{"id":"https://openalex.org/W4372348291","doi":"https://doi.org/10.1109/icassp49357.2023.10094698","title":"Stargan-vc Based Cross-Domain Data Augmentation for Speaker Verification","display_name":"Stargan-vc Based Cross-Domain Data Augmentation for Speaker Verification","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372348291","doi":"https://doi.org/10.1109/icassp49357.2023.10094698"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5109948403","display_name":"Hang-Rui Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]},{"id":"https://openalex.org/I4210103894","display_name":"Hefei National Center for Physical Sciences at Nanoscale","ror":"https://ror.org/01jeedh73","country_code":"CN","type":"facility","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366","https://openalex.org/I4210103894"]},{"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 Research Center for Speech and Language Information Processing,Hefei,China","Alibaba Group, China","National Engineering Research Center 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 Research Center for Speech and Language Information Processing,Hefei,China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I4210103894"]},{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"National Engineering Research Center 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"]},{"id":"https://openalex.org/I4210103894","display_name":"Hefei National Center for Physical Sciences at Nanoscale","ror":"https://ror.org/01jeedh73","country_code":"CN","type":"facility","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366","https://openalex.org/I4210103894"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Song","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center for Speech and Language Information Processing,Hefei,China","National Engineering Research Center 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 Research Center for Speech and Language Information Processing,Hefei,China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I4210103894"]},{"raw_affiliation_string":"National Engineering Research Center 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/A5100781674","display_name":"Jiantao Zhang","orcid":"https://orcid.org/0000-0001-8418-9047"},"institutions":[{"id":"https://openalex.org/I4210103894","display_name":"Hefei National Center for Physical Sciences at Nanoscale","ror":"https://ror.org/01jeedh73","country_code":"CN","type":"facility","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366","https://openalex.org/I4210103894"]},{"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":"Jian-Tao Zhang","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center for Speech and Language Information Processing,Hefei,China","National Engineering Research Center 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 Research Center for Speech and Language Information Processing,Hefei,China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I4210103894"]},{"raw_affiliation_string":"National Engineering Research Center 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/I4210103894","display_name":"Hefei National Center for Physical Sciences at Nanoscale","ror":"https://ror.org/01jeedh73","country_code":"CN","type":"facility","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366","https://openalex.org/I4210103894"]},{"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 Research Center for Speech and Language Information Processing,Hefei,China","National Engineering Research Center 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 Research Center for Speech and Language Information Processing,Hefei,China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I4210103894"]},{"raw_affiliation_string":"National Engineering Research Center 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/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"]},{"id":"https://openalex.org/I4210103894","display_name":"Hefei National Center for Physical Sciences at Nanoscale","ror":"https://ror.org/01jeedh73","country_code":"CN","type":"facility","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366","https://openalex.org/I4210103894"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ian McLoughlin","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center for Speech and Language Information Processing,Hefei,China","National Engineering Research Center 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 Research Center for Speech and Language Information Processing,Hefei,China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I4210103894"]},{"raw_affiliation_string":"National Engineering Research Center 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/A5002973086","display_name":"Zhu Zhuo","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhu Zhuo","raw_affiliation_strings":["Alibaba Group,China","Alibaba Group, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013277301","display_name":"Yu Zhou","orcid":"https://orcid.org/0000-0002-4193-311X"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhou","raw_affiliation_strings":["Alibaba Group,China","Alibaba Group, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341177","display_name":"Yuhong Li","orcid":"https://orcid.org/0009-0009-9185-7133"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Hong Li","raw_affiliation_strings":["Alibaba Group,China","Alibaba Group, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050108117","display_name":"Hui Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Xue","raw_affiliation_strings":["Alibaba Group,China","Alibaba Group, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5109948403"],"corresponding_institution_ids":["https://openalex.org/I126520041","https://openalex.org/I4210103894","https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":0.3497,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63085395,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"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/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":0.9994999766349792,"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":0.998199999332428,"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":0.7581565380096436},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5659672021865845},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5089676380157471},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.2646121382713318},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.24963587522506714},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05659019947052002}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7581565380096436},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5659672021865845},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5089676380157471},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2646121382713318},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.24963587522506714},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05659019947052002},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W125553504","https://openalex.org/W1524333225","https://openalex.org/W2402146185","https://openalex.org/W2888968865","https://openalex.org/W2890964092","https://openalex.org/W2914282508","https://openalex.org/W2936028438","https://openalex.org/W2963057973","https://openalex.org/W2963539064","https://openalex.org/W2963767194","https://openalex.org/W2964054038","https://openalex.org/W2969985801","https://openalex.org/W2970006822","https://openalex.org/W2972667718","https://openalex.org/W3008883495","https://openalex.org/W3015598461","https://openalex.org/W3024869864","https://openalex.org/W3097000690","https://openalex.org/W3110137169","https://openalex.org/W3160076723","https://openalex.org/W3197934710","https://openalex.org/W4206908380","https://openalex.org/W4283458492","https://openalex.org/W6631362777","https://openalex.org/W6759048824","https://openalex.org/W6767111847","https://openalex.org/W6839093550"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"Automatic":[0],"speaker":[1],"verification":[2],"(ASV)":[3],"faces":[4],"domain":[5,44,99],"shift":[6],"caused":[7],"by":[8,78],"the":[9,51,55,106,110,114,123,132,146,155,160],"mismatch":[10],"of":[11,54,109,142,150,159],"intrinsic":[12],"and":[13,20,95,118,127,152],"extrinsic":[14],"factors,":[15],"such":[16],"as":[17],"recording":[18],"device":[19],"speaking":[21],"style,":[22],"in":[23,41,148],"real-world":[24],"applications,":[25],"which":[26],"leads":[27],"to":[28,39,49,71,130],"severe":[29],"performance":[30,140],"degradation.":[31],"Since":[32],"single-speaker":[33],"multi-condition":[34],"(SSMC)":[35],"data":[36,68,100],"is":[37],"difficult":[38],"collect":[40],"practice,":[42],"existing":[43],"adaptation":[45,133],"methods":[46],"are":[47],"hard":[48],"ensure":[50],"feature":[52],"consistency":[53],"same":[56],"class":[57],"but":[58],"different":[59],"domains.":[60],"To":[61],"this":[62],"end,":[63],"we":[64,121],"propose":[65],"a":[66,73,83,138],"cross-domain":[67,90],"generation":[69],"method":[70],"obtain":[72],"domain-invariant":[74],"ASV":[75,117],"system.":[76],"Inspired":[77],"voice":[79],"conversion":[80],"(VC)":[81],"task,":[82,120],"StarGAN":[84],"based":[85],"generative":[86],"model":[87],"first":[88],"learns":[89],"mappings":[91],"from":[92],"SSMC":[93],"data,":[94],"then":[96],"generates":[97],"missing":[98],"for":[101],"all":[102],"speakers,":[103],"thus":[104],"increasing":[105],"intra-class":[107],"diversity":[108],"training":[111,125],"set.":[112],"Considering":[113],"difference":[115],"between":[116],"VC":[119],"renovate":[122],"corresponding":[124],"objectives":[126],"network":[128],"structure":[129],"make":[131],"task-specific.":[134],"Evaluations":[135],"on":[136],"achieve":[137],"relative":[139],"improvement":[141],"about":[143],"5-8%":[144],"over":[145],"baseline":[147],"terms":[149],"minDCF":[151],"EER,":[153],"outperforming":[154],"CNSRC":[156],"winner\u2019s":[157],"system":[158],"equivalent":[161],"scale.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}
