{"id":"https://openalex.org/W2046056978","doi":"https://doi.org/10.1109/icassp.2014.6854363","title":"Deep neural networks for small footprint text-dependent speaker verification","display_name":"Deep neural networks for small footprint text-dependent speaker verification","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2046056978","doi":"https://doi.org/10.1109/icassp.2014.6854363","mag":"2046056978"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854363","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854363","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5040131037","display_name":"Ehsan Variani","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":true,"raw_author_name":"Ehsan Variani","raw_affiliation_strings":["Johns Hopkins Univ., Baltimore, MD, USA","Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins Univ., Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049457213","display_name":"Xin Lei","orcid":"https://orcid.org/0000-0002-4400-4068"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Lei","raw_affiliation_strings":["Google Inc., USA","Google Inc., Mountain View, CA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., Mountain View, CA USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030109648","display_name":"Erik McDermott","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erik McDermott","raw_affiliation_strings":["Google Inc., USA","Google Inc., Mountain View, CA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., Mountain View, CA USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050898122","display_name":"Ignacio L\u00f3pez Moreno","orcid":"https://orcid.org/0000-0002-0900-3473"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ignacio Lopez Moreno","raw_affiliation_strings":["Google Inc, Mountain View, CA, US","Google Inc., Mountain View, CA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc, Mountain View, CA, US","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., Mountain View, CA USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089369295","display_name":"Javier G\u00f3nzalez-Dom\u00ednguez","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Javier Gonzalez-Dominguez","raw_affiliation_strings":["Google Inc., USA","Google Inc., Mountain View, CA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., Mountain View, CA USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5040131037"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":49.9014,"has_fulltext":false,"cited_by_count":1092,"citation_normalized_percentile":{"value":0.99879717,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4052","last_page":"4056"},"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":0.9965000152587891,"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":0.9894000291824341,"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":0.801534116268158},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.772546112537384},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7251805663108826},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6440932750701904},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6235212683677673},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.549646258354187},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.5186995267868042},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5103396773338318},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5071821212768555},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5036067366600037},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.49429893493652344},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45992594957351685},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4340433180332184},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11111658811569214}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.801534116268158},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.772546112537384},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7251805663108826},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6440932750701904},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6235212683677673},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.549646258354187},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.5186995267868042},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5103396773338318},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5071821212768555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5036067366600037},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.49429893493652344},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45992594957351685},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4340433180332184},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11111658811569214},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2014.6854363","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854363","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.674.3686","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.674.3686","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://static.googleusercontent.com/media/research.google.com/en/us/pubs/archive/41939.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.679.7742","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.679.7742","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://clsp.jhu.edu/%7Evariani/dnn_verifier.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W182365161","https://openalex.org/W1665214252","https://openalex.org/W1865113136","https://openalex.org/W1904365287","https://openalex.org/W1983833855","https://openalex.org/W2040105822","https://openalex.org/W2041823554","https://openalex.org/W2062227835","https://openalex.org/W2078953162","https://openalex.org/W2107638917","https://openalex.org/W2107789863","https://openalex.org/W2112582577","https://openalex.org/W2136879537","https://openalex.org/W2138547132","https://openalex.org/W2150769028","https://openalex.org/W2160815625","https://openalex.org/W2168231600","https://openalex.org/W2184045248","https://openalex.org/W2399828378","https://openalex.org/W2402072010","https://openalex.org/W2406312423","https://openalex.org/W3037950864","https://openalex.org/W6637242042","https://openalex.org/W6639179683","https://openalex.org/W6676071220","https://openalex.org/W6684859321","https://openalex.org/W6696761078","https://openalex.org/W6713097126","https://openalex.org/W6713727690"],"related_works":["https://openalex.org/W1521299571","https://openalex.org/W3096066489","https://openalex.org/W3141593045","https://openalex.org/W2134501921","https://openalex.org/W3048257020","https://openalex.org/W204267554","https://openalex.org/W2147062549","https://openalex.org/W215245425","https://openalex.org/W4252590334","https://openalex.org/W4317103504"],"abstract_inverted_index":{"In":[0,113],"this":[1],"paper":[2],"we":[3],"investigate":[4],"the":[5,31,36,47,62,78,90,115,127,137,141],"use":[6],"of":[7,53],"deep":[8],"neural":[9],"networks":[10],"(DNNs)":[11],"for":[12,72,154],"a":[13,23,68,84,101,106],"small":[14,107],"footprint":[15,108],"text-dependent":[16,109],"speaker":[17,34,43,55,63,80,93,110],"verification":[18,85,94,111],"task.":[19,112],"At":[20,65],"development":[21],"stage,":[22,67],"DNN":[24,38,91,116],"is":[25,39,59,70,119],"trained":[26,37],"to":[27,41,77,82,100,122],"classify":[28],"speakers":[29],"at":[30,130],"framelevel.":[32],"During":[33],"enrollment,":[35],"used":[40],"extract":[42],"specific":[44],"features":[45],"from":[46],"last":[48],"hidden":[49],"layer.":[50],"The":[51],"average":[52],"these":[54],"features,":[56],"or":[57],"d-vector,":[58],"taken":[60],"as":[61],"model.":[64],"evaluation":[66],"d-vector":[69],"extracted":[71],"each":[73],"utterance":[74],"and":[75,125,146,156],"compared":[76,99],"enrolled":[79],"model":[81],"make":[83],"decision.":[86],"Experimental":[87],"results":[88],"show":[89],"based":[92,117],"system":[95,104,118,129,139,143],"achieves":[96],"good":[97],"performance":[98],"popular":[102],"i-vector":[103,128,142],"on":[105],"addition,":[114],"more":[120],"robust":[121],"additive":[123],"noise":[124],"outperforms":[126,140],"low":[131],"False":[132],"Rejection":[133],"operating":[134],"points.":[135],"Finally":[136],"combined":[138],"by":[144],"14%":[145],"25%":[147],"relative":[148],"in":[149],"equal":[150],"error":[151],"rate":[152],"(EER)":[153],"clean":[155],"noisy":[157],"conditions":[158],"respectively.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":50},{"year":2024,"cited_by_count":80},{"year":2023,"cited_by_count":118},{"year":2022,"cited_by_count":112},{"year":2021,"cited_by_count":150},{"year":2020,"cited_by_count":226},{"year":2019,"cited_by_count":132},{"year":2018,"cited_by_count":95},{"year":2017,"cited_by_count":57},{"year":2016,"cited_by_count":37},{"year":2015,"cited_by_count":21},{"year":2014,"cited_by_count":3}],"updated_date":"2026-06-03T09:05:47.796612","created_date":"2025-10-10T00:00:00"}