{"id":"https://openalex.org/W2587150483","doi":"https://doi.org/10.1109/slt.2016.7846260","title":"Deep neural network-based speaker embeddings for end-to-end speaker verification","display_name":"Deep neural network-based speaker embeddings for end-to-end speaker verification","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2587150483","doi":"https://doi.org/10.1109/slt.2016.7846260","mag":"2587150483"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2016.7846260","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2016.7846260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Spoken Language Technology Workshop (SLT)","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/A5059065394","display_name":"David Snyder","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Snyder","raw_affiliation_strings":["Center for Language and Speech Processing & Human Language Technology Center of Excellence, The Johns Hopkins University, Baltimore, MD, USA","Spoken Labs, Spoken Communications, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing & Human Language Technology Center of Excellence, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Spoken Labs, Spoken Communications, Seattle, WA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029777844","display_name":"Pegah Ghahremani","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pegah Ghahremani","raw_affiliation_strings":["Center for Language and Speech Processing & Human Language Technology Center of Excellence, The Johns Hopkins University, Baltimore, MD, USA","Spoken Labs, Spoken Communications, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing & Human Language Technology Center of Excellence, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Spoken Labs, Spoken Communications, Seattle, WA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084286453","display_name":"Daniel Povey","orcid":"https://orcid.org/0000-0002-0611-3634"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Povey","raw_affiliation_strings":["Center for Language and Speech Processing & Human Language Technology Center of Excellence, The Johns Hopkins University, Baltimore, MD, USA","Spoken Labs, Spoken Communications, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing & Human Language Technology Center of Excellence, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Spoken Labs, Spoken Communications, Seattle, WA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000143881","display_name":"Daniel Garcia-Romero","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Garcia-Romero","raw_affiliation_strings":["Center for Language and Speech Processing & Human Language Technology Center of Excellence, The Johns Hopkins University, Baltimore, MD, USA","Spoken Labs, Spoken Communications, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing & Human Language Technology Center of Excellence, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Spoken Labs, Spoken Communications, Seattle, WA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060644900","display_name":"Yishay Carmiel","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yishay Carmiel","raw_affiliation_strings":["Center for Language and Speech Processing & Human Language Technology Center of Excellence, The Johns Hopkins University, Baltimore, MD, USA","Spoken Labs, Spoken Communications, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing & Human Language Technology Center of Excellence, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Spoken Labs, Spoken Communications, Seattle, WA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["Center for Language and Speech Processing & Human Language Technology Center of Excellence, The Johns Hopkins University, Baltimore, MD, USA","Spoken Labs, Spoken Communications, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing & Human Language Technology Center of Excellence, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Spoken Labs, Spoken Communications, Seattle, WA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":30.6986,"has_fulltext":false,"cited_by_count":374,"citation_normalized_percentile":{"value":0.99736447,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"165","last_page":"170"},"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":0.9980999827384949,"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":0.9932000041007996,"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-verification","display_name":"Speaker verification","score":0.8590410947799683},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7437705993652344},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6996475458145142},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6816363334655762},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6685823798179626},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6066302061080933},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5614022016525269},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5451785922050476},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5137268304824829},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5048023462295532},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.44442018866539},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41638800501823425},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4023313522338867}],"concepts":[{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.8590410947799683},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7437705993652344},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6996475458145142},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6816363334655762},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6685823798179626},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6066302061080933},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5614022016525269},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5451785922050476},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5137268304824829},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5048023462295532},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.44442018866539},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41638800501823425},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4023313522338867},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2016.7846260","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2016.7846260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W40124310","https://openalex.org/W1524333225","https://openalex.org/W1762484328","https://openalex.org/W1799366690","https://openalex.org/W2004497042","https://openalex.org/W2039057510","https://openalex.org/W2046056978","https://openalex.org/W2078169166","https://openalex.org/W2099797668","https://openalex.org/W2109761419","https://openalex.org/W2114925438","https://openalex.org/W2121812409","https://openalex.org/W2123768812","https://openalex.org/W2129379984","https://openalex.org/W2138547132","https://openalex.org/W2143694533","https://openalex.org/W2150769028","https://openalex.org/W2183016404","https://openalex.org/W2290689761","https://openalex.org/W2292259253","https://openalex.org/W2294814385","https://openalex.org/W2332932830","https://openalex.org/W2395619480","https://openalex.org/W2395750323","https://openalex.org/W2401594978","https://openalex.org/W2402919203","https://openalex.org/W2406312423","https://openalex.org/W2508048623","https://openalex.org/W3186851455","https://openalex.org/W6601610752","https://openalex.org/W6631362777","https://openalex.org/W6637956674","https://openalex.org/W6638444622","https://openalex.org/W6675120338","https://openalex.org/W6713727690"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W66821593","https://openalex.org/W2149220986","https://openalex.org/W1521299571","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W2972909277","https://openalex.org/W2144470400","https://openalex.org/W2911612049"],"abstract_inverted_index":{"In":[0],"this":[1,59],"study,":[2],"we":[3,56],"investigate":[4],"an":[5,80],"end-to-end":[6,97],"text-independent":[7,64],"speaker":[8,31],"verification":[9],"system.":[10],"The":[11,33,110],"architecture":[12],"consists":[13],"of":[14,73,116],"a":[15,21,30,70,114],"deep":[16],"neural":[17],"network":[18],"that":[19,58,68],"takes":[20],"variable":[22],"length":[23],"speech":[24],"segment":[25],"and":[26,38,41,87,104,119],"maps":[27],"it":[28],"to":[29,93],"embedding.":[32],"objective":[34],"function":[35],"separates":[36],"same-speaker":[37],"different-speaker":[39],"pairs,":[40],"is":[42,60],"reused":[43],"during":[44],"verification.":[45],"Similar":[46],"systems":[47],"have":[48],"recently":[49],"shown":[50],"promise":[51],"for":[52,62],"text-dependent":[53],"verification,":[54],"but":[55],"believe":[57],"unexplored":[61],"the":[63,76,94,96],"task.":[65],"We":[66],"show":[67],"given":[69],"large":[71],"number":[72],"training":[74],"speakers,":[75],"proposed":[77],"system":[78,98,112],"outperforms":[79],"i-vector":[81],"baseline":[82],"in":[83],"equal":[84],"error-rate":[85],"(EER)":[86],"at":[88],"low":[89],"miss":[90],"rates.":[91],"Relative":[92],"baseline,":[95],"reduces":[99],"EER":[100],"by":[101],"13%":[102],"average":[103,118],"29%":[105],"pooled":[106],"across":[107],"test":[108],"conditions.":[109],"fused":[111],"achieves":[113],"reduction":[115],"32%":[117],"38%":[120],"pooled.":[121]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":21},{"year":2022,"cited_by_count":30},{"year":2021,"cited_by_count":47},{"year":2020,"cited_by_count":85},{"year":2019,"cited_by_count":74},{"year":2018,"cited_by_count":65},{"year":2017,"cited_by_count":18},{"year":2016,"cited_by_count":1}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}