{"id":"https://openalex.org/W4292976050","doi":"https://doi.org/10.1109/jstsp.2022.3200915","title":"Augmentation Adversarial Training for Self-Supervised Speaker Representation Learning","display_name":"Augmentation Adversarial Training for Self-Supervised Speaker Representation Learning","publication_year":2022,"publication_date":"2022-08-22","ids":{"openalex":"https://openalex.org/W4292976050","doi":"https://doi.org/10.1109/jstsp.2022.3200915"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2022.3200915","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3200915","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-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/A5003313894","display_name":"Jingu Kang","orcid":"https://orcid.org/0000-0002-9284-5945"},"institutions":[{"id":"https://openalex.org/I191879574","display_name":"Inha University","ror":"https://ror.org/01easw929","country_code":"KR","type":"education","lineage":["https://openalex.org/I191879574"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jingu Kang","raw_affiliation_strings":["Inha University, Incheon, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-9284-5945","affiliations":[{"raw_affiliation_string":"Inha University, Incheon, South Korea","institution_ids":["https://openalex.org/I191879574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114067866","display_name":"Jaesung Huh","orcid":"https://orcid.org/0000-0001-7247-6401"},"institutions":[{"id":"https://openalex.org/I2802123492","display_name":"Oxford Research Group","ror":"https://ror.org/00z4w4f29","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2802123492"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jaesung Huh","raw_affiliation_strings":["Visual Geometry Group, University of Oxford, Oxford, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Visual Geometry Group, University of Oxford, Oxford, U.K","institution_ids":["https://openalex.org/I2802123492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112876029","display_name":"Hee Soo Heo","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hee Soo Heo","raw_affiliation_strings":["Naver Corporation, Seongnam-si, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Naver Corporation, Seongnam-si, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":["Korea Advanced Institute of Science, and Technology, Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0000-0001-7741-7275","affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science, and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5003313894"],"corresponding_institution_ids":["https://openalex.org/I191879574"],"apc_list":null,"apc_paid":null,"fwci":2.2197,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.89513516,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"16","issue":"6","first_page":"1253","last_page":"1262"},"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/T11309","display_name":"Music and Audio Processing","score":0.9951000213623047,"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/T10860","display_name":"Speech and Audio Processing","score":0.9916999936103821,"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":0.799993634223938},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7484235763549805},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7446180582046509},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6213443279266357},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6011335849761963},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5853236317634583},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5276378989219666},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5274924039840698},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4552024006843567},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.41410428285598755},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37291815876960754},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07906872034072876}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.799993634223938},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7484235763549805},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7446180582046509},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6213443279266357},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6011335849761963},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5853236317634583},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5276378989219666},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5274924039840698},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4552024006843567},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.41410428285598755},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37291815876960754},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07906872034072876},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jstsp.2022.3200915","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3200915","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W2100495367","https://openalex.org/W2101261946","https://openalex.org/W2123768812","https://openalex.org/W2150769028","https://openalex.org/W2214409633","https://openalex.org/W2219249508","https://openalex.org/W2326925005","https://openalex.org/W2502312327","https://openalex.org/W2516764878","https://openalex.org/W2604379605","https://openalex.org/W2619697695","https://openalex.org/W2726515241","https://openalex.org/W2801581493","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2939763029","https://openalex.org/W2962699416","https://openalex.org/W2962788262","https://openalex.org/W2962788625","https://openalex.org/W2963040451","https://openalex.org/W2963386851","https://openalex.org/W2963420272","https://openalex.org/W2963450999","https://openalex.org/W2963902346","https://openalex.org/W2964154960","https://openalex.org/W2972894903","https://openalex.org/W2998115938","https://openalex.org/W3010925296","https://openalex.org/W3013020904","https://openalex.org/W3015443711","https://openalex.org/W3015598461","https://openalex.org/W3015734344","https://openalex.org/W3023351797","https://openalex.org/W3024869864","https://openalex.org/W3025075133","https://openalex.org/W3034781633","https://openalex.org/W3035524453","https://openalex.org/W3108655343","https://openalex.org/W3163505255","https://openalex.org/W4289750118","https://openalex.org/W6631362777","https://openalex.org/W6688816777","https://openalex.org/W6713727690","https://openalex.org/W6724804524","https://openalex.org/W6735236233","https://openalex.org/W6753575415","https://openalex.org/W6761233929","https://openalex.org/W6763416564","https://openalex.org/W6774314701","https://openalex.org/W6779230768","https://openalex.org/W6779326418","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W2529301793","https://openalex.org/W3148366653","https://openalex.org/W3208297503","https://openalex.org/W3119773509","https://openalex.org/W2889153461","https://openalex.org/W2964117661","https://openalex.org/W4388405611","https://openalex.org/W2619127353"],"abstract_inverted_index":{"The":[0],"goal":[1],"of":[2,138,145,163],"this":[3,65],"work":[4],"is":[5,53],"to":[6,33,39,55,78,87,101,104,110,113,153],"train":[7],"robust":[8],"speaker":[9,20,58,83,164],"recognition":[10],"models":[11,141],"using":[12,133],"self-supervised":[13,19,140],"representation":[14],"learning.":[15],"Recent":[16],"works":[17,132],"on":[18,24,121],"representations":[21],"are":[22],"based":[23],"contrastive":[25],"learning":[26,151],"in":[27,117,161],"which":[28],"they":[29],"encourage":[30],"within-utterance":[31,45],"embeddings":[32,38],"be":[34,40,79,102,111],"similar":[35],"and":[36,124,135],"across-utterance":[37],"dissimilar.":[41],"However,":[42],"since":[43],"the":[44,48,57,61,76,82,88,92,95,99,108,114,122,136],"segments":[46],"share":[47],"same":[49],"acoustic":[50,96],"characteristics,":[51,97],"it":[52],"difficult":[54],"separate":[56],"information":[59,116],"from":[60],"channel":[62,115],"information.":[63],"To":[64],"end,":[66],"we":[67],"propose":[68],"an":[69],"augmentation":[70,89,93,105,156],"adversarial":[71,157],"training":[72,98,158],"strategy":[73],"that":[74,144,155],"trains":[75],"network":[77,100,109],"discriminative":[80],"for":[81],"information,":[84],"while":[85],"invariant":[86,103,112],"applied.":[90],"Since":[91],"simulates":[94],"also":[106,148],"encourages":[107],"general.":[118],"Extensive":[119],"experiments":[120,152],"VoxCeleb":[123],"VOiCES":[125],"datasets":[126],"show":[127,154],"significant":[128],"improvements":[129],"over":[130],"previous":[131],"self-supervision,":[134],"performance":[137,160],"our":[139],"far":[142],"exceeds":[143],"humans.":[146],"We":[147],"conduct":[149],"semi-supervised":[150],"benefits":[159],"presence":[162],"labels.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}