{"id":"https://openalex.org/W4405709680","doi":"https://doi.org/10.1109/iscslp63861.2024.10800205","title":"Simplified Skip-Connected UNet for Robust Speaker Verification Under Noisy Environments","display_name":"Simplified Skip-Connected UNet for Robust Speaker Verification Under Noisy Environments","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709680","doi":"https://doi.org/10.1109/iscslp63861.2024.10800205"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800205","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":["School of Computer Science and Technology, Xinjiang University,Urumqi"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University,Urumqi","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000449705","display_name":"Zhihua Fang","orcid":"https://orcid.org/0000-0002-3018-7414"},"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":["School of Computer Science and Technology, Xinjiang University,Urumqi"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University,Urumqi","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020817636","display_name":"Zhida Song","orcid":"https://orcid.org/0000-0002-4987-5962"},"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":"Zhida Song","raw_affiliation_strings":["School of Computer Science and Technology, Xinjiang University,Urumqi"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University,Urumqi","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049944728","display_name":"Liang He","orcid":"https://orcid.org/0000-0003-4076-7479"},"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":["School of Computer Science and Technology, Xinjiang University,Urumqi"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University,Urumqi","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5005177639"],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21936326,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"691","last_page":"695"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9968000054359436,"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":0.9968000054359436,"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":0.9886999726295471,"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":0.9067000150680542,"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":0.7918421626091003},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.7438398599624634},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6011356115341187},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4813145399093628},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.41749805212020874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7918421626091003},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.7438398599624634},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6011356115341187},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4813145399093628},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.41749805212020874},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800205","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2224866389","display_name":null,"funder_award_id":"62366051","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W46095808","https://openalex.org/W1622676895","https://openalex.org/W1901129140","https://openalex.org/W2055611715","https://openalex.org/W2129244720","https://openalex.org/W2194775991","https://openalex.org/W2407127962","https://openalex.org/W2752782242","https://openalex.org/W2890964092","https://openalex.org/W2899754108","https://openalex.org/W2928133111","https://openalex.org/W2962866211","https://openalex.org/W2972425344","https://openalex.org/W3013020904","https://openalex.org/W3024869864","https://openalex.org/W3096641561","https://openalex.org/W3137249133","https://openalex.org/W3196650842","https://openalex.org/W4224934178","https://openalex.org/W4283703262","https://openalex.org/W4297841892","https://openalex.org/W4312938066","https://openalex.org/W4372267288","https://openalex.org/W6637242042"],"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":{"In":[0,41],"recent":[1],"years,":[2],"deep":[3],"neural":[4],"network":[5],"based":[6,80],"methods":[7],"for":[8,94,133],"speaker":[9,28,66,100,134],"verification":[10,29,67,135],"have":[11,126],"made":[12],"remarkable":[13],"progress":[14],"in":[15,117,136],"clean":[16],"environments.":[17,138],"However,":[18],"background":[19],"noise":[20,63,95,122],"significantly":[21],"reduces":[22,85],"the":[23,35,39,55,65,86,109,118],"accuracy":[24],"and":[25,60,97,111],"reliability":[26],"of":[27,38,57,62,73,89,120],"systems":[30],"by":[31],"masking":[32],"or":[33],"changing":[34],"voice":[36],"characteristics":[37],"speaker.":[40],"this":[42,128],"paper,":[43],"we":[44],"propose":[45],"a":[46,76,98],"cascaded":[47],"framework":[48],"optimized":[49],"with":[50],"multiobjective":[51],"loss":[52],"to":[53],"mitigate":[54],"interference":[56],"different":[58],"levels":[59],"types":[61],"on":[64,81,108],"task.":[68],"The":[69,124],"proposed":[70],"architecture":[71],"consists":[72],"two":[74],"components:":[75],"speech":[77],"enhancement":[78],"module":[79],"improved":[82],"2D-UNet,":[83],"which":[84],"structural":[87],"limitations":[88],"directly":[90],"using":[91],"classical":[92],"UNet":[93],"reduction,":[96],"back-end":[99],"embedding":[101],"extraction":[102],"module.":[103],"We":[104],"carry":[105],"our":[106],"experiments":[107],"VoxCeleb1":[110],"VOiCES":[112],"datasets,":[113],"as":[114,116],"well":[115],"presence":[119],"out-of-domain":[121],"conditions.":[123],"evaluations":[125],"demonstrated":[127],"method":[129],"shows":[130],"great":[131],"potential":[132],"noisy":[137]},"counts_by_year":[],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}