{"id":"https://openalex.org/W4224917963","doi":"https://doi.org/10.1109/icassp43922.2022.9747364","title":"Domain Robust Deep Embedding Learning for Speaker Recognition","display_name":"Domain Robust Deep Embedding Learning for Speaker Recognition","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224917963","doi":"https://doi.org/10.1109/icassp43922.2022.9747364"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747364","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747364","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/conference_contribution/Domain_Robust_Deep_Embedding_Learning_for_Speaker_Recognition/24217284","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109948403","display_name":"Hang-Rui Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hang-Rui Hu","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,China","National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100381758","display_name":"Yan Song","orcid":"https://orcid.org/0000-0002-5668-9068"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Song","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,China","National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100414442","display_name":"Ying Liu","orcid":"https://orcid.org/0000-0003-3121-1276"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Liu","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,China","National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li-Rong Dai","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,China","National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000620878","display_name":"Ian McLoughlin","orcid":"https://orcid.org/0000-0001-7111-2008"},"institutions":[{"id":"https://openalex.org/I168639165","display_name":"Singapore Institute of Technology","ror":"https://ror.org/01v2c2791","country_code":"SG","type":"education","lineage":["https://openalex.org/I168639165"]},{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Ian McLoughlin","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,China","ICT Cluster, Singapore Institute of Technology, Singapore","National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"ICT Cluster, Singapore Institute of Technology, Singapore","institution_ids":["https://openalex.org/I168639165"]},{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100383342","display_name":"Lin Liu","orcid":"https://orcid.org/0000-0003-2843-5738"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin Liu","raw_affiliation_strings":["iFLYTEK CO. LTD.,iFLYTEK Research,Hefei,China","iFLYTEK Research, iFLYTEK CO. LTD., Hefei, China"],"affiliations":[{"raw_affiliation_string":"iFLYTEK CO. LTD.,iFLYTEK Research,Hefei,China","institution_ids":[]},{"raw_affiliation_string":"iFLYTEK Research, iFLYTEK CO. LTD., Hefei, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5109948403"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":1.2465,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.80990088,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7182","last_page":"7186"},"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":0.996399998664856,"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":0.9922999739646912,"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/nist","display_name":"NIST","score":0.8147241473197937},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8122417330741882},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7911593914031982},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7893080711364746},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6850807666778564},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5978447794914246},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5209487676620483},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.519943118095398},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.519605815410614},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5040044188499451},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4803784489631653},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4582350552082062},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45253899693489075},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.45213666558265686},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4382352828979492},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08113265037536621},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.0688433051109314}],"concepts":[{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.8147241473197937},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8122417330741882},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7911593914031982},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7893080711364746},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6850807666778564},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5978447794914246},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5209487676620483},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.519943118095398},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.519605815410614},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5040044188499451},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4803784489631653},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4582350552082062},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45253899693489075},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.45213666558265686},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4382352828979492},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08113265037536621},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0688433051109314},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747364","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747364","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:figshare.com:article/24217284","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Domain_Robust_Deep_Embedding_Learning_for_Speaker_Recognition/24217284","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/24217284","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Domain_Robust_Deep_Embedding_Learning_for_Speaker_Recognition/24217284","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1821462560","https://openalex.org/W2114925438","https://openalex.org/W2181594395","https://openalex.org/W2183016404","https://openalex.org/W2183341477","https://openalex.org/W2404617565","https://openalex.org/W2572730214","https://openalex.org/W2603777577","https://openalex.org/W2612434969","https://openalex.org/W2747741332","https://openalex.org/W2748488820","https://openalex.org/W2807246346","https://openalex.org/W2808631503","https://openalex.org/W2884366600","https://openalex.org/W2890964092","https://openalex.org/W2936780106","https://openalex.org/W2962788262","https://openalex.org/W2963275094","https://openalex.org/W2963446838","https://openalex.org/W2963450999","https://openalex.org/W2964154960","https://openalex.org/W2964216323","https://openalex.org/W2964288524","https://openalex.org/W3015964387","https://openalex.org/W3034727830","https://openalex.org/W3034756453","https://openalex.org/W3097000690","https://openalex.org/W3160646455","https://openalex.org/W3165865052","https://openalex.org/W3197934710","https://openalex.org/W6631362777","https://openalex.org/W6638523607","https://openalex.org/W6720111944","https://openalex.org/W6737575990"],"related_works":["https://openalex.org/W2158491338","https://openalex.org/W2807901368","https://openalex.org/W2133733652","https://openalex.org/W2072658171","https://openalex.org/W1617617605","https://openalex.org/W4287755480","https://openalex.org/W3113607506","https://openalex.org/W4297779039","https://openalex.org/W2578444090","https://openalex.org/W2963548962"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,90,112,134,148],"domain":[4],"robust":[5,160],"deep":[6,19],"embedding":[7],"learning":[8,119],"method":[9,120],"for":[10,52],"speaker":[11,28,98],"verification":[12],"(SV)":[13],"tasks.":[14],"Most":[15],"recent":[16],"methods":[17],"utilize":[18],"neural":[20],"networks":[21],"(DNN)":[22],"to":[23,58,79,96,123,141,155,161],"learn":[24,97,156],"compact":[25],"and":[26,37,64,72,104],"discriminative":[27],"embeddings":[29,99],"from":[30,100,128],"large-scale":[31],"labeled":[32,102],"datasets":[33],"such":[34],"as":[35],"VoxCeleb":[36],"the":[38,43,59,73,129,143],"NIST":[39,166],"SRE":[40],"corpus.":[41],"Despite":[42],"success":[44],"of":[45],"exiting":[46],"methods,":[47],"performance":[48,170],"may":[49],"degrade":[50],"significantly":[51],"new":[53],"target":[54,106,131],"datasets,":[55],"mainly":[56],"due":[57],"distribution":[60,145],"discrepancy":[61],"between":[62],"training":[63],"test":[65],"domains.":[66,86],"Moreover,":[67],"how":[68],"corpora":[69],"are":[70,159],"collected,":[71],"languages":[74],"they":[75],"contain":[76],"differ,":[77],"leading":[78],"them":[80],"spanning":[81],"multiple,":[82],"perhaps":[83],"mismatched,":[84],"latent":[85,125],"To":[87],"address":[88],"this,":[89],"multi-task":[91],"end-to-end":[92],"framework":[93],"is":[94,121],"proposed":[95],"both":[101],"source":[103],"unlabeled":[105,130],"datasets.":[107],"Motivated":[108],"by":[109],"label":[110],"smoothing,":[111],"smoothed":[113],"knowledge":[114],"distillation":[115],"(SKD)":[116],"based":[117],"self-supervised":[118],"designed":[122],"exploit":[124],"structural":[126],"information":[127],"domain.":[132],"Furthermore,":[133],"domain-aware":[135],"batch":[136],"normalization":[137,151],"(DABN)":[138],"module":[139,153],"aims":[140,154],"reduce":[142],"cross-domain":[144],"discrepancy,":[146],"while":[147],"domain-agnostic":[149],"instance":[150],"(DAIN)":[152],"features":[157],"that":[158],"within-domain":[162],"variance.":[163],"Evaluation":[164],"on":[165],"SRE16":[167],"demonstrates":[168],"significant":[169],"gains.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}