{"id":"https://openalex.org/W4408355031","doi":"https://doi.org/10.1109/icassp49660.2025.10888454","title":"Stable Extended U-Net for Noise-Robust Speaker Verification","display_name":"Stable Extended U-Net for Noise-Robust Speaker Verification","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355031","doi":"https://doi.org/10.1109/icassp49660.2025.10888454"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888454","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888454","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5005177639","display_name":"Zonghui Wang","orcid":"https://orcid.org/0000-0002-8212-4618"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zonghui Wang","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China,830017"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China,830017","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007636953","display_name":"Zhihua Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihua Fang","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China,830017"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China,830017","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100507059","display_name":"Liang He","orcid":"https://orcid.org/0000-0001-8032-8767"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang He","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China,830017"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China,830017","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005177639"],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":null,"apc_paid":null,"fwci":3.1486,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.89782375,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9958999752998352,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9958999752998352,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9955000281333923,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9451000094413757,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.7211475372314453},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6957371234893799},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6492455005645752},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5729122757911682},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5050731301307678},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.412799209356308},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27128052711486816},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.09978979825973511}],"concepts":[{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.7211475372314453},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6957371234893799},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6492455005645752},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5729122757911682},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5050731301307678},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.412799209356308},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27128052711486816},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.09978979825973511},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888454","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888454","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2041823554","https://openalex.org/W2112582577","https://openalex.org/W2147147599","https://openalex.org/W2159202424","https://openalex.org/W2165880886","https://openalex.org/W2194775991","https://openalex.org/W2326699523","https://openalex.org/W2476548250","https://openalex.org/W2535388113","https://openalex.org/W2726515241","https://openalex.org/W2807992610","https://openalex.org/W2890964092","https://openalex.org/W2963040451","https://openalex.org/W2964132737","https://openalex.org/W2969985801","https://openalex.org/W2972425344","https://openalex.org/W2997746169","https://openalex.org/W3015197852","https://openalex.org/W3015231328","https://openalex.org/W3015737406","https://openalex.org/W3024869864","https://openalex.org/W3097470351","https://openalex.org/W3177052299","https://openalex.org/W3180303049","https://openalex.org/W3196650842","https://openalex.org/W4283703262","https://openalex.org/W4297841892","https://openalex.org/W4313178214","https://openalex.org/W4372267288","https://openalex.org/W4385823321","https://openalex.org/W4392904246","https://openalex.org/W4392904642","https://openalex.org/W6688816777","https://openalex.org/W6854635559"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W66821593","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W1521299571","https://openalex.org/W4313854686","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W1516392727","https://openalex.org/W2140022733"],"abstract_inverted_index":{"With":[0],"advancements":[1],"in":[2,13,37,51],"deep":[3],"learning,":[4],"speaker":[5,87,116],"verification":[6,88],"systems":[7],"have":[8],"significantly":[9],"improved":[10,23,86],"their":[11,22],"performance":[12,27,55],"noisy":[14],"environments.":[15],"Researchers":[16],"typically":[17],"demonstrate":[18],"the":[19,33,42,64,74,77,95,101,127],"effectiveness":[20,128],"of":[21,76,129],"models":[24],"by":[25],"comparing":[26],"on":[28,58,80,94,135],"specific":[29],"datasets,":[30],"such":[31],"as":[32],"VoxCeleb":[34],"benchmark.":[35],"However,":[36],"diverse":[38],"real-world":[39],"noise":[40,141],"conditions,":[41],"out-of-domain":[43,140],"generalization":[44,75,92,146],"ability":[45],"is":[46],"also":[47],"a":[48,53],"crucial":[49],"factor":[50],"evaluating":[52],"model\u2019s":[54],"improvement.":[56],"Research":[57],"stable":[59,106],"learning":[60,107],"indicates":[61],"that":[62],"eliminating":[63],"spurious":[65],"correlation":[66],"between":[67],"training":[68],"and":[69,112,121,138,148],"testing":[70],"data":[71],"can":[72],"enhance":[73],"model.":[78],"Building":[79],"this":[81,130],"idea,":[82],"we":[83],"propose":[84],"an":[85],"system":[89],"with":[90],"high":[91],"based":[93],"extended":[96],"U-Net":[97],"(ExU-Net).":[98],"It":[99],"uses":[100],"sample":[102,110],"reweighting":[103],"method":[104],"from":[105],"to":[108],"eliminate":[109],"correlations":[111],"retains":[113],"more":[114],"effective":[115],"information":[117],"through":[118,132],"subpixel":[119],"convolutions":[120],"coordinate":[122],"attention":[123],"mechanisms.":[124],"We":[125],"validate":[126],"approach":[131],"extensive":[133],"evaluations":[134],"VoxCeleb1,":[136],"VOiCES,":[137],"other":[139],"test":[142],"sets,":[143],"highlighting":[144],"its":[145],"capability":[147],"model":[149],"robustness.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}