{"id":"https://openalex.org/W3015231328","doi":"https://doi.org/10.1109/icassp40776.2020.9053407","title":"Within-Sample Variability-Invariant Loss for Robust Speaker Recognition Under Noisy Environments","display_name":"Within-Sample Variability-Invariant Loss for Robust Speaker Recognition Under Noisy Environments","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015231328","doi":"https://doi.org/10.1109/icassp40776.2020.9053407","mag":"3015231328"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053407","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5090055875","display_name":"Danwei Cai","orcid":"https://orcid.org/0000-0002-5122-0623"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Danwei Cai","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Duke University, Durham, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Duke University, Durham, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103888187","display_name":"Weicheng Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weicheng Cai","raw_affiliation_strings":["Data Science Research Center, Duke Kunshan University, Kunshan, China"],"affiliations":[{"raw_affiliation_string":"Data Science Research Center, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100351449","display_name":"Ming Li","orcid":"https://orcid.org/0000-0002-6406-1983"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Duke University, Durham, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Duke University, Durham, USA","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5090055875"],"corresponding_institution_ids":["https://openalex.org/I170897317"],"apc_list":null,"apc_paid":null,"fwci":4.3745,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.95261453,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6469","last_page":"6473"},"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":0.9994000196456909,"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":0.9980000257492065,"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/utterance","display_name":"Utterance","score":0.739497721195221},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7372692227363586},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7350742816925049},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7242505550384521},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6150528192520142},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5547072291374207},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5465724468231201},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.52861088514328},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.4891689121723175},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4569336771965027},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4336685240268707},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13837897777557373}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.739497721195221},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7372692227363586},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7350742816925049},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7242505550384521},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6150528192520142},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5547072291374207},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5465724468231201},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.52861088514328},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.4891689121723175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4569336771965027},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4336685240268707},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13837897777557373},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053407","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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":31,"referenced_works":["https://openalex.org/W2055611715","https://openalex.org/W2114719288","https://openalex.org/W2129379984","https://openalex.org/W2139959413","https://openalex.org/W2150769028","https://openalex.org/W2180339972","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2326699523","https://openalex.org/W2397634864","https://openalex.org/W2407127962","https://openalex.org/W2513927927","https://openalex.org/W2586068394","https://openalex.org/W2726515241","https://openalex.org/W2746742816","https://openalex.org/W2885724687","https://openalex.org/W2890964092","https://openalex.org/W2901368553","https://openalex.org/W2916104401","https://openalex.org/W2937328535","https://openalex.org/W2937813194","https://openalex.org/W2963077989","https://openalex.org/W2963103750","https://openalex.org/W2963371159","https://openalex.org/W2963466847","https://openalex.org/W2972425344","https://openalex.org/W2972697221","https://openalex.org/W4206633762","https://openalex.org/W6688816777","https://openalex.org/W6756075375"],"related_works":["https://openalex.org/W2126085626","https://openalex.org/W1521299571","https://openalex.org/W2767892728","https://openalex.org/W3141593045","https://openalex.org/W1998549096","https://openalex.org/W1996621592","https://openalex.org/W2134501921","https://openalex.org/W3048257020","https://openalex.org/W204267554","https://openalex.org/W2545131480"],"abstract_inverted_index":{"Despite":[0],"the":[1,23,29,33,37,42,61,65,74,78,84,90,109,118,132,137,140],"significant":[2],"improvements":[3],"in":[4,144],"speaker":[5,24,44,85,119,141],"recognition":[6],"enabled":[7],"by":[8],"deep":[9],"neural":[10],"networks,":[11],"unsatisfactory":[12],"performance":[13,138],"persists":[14],"under":[15,124],"noisy":[16,34,70,98,106,125,148],"environments.":[17,126],"In":[18],"this":[19],"paper,":[20],"we":[21,88],"train":[22],"embedding":[25,31,63,120],"network":[26,38,75,121],"to":[27,59],"learn":[28,60],"\"clean\"":[30],"of":[32,139],"utterance.":[35],"Specifically,":[36],"is":[39,57],"trained":[40],"with":[41,47],"original":[43],"identification":[45],"loss":[46,56],"an":[48],"auxiliary":[49,54],"within-sample":[50],"variability-invariant":[51,55],"loss.":[52],"This":[53],"used":[58],"same":[62,110],"among":[64],"clean":[66,96,111,146],"utterance":[67,99,112],"and":[68,72,97,147],"its":[69],"copies":[71,107],"prevents":[73],"from":[76],"encoding":[77],"undesired":[79],"noises":[80],"or":[81],"variabilities":[82],"into":[83],"representation.":[86],"Furthermore,":[87],"investigate":[89],"data":[91],"preparation":[92],"strategy":[93,103],"for":[94,108],"generating":[95],"pairs":[100],"on-the-fly.":[101],"The":[102],"generates":[104],"different":[105],"at":[113],"each":[114],"training":[115,134],"step,":[116],"helping":[117],"generalize":[122],"better":[123],"Experiments":[127],"on":[128],"VoxCeleb1":[129],"indicate":[130],"that":[131],"proposed":[133],"framework":[135],"improves":[136],"verification":[142],"system":[143],"both":[145],"conditions.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":10}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}