{"id":"https://openalex.org/W2802488037","doi":"https://doi.org/10.1109/icassp.2018.8462575","title":"A Complete End-to-End Speaker Verification System Using Deep Neural Networks: From Raw Signals to Verification Result","display_name":"A Complete End-to-End Speaker Verification System Using Deep Neural Networks: From Raw Signals to Verification Result","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2802488037","doi":"https://doi.org/10.1109/icassp.2018.8462575","mag":"2802488037"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462575","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":"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/A5037481392","display_name":"Jee- Weon Jung","orcid":null},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jee- Weon Jung","raw_affiliation_strings":["School of Computer Science, University of Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Seoul, South Korea","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070613375","display_name":"Hee-Soo Heo","orcid":"https://orcid.org/0000-0003-1567-123X"},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hee-Soo Heo","raw_affiliation_strings":["School of Computer Science, University of Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Seoul, South Korea","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103369457","display_name":"IL-Ho Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Il-Ho Yang","raw_affiliation_strings":["School of Computer Science, University of Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Seoul, South Korea","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103211980","display_name":"Hye-jin Shim","orcid":null},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hye-Jin Shim","raw_affiliation_strings":["School of Computer Science, University of Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Seoul, South Korea","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030475312","display_name":"Ha-Jin Yu","orcid":"https://orcid.org/0000-0003-3657-0665"},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ha-Jin Yu","raw_affiliation_strings":["School of Computer Science, University of Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Seoul, South Korea","institution_ids":["https://openalex.org/I124633538"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5037481392"],"corresponding_institution_ids":["https://openalex.org/I124633538"],"apc_list":null,"apc_paid":null,"fwci":7.4927,"has_fulltext":false,"cited_by_count":70,"citation_normalized_percentile":{"value":0.97720411,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5349","last_page":"5353"},"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":0.9968000054359436,"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":0.9958000183105469,"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":0.8108701705932617},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7108153104782104},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6588660478591919},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.6369919776916504},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.636802077293396},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5823268294334412},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5105829834938049},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5069006085395813},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4514068067073822},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4483548104763031},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44018489122390747},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40524715185165405}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8108701705932617},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7108153104782104},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6588660478591919},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.6369919776916504},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.636802077293396},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5823268294334412},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5105829834938049},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5069006085395813},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4514068067073822},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4483548104763031},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44018489122390747},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40524715185165405},{"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/icassp.2018.8462575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462575","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1006777433","https://openalex.org/W1548442879","https://openalex.org/W1836465849","https://openalex.org/W1922655562","https://openalex.org/W1996512145","https://openalex.org/W2039057510","https://openalex.org/W2046056978","https://openalex.org/W2049244943","https://openalex.org/W2064675550","https://openalex.org/W2095705004","https://openalex.org/W2114925438","https://openalex.org/W2116261113","https://openalex.org/W2136848157","https://openalex.org/W2168249605","https://openalex.org/W2505121225","https://openalex.org/W2593179621","https://openalex.org/W2747900149","https://openalex.org/W2748488820","https://openalex.org/W2949117887","https://openalex.org/W2964351684","https://openalex.org/W4234330420","https://openalex.org/W6662018943","https://openalex.org/W6674330103","https://openalex.org/W6684821101"],"related_works":["https://openalex.org/W2811390910","https://openalex.org/W2146076056","https://openalex.org/W2546942002","https://openalex.org/W4386303287","https://openalex.org/W4288323920","https://openalex.org/W3114320604","https://openalex.org/W2003826957","https://openalex.org/W3017138616","https://openalex.org/W2372334721","https://openalex.org/W3015923889"],"abstract_inverted_index":{"End-to-end":[0],"systems":[1,42],"using":[2,43,113],"deep":[3],"neural":[4],"networks":[5],"have":[6,47],"been":[7,22,49],"widely":[8,23],"studied":[9,24],"in":[10,25,51,124],"the":[11,26,72,79,102,125],"field":[12],"of":[13,28],"speaker":[14,52,60,81,109],"verification.":[15,53],"Raw":[16],"audio":[17,45,68],"signal":[18],"processing":[19],"has":[20],"also":[21],"fields":[27],"automatic":[29],"music":[30],"tagging":[31],"and":[32,70,78,115],"speech":[33],"recognition.":[34],"However,":[35],"as":[36,38],"far":[37],"we":[39],"know,":[40],"end-to-end":[41,59,127],"raw":[44,67],"signals":[46,69],"not":[48],"explored":[50],"In":[54,107],"this":[55],"paper,":[56],"a":[57,95],"complete":[58],"verification":[61,73],"system":[62],"is":[63],"proposed,":[64],"which":[65],"inputs":[66],"outputs":[71],"results.":[74],"A":[75],"pre-processing":[76,100],"layer":[77,91,98],"embedded":[80,123],"feature":[82,110],"extraction":[83,111],"models":[84,112],"were":[85],"mainly":[86],"investigated.":[87],"The":[88],"proposed":[89,120,126],"pre-emphasis":[90],"was":[92],"combined":[93],"with":[94],"strided":[96],"convolution":[97],"for":[99],"at":[101],"first":[103],"two":[104],"hidden":[105],"layers.":[106],"addition,":[108],"convolutionallayer":[114],"long":[116],"short-term":[117],"memory":[118],"are":[119],"to":[121],"be":[122],"system.":[128]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}