https://openalex.org/W2405524873","https://openalex.org/W2406366455","https://openalex.org/W2519781924","https://openalex.org/W2520774990","https://openalex.org/W2576165910","https://openalex.org/W2584329820","https://openalex.org/W2587150483","https://openalex.org/W2747238065","https://openalex.org/W2953309350","https://openalex.org/W2963702081","https://openalex.org/W2964228006","https://openalex.org/W3099206234","https://openalex.org/W4234330420","https://openalex.org/W6631362777","https://openalex.org/W6676338569","https://openalex.org/W6711901354","https://openalex.org/W6726946684","https://openalex.org/W6732884072"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W147410782","https://openalex.org/W3022252430","https://openalex.org/W4287804464","https://openalex.org/W3103989898","https://openalex.org/W3211292372","https://openalex.org/W803346624"],"abstract_inverted_index":{"We":[0],"continue":[1],"to":[2,44,90,110],"investigate":[3],"end-to-end":[4,29,129,151,164,177],"text-independent":[5,30],"speaker":[6,31],"verification":[7,32],"by":[8,47,160],"incorporating":[9],"the":[10,36,45,92,104,112,118,122,134,149,163,172],"variability":[11],"from":[12],"different":[13],"utterance":[14],"durations.":[15],"Our":[16],"previous":[17],"study":[18],"[1]":[19],"showed":[20],"a":[21,25,48,98],"competitive":[22],"performance":[23],"with":[24,79,97,121,153,166],"triplet":[26],"loss":[27],"based":[28],"system.":[33,175],"To":[34],"normalize":[35],"duration":[37,63],"variability,":[38],"we":[39,88],"provided":[40],"fixed":[41,143],"length":[42,140,144],"inputs":[43],"network":[46,120,136],"simple":[49],"cropping":[50],"or":[51],"padding":[52],"operation.":[53],"Those":[54],"operations":[55],"do":[56],"not":[57],"seem":[58],"ideal,":[59],"particularly":[60],"for":[61],"long":[62],"where":[64],"some":[65],"amount":[66],"of":[67,125],"information":[68],"is":[69],"discarded,":[70],"while":[71],"an":[72,80,128,176],"i-vector":[73],"system":[74,152,165,178],"typically":[75],"has":[76],"improved":[77],"accuracy":[78],"increase":[81],"in":[82,103,127],"input":[83,114,126,156],"duration.":[84],"In":[85,131],"this":[86,132],"study,":[87],"propose":[89],"replace":[91],"final":[93],"max/average":[94],"pooling":[95],"layer":[96,102],"Spatial":[99],"Pyramid":[100],"Pooling":[101],"Inception-Resnet-v1":[105],"architecture,":[106],"which":[107],"allows":[108],"us":[109],"relax":[111],"fixed-length":[113,167],"constraint":[115],"and":[116,169],"train":[117],"entire":[119],"arbitrary":[123],"size":[124,155],"fashion.":[130],"way,":[133],"modified":[135],"can":[137],"map":[138],"variable":[139,154],"utterances":[141],"into":[142],"embeddings.":[145],"Experiments":[146],"shows":[147],"that":[148],"new":[150],"relatively":[157],"reduces":[158],"EER":[159],"8.4%":[161],"over":[162,171],"input,":[168],"24.0%":[170],"i-vector/PLDA":[173],"baseline":[174],"with.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}