{"id":"https://openalex.org/W4283703262","doi":"https://doi.org/10.21437/interspeech.2022-155","title":"Extended U-Net for Speaker Verification in Noisy Environments","display_name":"Extended U-Net for Speaker Verification in Noisy Environments","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283703262","doi":"https://doi.org/10.21437/interspeech.2022-155"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-155","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-155","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/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, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Seoul, Republic of Korea","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103180203","display_name":"Jungwoo Heo","orcid":"https://orcid.org/0000-0002-1254-0413"},"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, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Seoul, Republic of Korea","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080292725","display_name":"Hye-jin Shim","orcid":"https://orcid.org/0000-0002-0912-6983"},"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, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Seoul, Republic of 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, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Seoul, Republic of Korea","institution_ids":["https://openalex.org/I124633538"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5013987547"],"corresponding_institution_ids":["https://openalex.org/I124633538"],"apc_list":null,"apc_paid":null,"fwci":1.9894,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.88424233,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"590","last_page":"594"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/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":0.9828000068664551,"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":0.8160333037376404},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6268213391304016},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5313601493835449},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5029637217521667},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.5022127628326416},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4954763650894165},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.47223448753356934},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4502404034137726},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.441548615694046},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4371398389339447},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4169628620147705},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34747591614723206}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8160333037376404},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6268213391304016},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5313601493835449},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5029637217521667},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.5022127628326416},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4954763650894165},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.47223448753356934},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4502404034137726},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.441548615694046},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4371398389339447},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4169628620147705},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34747591614723206},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-155","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-155","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322030","display_name":"Ministry of Science, ICT and Future Planning","ror":"https://ror.org/032e49973"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320322347","display_name":"Ministry of Science ICT and Future Planning","ror":"https://ror.org/032e49973"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1665214252","https://openalex.org/W1836465849","https://openalex.org/W1901129140","https://openalex.org/W2041823554","https://openalex.org/W2046056978","https://openalex.org/W2150769028","https://openalex.org/W2153485077","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2397634864","https://openalex.org/W2407127962","https://openalex.org/W2586068394","https://openalex.org/W2726515241","https://openalex.org/W2793459270","https://openalex.org/W2794506738","https://openalex.org/W2799831802","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2963040451","https://openalex.org/W2972425344","https://openalex.org/W2972552635","https://openalex.org/W2998678989","https://openalex.org/W3013020904","https://openalex.org/W3015231328","https://openalex.org/W3025515949","https://openalex.org/W3025788388","https://openalex.org/W3196650842","https://openalex.org/W4206633762","https://openalex.org/W4289302904","https://openalex.org/W4309845474"],"related_works":["https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W4235705411","https://openalex.org/W1521299571","https://openalex.org/W3000153094","https://openalex.org/W2542062716","https://openalex.org/W2738829087","https://openalex.org/W2231565466","https://openalex.org/W2134501921","https://openalex.org/W3043214604"],"abstract_inverted_index":{"Background":[0],"noise":[1,116],"is":[2,156],"a":[3,93],"well-known":[4],"factor":[5],"that":[6,68,97,149],"deteriorates":[7],"the":[8,29,33,45,55,61,69,108,129,132,150,160,163,170],"accuracy":[9],"and":[10,39,72,102,119,137,162],"reliability":[11],"of":[12,32,48,111],"speaker":[13,62,73,100],"verification":[14],"(SV)":[15],"systems":[16],"by":[17],"blurring":[18],"speech":[19],"intelligibility.Various":[20],"studies":[21],"have":[22],"used":[23],"separate":[24],"pretrained":[25],"enhancement":[26,50,70,104],"models":[27,51,130],"as":[28],"front-end":[30],"module":[31],"SV":[34,56,82,117],"system":[35],"in":[36,65,142],"noisy":[37,85,144],"environments,":[38],"these":[40,126],"methods":[41],"effectively":[42],"remove":[43],"noises.However,":[44],"denoising":[46],"process":[47],"independent":[49],"not":[52],"tailored":[53],"to":[54,87,124],"task":[57],"can":[58],"also":[59],"distort":[60],"information":[63],"included":[64],"utterances.We":[66],"argue":[67],"network":[71],"embedding":[74],"extractor":[75],"should":[76],"be":[77],"fully":[78,152],"jointly":[79],"trained":[80],"for":[81,115],"tasks":[83,118],"under":[84],"conditions":[86],"alleviate":[88],"this":[89],"issue.Therefore,":[90],"we":[91,106],"proposed":[92,121,172],"U-Net-based":[94,151],"integrated":[95],"framework":[96,155],"simultaneously":[98],"optimizes":[99],"identification":[101],"feature":[103],"losses.Moreover,":[105],"analyzed":[107],"structural":[109],"limitations":[110],"using":[112],"U-Net":[113,123,165],"directly":[114],"further":[120],"Extended":[122],"reduce":[125],"drawbacks.We":[127],"evaluated":[128],"on":[131],"noise-synthesized":[133],"VoxCeleb1":[134],"test":[135],"set":[136,140],"VOiCES":[138],"development":[139],"recorded":[141],"various":[143],"scenarios.The":[145],"experimental":[146],"results":[147],"demonstrate":[148],"joint":[153],"training":[154],"more":[157],"effective":[158],"than":[159],"baseline,":[161],"extended":[164],"exhibited":[166],"state-of-the-art":[167],"performance":[168],"versus":[169],"recently":[171],"compensation":[173],"systems.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-21T06:30:42.041108","created_date":"2025-10-10T00:00:00"}