{"id":"https://openalex.org/W2962959915","doi":"https://doi.org/10.1109/icassp.2018.8461587","title":"Attention-Based Models for Text-Dependent Speaker Verification","display_name":"Attention-Based Models for Text-Dependent Speaker Verification","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2962959915","doi":"https://doi.org/10.1109/icassp.2018.8461587","mag":"2962959915"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461587","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461587","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","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/A5112483806","display_name":"F A Rezaur Rahman Chowdhury","orcid":null},"institutions":[{"id":"https://openalex.org/I72951846","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17","country_code":"US","type":"education","lineage":["https://openalex.org/I72951846"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"F A Rezaur rahman Chowdhury","raw_affiliation_strings":["Washington State University"],"affiliations":[{"raw_affiliation_string":"Washington State University","institution_ids":["https://openalex.org/I72951846"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418247","display_name":"Quan Wang","orcid":"https://orcid.org/0000-0001-6913-8604"},"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":"Quan Wang","raw_affiliation_strings":["Google Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., 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., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100320150","display_name":"Li Wan","orcid":"https://orcid.org/0000-0003-0690-0272"},"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":"Li Wan","raw_affiliation_strings":["Google Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5112483806"],"corresponding_institution_ids":["https://openalex.org/I72951846"],"apc_list":null,"apc_paid":null,"fwci":11.049,"has_fulltext":false,"cited_by_count":146,"citation_normalized_percentile":{"value":0.98721588,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5359","last_page":"5363"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987000226974487,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8304530382156372},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7552282214164734},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6970640420913696},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6676371097564697},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.6006036400794983},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.595234751701355},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5880789756774902},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5023465156555176},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49659067392349243},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.49419906735420227},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4685802161693573},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42811456322669983},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.41192173957824707},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.20165443420410156}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8304530382156372},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7552282214164734},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6970640420913696},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6676371097564697},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.6006036400794983},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.595234751701355},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5880789756774902},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5023465156555176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49659067392349243},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.49419906735420227},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4685802161693573},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42811456322669983},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.41192173957824707},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.20165443420410156},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461587","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461587","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":15,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1485222997","https://openalex.org/W1514535095","https://openalex.org/W2034940213","https://openalex.org/W2064675550","https://openalex.org/W2096733369","https://openalex.org/W2114925438","https://openalex.org/W2150769028","https://openalex.org/W2293634267","https://openalex.org/W2395750323","https://openalex.org/W2919115771","https://openalex.org/W2962788625","https://openalex.org/W2963470929","https://openalex.org/W2964351684","https://openalex.org/W3099206234"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W2499802997","https://openalex.org/W4255044973","https://openalex.org/W2112059504","https://openalex.org/W2727729836","https://openalex.org/W1960256358","https://openalex.org/W2464377622","https://openalex.org/W2914064142","https://openalex.org/W2394963835"],"abstract_inverted_index":{"Attention-based":[0],"models":[1,87],"have":[2],"recently":[3],"shown":[4],"great":[5],"performance":[6],"on":[7,78],"a":[8],"range":[9],"of":[10,35,46,52,69,95],"tasks,":[11],"such":[12],"as":[13],"speech":[14],"recognition,":[15],"machine":[16],"translation,":[17],"and":[18,66,73],"image":[19],"captioning":[20],"due":[21],"to":[22,25,49,104],"their":[23,67],"ability":[24],"summarize":[26],"relevant":[27],"information":[28],"that":[29,85],"expands":[30],"through":[31],"the":[32,44,50,70,79,90],"entire":[33],"length":[34],"an":[36],"input":[37],"sequence.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42,83],"analyze":[43],"usage":[45],"attention":[47,71,80],"mechanisms":[48],"problem":[51],"sequence":[53],"summarization":[54],"in":[55],"our":[56,96,105],"end-to-end":[57],"text-dependent":[58],"speaker":[59,97],"recognition":[60],"system.":[61],"We":[62],"explore":[63],"different":[64,75],"topologies":[65],"variants":[68],"layer,":[72],"compare":[74],"pooling":[76],"methods":[77],"weights.":[81],"Ultimately,":[82],"show":[84],"attention-based":[86],"can":[88],"improves":[89],"Equal":[91],"Error":[92],"Rate":[93],"(EER)":[94],"verification":[98],"system":[99],"by":[100],"relatively":[101],"14%":[102],"compared":[103],"non-attention":[106],"LSTM":[107],"baseline":[108],"model.":[109]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":25},{"year":2020,"cited_by_count":40},{"year":2019,"cited_by_count":28},{"year":2018,"cited_by_count":11}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}
