{"id":"https://openalex.org/W4393065886","doi":"https://doi.org/10.1109/taslp.2024.3381005","title":"FA-ExU-Net: The Simultaneous Training of an Embedding Extractor and Enhancement Model for a Speaker Verification System Robust to Short Noisy Utterances","display_name":"FA-ExU-Net: The Simultaneous Training of an Embedding Extractor and Enhancement Model for a Speaker Verification System Robust to Short Noisy Utterances","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4393065886","doi":"https://doi.org/10.1109/taslp.2024.3381005"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3381005","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3381005","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5013987547","display_name":"Ju-ho Kim","orcid":"https://orcid.org/0000-0001-6468-1368"},"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":"Ju-ho Kim","raw_affiliation_strings":["School of Computer Science, University of Seoul, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Seoul, Seoul, South Korea","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046942516","display_name":"Jungwoo Heo","orcid":"https://orcid.org/0009-0008-7977-2789"},"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":"Jungwoo Heo","raw_affiliation_strings":["School of Computer Science, University of Seoul, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Seoul, Seoul, South Korea","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006973604","display_name":"Hyun-seo Shin","orcid":"https://orcid.org/0009-0005-6022-7674"},"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":"Hyun-seo Shin","raw_affiliation_strings":["School of Computer Science, University of Seoul, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Seoul, Seoul, South Korea","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036516187","display_name":"Chan-yeong Lim","orcid":"https://orcid.org/0009-0001-6671-5004"},"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":"Chan-yeong Lim","raw_affiliation_strings":["School of Computer Science, University of Seoul, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Seoul, 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, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Seoul, Seoul, South Korea","institution_ids":["https://openalex.org/I124633538"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5013987547"],"corresponding_institution_ids":["https://openalex.org/I124633538"],"apc_list":null,"apc_paid":null,"fwci":1.0878,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.79382581,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"32","issue":null,"first_page":"2269","last_page":"2282"},"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":0.9976000189781189,"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":0.9914000034332275,"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/extractor","display_name":"Extractor","score":0.7673863172531128},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6544939279556274},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6423513889312744},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5626358389854431},{"id":"https://openalex.org/keywords/net","display_name":"Net (polyhedron)","score":0.5374816656112671},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49099400639533997},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37061062455177307},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3226785659790039},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2127305567264557},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1181226372718811},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.0611230731010437},{"id":"https://openalex.org/keywords/process-engineering","display_name":"Process engineering","score":0.05027329921722412}],"concepts":[{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.7673863172531128},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6544939279556274},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6423513889312744},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5626358389854431},{"id":"https://openalex.org/C14166107","wikidata":"https://www.wikidata.org/wiki/Q253829","display_name":"Net (polyhedron)","level":2,"score":0.5374816656112671},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49099400639533997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37061062455177307},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3226785659790039},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2127305567264557},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1181226372718811},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0611230731010437},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.05027329921722412},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3381005","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3381005","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":84,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2026358225","https://openalex.org/W2041823554","https://openalex.org/W2046015436","https://openalex.org/W2046056978","https://openalex.org/W2051802399","https://openalex.org/W2092956033","https://openalex.org/W2120847449","https://openalex.org/W2121750345","https://openalex.org/W2144760012","https://openalex.org/W2150769028","https://openalex.org/W2153485077","https://openalex.org/W2154278880","https://openalex.org/W2165880886","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2407127962","https://openalex.org/W2565639579","https://openalex.org/W2586068394","https://openalex.org/W2726515241","https://openalex.org/W2746742816","https://openalex.org/W2748488820","https://openalex.org/W2785523195","https://openalex.org/W2793459270","https://openalex.org/W2794506738","https://openalex.org/W2799831802","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2916301830","https://openalex.org/W2962788625","https://openalex.org/W2963040451","https://openalex.org/W2963263347","https://openalex.org/W2963323244","https://openalex.org/W2972425344","https://openalex.org/W2972441390","https://openalex.org/W2972552635","https://openalex.org/W2972627751","https://openalex.org/W2981087920","https://openalex.org/W3004720752","https://openalex.org/W3008104819","https://openalex.org/W3008911072","https://openalex.org/W3013020904","https://openalex.org/W3015231328","https://openalex.org/W3015648588","https://openalex.org/W3020953549","https://openalex.org/W3023888872","https://openalex.org/W3024869864","https://openalex.org/W3025515949","https://openalex.org/W3025788388","https://openalex.org/W3088315586","https://openalex.org/W3096084197","https://openalex.org/W3096235116","https://openalex.org/W3097077247","https://openalex.org/W3097435397","https://openalex.org/W3104056985","https://openalex.org/W3142516134","https://openalex.org/W3149926570","https://openalex.org/W3163082428","https://openalex.org/W3196650842","https://openalex.org/W3197340960","https://openalex.org/W3198564914","https://openalex.org/W3198742213","https://openalex.org/W3206287456","https://openalex.org/W3208777959","https://openalex.org/W3209059054","https://openalex.org/W4220961503","https://openalex.org/W4221154746","https://openalex.org/W4224916701","https://openalex.org/W4224917447","https://openalex.org/W4224924624","https://openalex.org/W4283376778","https://openalex.org/W4283703262","https://openalex.org/W4295789112","https://openalex.org/W4296069297","https://openalex.org/W4297841768","https://openalex.org/W4297841892","https://openalex.org/W6604530394","https://openalex.org/W6637373629","https://openalex.org/W6688816777","https://openalex.org/W6712325649","https://openalex.org/W6713727690","https://openalex.org/W6726497184","https://openalex.org/W6747620207","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W3082848404","https://openalex.org/W2081900870","https://openalex.org/W1979583797","https://openalex.org/W2233261550","https://openalex.org/W2016864125","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W2372254676"],"abstract_inverted_index":{"Speaker":[0],"verification":[1],"(SV)":[2],"technology":[3],"has":[4],"the":[5,27,66,77,101,106,143,171,174,194],"potential":[6],"to":[7,41,157,163,191,193],"enhance":[8],"personalization":[9],"and":[10,20,35,44,76,119,130,161,179,182,199],"security":[11],"in":[12,37,53,57,166],"various":[13],"applications,":[14],"such":[15],"as":[16],"voice":[17],"assistants,":[18],"forensics,":[19],"access":[21],"control.":[22],"However,":[23],"several":[24],"challenges":[25,102],"hinder":[26],"practical":[28,204],"application":[29],"of":[30,62,68,79,108,173,196],"SV":[31,63,90,201],"systems,":[32],"including":[33],"limitations":[34],"distortions":[36],"speaker":[38],"information":[39],"due":[40],"short":[42,153,164],"utterances":[43,165],"noisy":[45,159,167],"environments.":[46,168],"Furthermore,":[47],"these":[48,69],"two":[49],"factors":[50,81],"often":[51],"coexist":[52],"real-world":[54],"situations,":[55],"resulting":[56],"a":[58,88,124,131],"significant":[59],"performance":[60],"degradation":[61],"systems.":[64],"Despite":[65],"significance":[67],"obstacles,":[70],"each":[71,112],"factor":[72],"is":[73,82,189],"independently":[74],"studied,":[75],"co-occurrence":[78],"both":[80,100],"rarely":[83],"investigated.":[84],"Here,":[85],"we":[86],"propose":[87],"novel":[89,187],"framework,":[91],"feature":[92,121,127,133],"aggregated":[93],"extended":[94],"U-Net":[95],"(FA-ExU-Net),":[96],"which":[97],"simultaneously":[98],"addresses":[99],"by":[103],"building":[104],"on":[105,111,148],"success":[107],"prior":[109],"research":[110],"factor.":[113],"The":[114,185],"FA-ExU-Net":[115],"incorporates":[116],"an":[117],"iterative":[118],"hierarchical":[120],"aggregation":[122],"scheme,":[123],"target":[125],"task-specific":[126],"enhancement":[128],"module,":[129],"multi-scale":[132],"aggregator":[134],"for":[135,203],"extracting":[136],"information-rich":[137],"embeddings.":[138],"Our":[139,206],"proposed":[140,175,186],"system":[141],"outperforms":[142],"recent":[144],"baseline":[145],"models":[146,202],"based":[147],"four":[149],"evaluation":[150],"criteria:":[151],"generalizability,":[152],"utterance":[154],"performance,":[155],"capacity":[156],"handle":[158],"environments,":[160],"robustness":[162],"We":[169],"demonstrate":[170],"effectiveness":[172],"model":[176],"through":[177],"comparison":[178],"ablation":[180],"experiments":[181],"intuitive":[183],"visualizations.":[184],"approach":[188],"expected":[190],"contribute":[192],"development":[195],"more":[197],"robust":[198],"accurate":[200],"applications.":[205],"training":[207],"codes":[208],"are":[209],"available":[210],"at":[211],"<uri":[212],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[213],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/wngh1187/FA-ExU-Net.</uri>":[214]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}