{"id":"https://openalex.org/W3049278490","doi":"https://doi.org/10.1109/taslp.2020.3016498","title":"Data Augmentation Using Deep Generative Models for Embedding Based Speaker Recognition","display_name":"Data Augmentation Using Deep Generative Models for Embedding Based Speaker Recognition","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3049278490","doi":"https://doi.org/10.1109/taslp.2020.3016498","mag":"3049278490"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.3016498","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3016498","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language 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/A5100328340","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0003-1523-9631"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["SpeechLab, Department of Computer Science and Engineering & MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1523-9631","affiliations":[{"raw_affiliation_string":"SpeechLab, Department of Computer Science and Engineering & MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057050425","display_name":"Yexin Yang","orcid":"https://orcid.org/0000-0001-9597-9829"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yexin Yang","raw_affiliation_strings":["SpeechLab, Department of Computer Science and Engineering & MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9597-9829","affiliations":[{"raw_affiliation_string":"SpeechLab, Department of Computer Science and Engineering & MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082308834","display_name":"Zhanghao Wu","orcid":"https://orcid.org/0000-0003-2352-4002"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanghao Wu","raw_affiliation_strings":["SpeechLab, Department of Computer Science and Engineering & MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-2352-4002","affiliations":[{"raw_affiliation_string":"SpeechLab, Department of Computer Science and Engineering & MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["SpeechLab, Department of Computer Science and Engineering & MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0314-3790","affiliations":[{"raw_affiliation_string":"SpeechLab, Department of Computer Science and Engineering & MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":["SpeechLab, Department of Computer Science and Engineering & MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-7102-9826","affiliations":[{"raw_affiliation_string":"SpeechLab, Department of Computer Science and Engineering & MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":4.5631,"has_fulltext":false,"cited_by_count":57,"citation_normalized_percentile":{"value":0.95651279,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"28","issue":null,"first_page":"2598","last_page":"2609"},"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":0.9997000098228455,"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":0.996999979019165,"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/robustness","display_name":"Robustness (evolution)","score":0.7729507088661194},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7688193321228027},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6945617198944092},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6274102926254272},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5483409762382507},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5200654864311218},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.5069432258605957},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4579848349094391},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.4450732469558716}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7729507088661194},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7688193321228027},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6945617198944092},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6274102926254272},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5483409762382507},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5200654864311218},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.5069432258605957},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4579848349094391},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.4450732469558716},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2020.3016498","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3016498","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2564042278","display_name":null,"funder_award_id":"2017YFB1302402","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G257170","display_name":null,"funder_award_id":"U1736202","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":77,"referenced_works":["https://openalex.org/W128628490","https://openalex.org/W204053250","https://openalex.org/W577640895","https://openalex.org/W1006777433","https://openalex.org/W1492587309","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1589137271","https://openalex.org/W1959608418","https://openalex.org/W1999033484","https://openalex.org/W2041823554","https://openalex.org/W2046056978","https://openalex.org/W2099471712","https://openalex.org/W2112739286","https://openalex.org/W2121812409","https://openalex.org/W2123237149","https://openalex.org/W2125389028","https://openalex.org/W2143612262","https://openalex.org/W2144760012","https://openalex.org/W2147147599","https://openalex.org/W2150769028","https://openalex.org/W2160815625","https://openalex.org/W2163605009","https://openalex.org/W2173520492","https://openalex.org/W2194775991","https://openalex.org/W2293078015","https://openalex.org/W2294814385","https://openalex.org/W2360384684","https://openalex.org/W2404292690","https://openalex.org/W2404617565","https://openalex.org/W2406312423","https://openalex.org/W2470142083","https://openalex.org/W2488005896","https://openalex.org/W2491474862","https://openalex.org/W2577946330","https://openalex.org/W2585528105","https://openalex.org/W2618530766","https://openalex.org/W2739748921","https://openalex.org/W2747238065","https://openalex.org/W2748488820","https://openalex.org/W2808631503","https://openalex.org/W2888897023","https://openalex.org/W2888968865","https://openalex.org/W2890964092","https://openalex.org/W2891138528","https://openalex.org/W2893749619","https://openalex.org/W2899520410","https://openalex.org/W2936774411","https://openalex.org/W2944613371","https://openalex.org/W2949811029","https://openalex.org/W2952716587","https://openalex.org/W2962914040","https://openalex.org/W2963684088","https://openalex.org/W2970971581","https://openalex.org/W2972668418","https://openalex.org/W2981461916","https://openalex.org/W3099631870","https://openalex.org/W4288091954","https://openalex.org/W4295312788","https://openalex.org/W4320013936","https://openalex.org/W6605273041","https://openalex.org/W6608353291","https://openalex.org/W6629705578","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6640963894","https://openalex.org/W6678292227","https://openalex.org/W6678815747","https://openalex.org/W6685352114","https://openalex.org/W6713629195","https://openalex.org/W6713727690","https://openalex.org/W6732248266","https://openalex.org/W6732897885","https://openalex.org/W6741832134","https://openalex.org/W6755312952","https://openalex.org/W6766978945","https://openalex.org/W6769178842"],"related_works":["https://openalex.org/W2158491338","https://openalex.org/W2807901368","https://openalex.org/W2133733652","https://openalex.org/W2072658171","https://openalex.org/W2606392311","https://openalex.org/W2320042380","https://openalex.org/W4385956668","https://openalex.org/W2900895161","https://openalex.org/W4380838366","https://openalex.org/W3134175397"],"abstract_inverted_index":{"Data":[0],"augmentation":[1,35,100,133,138],"is":[2],"an":[3],"effective":[4],"method":[5,134],"to":[6,20,44,53,58],"improve":[7],"the":[8,22,28,33,45,112,118,128],"robustness":[9],"of":[10],"embedding":[11,25,83],"based":[12,88,91,95,131],"speaker":[13,24,63],"verification":[14],"systems,":[15],"which":[16,65],"could":[17],"be":[18,67],"applied":[19],"either":[21],"front-end":[23,137],"extractor":[26],"or":[27,42],"back-end":[29,99,132],"PLDA.":[30],"Different":[31],"from":[32],"conventional":[34],"methods":[36,101,125,139],"such":[37],"as":[38],"manually":[39],"adding":[40],"noise":[41],"reverberation":[43],"original":[46],"audios,":[47],"in":[48],"this":[49],"article,":[50],"we":[51],"propose":[52],"use":[54],"deep":[55],"generative":[56],"models":[57],"directly":[59],"generate":[60],"more":[61],"diverse":[62],"embeddings,":[64],"would":[66],"used":[68],"for":[69,81],"robust":[70],"PLDA":[71],"training.":[72],"Conditional":[73],"GAN,":[74],"and":[75,79,93,108,115],"VAE":[76],"are":[77,102,140],"designed,":[78],"investigated":[80],"different":[82,136],"types,":[84],"including":[85],"factor":[86],"analysis":[87],"i-vector,":[89],"TDNN":[90],"x-vector,":[92,114],"ResNet":[94],"r-vector.":[96],"The":[97],"proposed":[98,124],"evaluated":[103],"on":[104],"NIST":[105],"SRE":[106],"2016,":[107],"2018":[109],"dataset.":[110],"Within":[111],"popular":[113],"r-vector":[116],"framework,":[117],"experimental":[119],"results":[120],"show":[121],"that":[122],"our":[123],"can":[126],"outperform":[127],"traditional":[129],"audio":[130],"while":[135],"considered.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}