{"id":"https://openalex.org/W3133917823","doi":"https://doi.org/10.1109/iscslp49672.2021.9362053","title":"Adversarial Training for Multi-domain Speaker Recognition","display_name":"Adversarial Training for Multi-domain Speaker Recognition","publication_year":2021,"publication_date":"2021-01-24","ids":{"openalex":"https://openalex.org/W3133917823","doi":"https://doi.org/10.1109/iscslp49672.2021.9362053","mag":"3133917823"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp49672.2021.9362053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp49672.2021.9362053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th 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/A5100434894","display_name":"Qing Wang","orcid":"https://orcid.org/0000-0003-3439-0644"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Wang","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035226758","display_name":"Wei Rao","orcid":"https://orcid.org/0000-0002-7237-0874"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Rao","raw_affiliation_strings":["Tencent Media Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Media Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101783173","display_name":"Pengcheng Guo","orcid":"https://orcid.org/0009-0001-2388-5935"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengcheng Guo","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9795,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.80039956,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"17","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":0.9997000098228455,"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":0.9997000098228455,"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":0.9865999817848206,"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":0.9746999740600586,"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":0.8452562689781189},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7914217710494995},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6715868711471558},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.640662431716919},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6164134740829468},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5618259906768799},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.5524008274078369},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5487349033355713},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5245782732963562},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.513263463973999},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.354050874710083},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.1094532310962677},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08363422751426697}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8452562689781189},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7914217710494995},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6715868711471558},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.640662431716919},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6164134740829468},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5618259906768799},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.5524008274078369},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5487349033355713},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5245782732963562},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.513263463973999},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.354050874710083},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.1094532310962677},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08363422751426697},{"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/iscslp49672.2021.9362053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp49672.2021.9362053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.75,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W123007118","https://openalex.org/W866349134","https://openalex.org/W1480629789","https://openalex.org/W1505813640","https://openalex.org/W1731081199","https://openalex.org/W1882958252","https://openalex.org/W2067301010","https://openalex.org/W2073017590","https://openalex.org/W2121812409","https://openalex.org/W2124112941","https://openalex.org/W2150769028","https://openalex.org/W2166637769","https://openalex.org/W2360384684","https://openalex.org/W2395750323","https://openalex.org/W2517850878","https://openalex.org/W2788768841","https://openalex.org/W2801581493","https://openalex.org/W2888473984","https://openalex.org/W2890964092","https://openalex.org/W2907380995","https://openalex.org/W2916058012","https://openalex.org/W2936595123","https://openalex.org/W2936780106","https://openalex.org/W2962679215","https://openalex.org/W2962684181","https://openalex.org/W2963826681","https://openalex.org/W2972864786","https://openalex.org/W2972908178","https://openalex.org/W2973099347","https://openalex.org/W3011500442","https://openalex.org/W3026494492","https://openalex.org/W3038083940","https://openalex.org/W3095570773","https://openalex.org/W6605010638","https://openalex.org/W6623950054","https://openalex.org/W6637618735","https://openalex.org/W6639480849","https://openalex.org/W6757304564"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W3148366653","https://openalex.org/W4312246223","https://openalex.org/W3211393740","https://openalex.org/W3208049411","https://openalex.org/W3022908591","https://openalex.org/W3172695526","https://openalex.org/W4285706568","https://openalex.org/W2531741693"],"abstract_inverted_index":{"In":[0,85],"real-life":[1],"applications,":[2],"the":[3,31,100,104,110,134,143,150],"performance":[4],"of":[5,48,54],"speaker":[6,35,82,96,125],"recognition":[7,83,97],"systems":[8],"always":[9],"degrades":[10],"when":[11],"there":[12],"is":[13,137],"a":[14],"mismatch":[15,102,145],"between":[16],"training":[17,40,93],"and":[18,41,103,120],"evaluation":[19,42],"data.":[20],"Many":[21],"domain":[22,32,71,101,153],"adaptation":[23,154],"methods":[24],"have":[25],"been":[26],"successfully":[27],"used":[28],"for":[29,94,124],"eliminating":[30],"mismatches":[33],"in":[34,67],"recognition.":[36,126],"However,":[37],"usually":[38],"both":[39,118],"data":[43],"themselves":[44],"can":[45,57,73],"be":[46,59],"composed":[47],"several":[49],"subsets.":[50],"These":[51],"inner":[52],"variances":[53],"each":[55],"dataset":[56,72,105,131],"also":[58,74,148],"considered":[60],"as":[61],"different":[62],"domains.":[63],"Different":[64],"distributed":[65],"subsets":[66],"source":[68],"or":[69],"target":[70],"cause":[75],"multi-domain":[76,95,144],"mismatches,":[77],"which":[78],"are":[79,114],"influential":[80],"to":[81,90,98,116,141],"performance.":[84],"this":[86],"study,":[87],"we":[88,113],"propose":[89],"use":[91],"adversarial":[92],"solve":[99,142],"variance":[106],"problems.":[107],"By":[108],"adopting":[109],"proposed":[111,135],"method,":[112],"able":[115],"obtain":[117],"multi-domain-invariant":[119],"speaker-discriminative":[121],"speech":[122],"representations":[123],"Experimental":[127],"results":[128],"on":[129],"DAC13":[130],"indicate":[132],"that":[133],"method":[136],"not":[138],"only":[139],"effective":[140],"problem,":[146],"but":[147],"outperforms":[149],"compared":[151],"unsupervised":[152],"methods.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}