{"id":"https://openalex.org/W3044308976","doi":null,"title":"Augmentation adversarial training for unsupervised speaker recognition.","display_name":"Augmentation adversarial training for unsupervised speaker recognition.","publication_year":2020,"publication_date":"2020-07-23","ids":{"openalex":"https://openalex.org/W3044308976","mag":"3044308976"},"language":"en","primary_location":{"id":"mag:3044308976","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2007.12085.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2007.12085.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114067866","display_name":"Jaesung Huh","orcid":"https://orcid.org/0000-0001-7247-6401","observed_orcids":["https://orcid.org/0000-0001-7247-6401"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaesung Huh","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-7247-6401","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112876029","display_name":"Hee Soo Heo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hee Soo Heo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039455262","display_name":"Jingu Kang","orcid":"https://orcid.org/0000-0003-2063-2972","observed_orcids":["https://orcid.org/0000-0003-2063-2972"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingu Kang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-2063-2972","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631","observed_orcids":["https://orcid.org/0000-0002-5970-8631"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-5970-8631","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275","observed_orcids":["https://orcid.org/0000-0001-7741-7275"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-7741-7275","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9955999851226807,"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":0.9955999851226807,"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":0.002199999988079071,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/self-supervised-learning","display_name":"self-supervised learning","score":0.8140000104904175},{"id":"https://openalex.org/keywords/contrastive-learning","display_name":"contrastive learning","score":0.8130000233650208},{"id":"https://openalex.org/keywords/speaker-representation-learning","display_name":"speaker representation learning","score":0.6140000224113464}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7758437395095825},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7684159874916077},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7408128380775452},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7034652829170227},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5716280937194824},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.548491895198822},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5324241518974304},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49495166540145874},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4646548628807068},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4584391415119171},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.44652724266052246},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07308849692344666},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3044308976","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2007.12085.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3044308976","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2007.12085.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1731081199","https://openalex.org/W1999408164","https://openalex.org/W2100495367","https://openalex.org/W2101261946","https://openalex.org/W2123768812","https://openalex.org/W2147145909","https://openalex.org/W2150769028","https://openalex.org/W2214409633","https://openalex.org/W2219249508","https://openalex.org/W2342877626","https://openalex.org/W2406312423","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/W2806993054","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2900022717","https://openalex.org/W2900157271","https://openalex.org/W2900161882","https://openalex.org/W2902368158","https://openalex.org/W2936229313","https://openalex.org/W2939763029","https://openalex.org/W2949517790","https://openalex.org/W2962788625","https://openalex.org/W2963040451","https://openalex.org/W2970971581","https://openalex.org/W2971155163","https://openalex.org/W2994536315","https://openalex.org/W3010925296","https://openalex.org/W3013020904","https://openalex.org/W3015443711","https://openalex.org/W3015734344","https://openalex.org/W3023351797","https://openalex.org/W3025075133","https://openalex.org/W3034978746","https://openalex.org/W4289750118","https://openalex.org/W7208177202"],"related_works":["https://openalex.org/W4394665180","https://openalex.org/W4292976050","https://openalex.org/W4200633018","https://openalex.org/W4319862473","https://openalex.org/W2982817420","https://openalex.org/W4221161775","https://openalex.org/W4224917505","https://openalex.org/W4416799023","https://openalex.org/W3112495938","https://openalex.org/W7219614487"],"abstract_inverted_index":{"The":[0],"goal":[1],"of":[2,136,143],"this":[3,64],"work":[4],"is":[5,52],"to":[6,32,38,54,76,85,99,102,108,111],"train":[7],"robust":[8],"speaker":[9,13,19,57,81],"recognition":[10],"models":[11,139],"without":[12],"labels.":[14],"Recent":[15],"works":[16,130],"on":[17,23,119],"unsupervised":[18],"representations":[20],"are":[21],"based":[22],"contrastive":[24],"learning":[25],"in":[26,115],"which":[27],"they":[28],"encourage":[29],"within-utterance":[30,44],"embeddings":[31,37],"be":[33,39,77,100,109],"similar":[34],"and":[35,122,133],"across-utterance":[36],"dissimilar.":[40],"However,":[41],"since":[42],"the":[43,47,56,60,74,80,86,90,93,97,106,112,120,134],"segments":[45],"share":[46],"same":[48],"acoustic":[49,94],"characteristics,":[50,95],"it":[51],"difficult":[53],"separate":[55],"information":[58,114],"from":[59],"channel":[61,113],"information.":[62],"To":[63],"end,":[65],"we":[66],"propose":[67],"augmentation":[68,87,91,103],"adversarial":[69],"training":[70,96],"strategy":[71],"that":[72,142],"trains":[73],"network":[75,98,107],"discriminative":[78],"for":[79],"information,":[82],"while":[83],"invariant":[84,101,110],"applied.":[88],"Since":[89],"simulates":[92],"also":[104],"encourages":[105],"general.":[116],"Extensive":[117],"experiments":[118],"VoxCeleb":[121],"VOiCES":[123],"datasets":[124],"show":[125],"significant":[126],"improvements":[127],"over":[128],"previous":[129],"using":[131],"self-supervision,":[132],"performance":[135],"our":[137],"self-supervised":[138],"far":[140],"exceed":[141],"humans.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":4}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2020-07-29T00:00:00"}