{"id":"https://openalex.org/W4395057330","doi":"https://doi.org/10.1145/3638884.3638917","title":"Adversarial Data Augmentation for Robust Speaker Verification","display_name":"Adversarial Data Augmentation for Robust Speaker Verification","publication_year":2023,"publication_date":"2023-12-14","ids":{"openalex":"https://openalex.org/W4395057330","doi":"https://doi.org/10.1145/3638884.3638917"},"language":"en","primary_location":{"id":"doi:10.1145/3638884.3638917","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3638884.3638917","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 9th International Conference on Communication and Information Processing","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/A5103279839","display_name":"Zhenyu Zhou","orcid":"https://orcid.org/0009-0009-8492-5222"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhenyu Zhou","raw_affiliation_strings":["Beijing University of Post Telecommunications, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Post Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102714190","display_name":"Junhui Chen","orcid":"https://orcid.org/0009-0006-9097-0167"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junhui Chen","raw_affiliation_strings":["Beijing University of Post Telecommunications, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Post Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024196194","display_name":"Namin Wang","orcid":"https://orcid.org/0009-0004-1504-4345"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Namin Wang","raw_affiliation_strings":["Huawei Cloud, China"],"affiliations":[{"raw_affiliation_string":"Huawei Cloud, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101744768","display_name":"Lantian Li","orcid":"https://orcid.org/0000-0002-5546-8060"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lantian Li","raw_affiliation_strings":["Beijing University of Post Telecommunications, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Post Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100776545","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-1286-0644"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103279839"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.6921,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.77365573,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"226","last_page":"230"},"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":0.9957000017166138,"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":0.9932000041007996,"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":0.8076313734054565},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.784907341003418},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.6778639554977417},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6490059494972229},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6346211433410645},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.6071650981903076},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5820034742355347},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5615471005439758},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5194351673126221},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47685158252716064},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4698715806007385},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.4572439193725586},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.4425183832645416},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.423576295375824},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1302972137928009},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07337483763694763}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8076313734054565},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.784907341003418},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.6778639554977417},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6490059494972229},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6346211433410645},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.6071650981903076},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5820034742355347},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5615471005439758},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5194351673126221},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47685158252716064},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4698715806007385},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4572439193725586},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.4425183832645416},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.423576295375824},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1302972137928009},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07337483763694763},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"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/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3638884.3638917","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3638884.3638917","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 9th International Conference on Communication and Information Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8814117630","display_name":null,"funder_award_id":"62171250, 62301075","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1882958252","https://openalex.org/W1936725236","https://openalex.org/W2129244720","https://openalex.org/W2154278880","https://openalex.org/W2593116425","https://openalex.org/W2606429533","https://openalex.org/W2696967604","https://openalex.org/W2801581493","https://openalex.org/W2890964092","https://openalex.org/W2951534110","https://openalex.org/W2973032144","https://openalex.org/W2973190269","https://openalex.org/W2984956686","https://openalex.org/W3015611708","https://openalex.org/W3037737213","https://openalex.org/W3104648745","https://openalex.org/W3136751735","https://openalex.org/W3137249133","https://openalex.org/W4206227007","https://openalex.org/W4254781156","https://openalex.org/W4283011175","https://openalex.org/W4385823104","https://openalex.org/W4387872955"],"related_works":["https://openalex.org/W2950183588","https://openalex.org/W3080754722","https://openalex.org/W3093978547","https://openalex.org/W2953536436","https://openalex.org/W66821593","https://openalex.org/W3203790781","https://openalex.org/W4313346231","https://openalex.org/W2738001131","https://openalex.org/W4285785480","https://openalex.org/W2997056298"],"abstract_inverted_index":{"Data":[0],"augmentation":[1,56],"(DA)":[2],"has":[3],"gained":[4],"widespread":[5],"popularity":[6],"in":[7],"deep":[8,30],"speaker":[9],"models":[10],"due":[11],"to":[12,33],"its":[13],"ease":[14],"of":[15,65],"implementation":[16],"and":[17,45],"significant":[18],"effectiveness.":[19],"It":[20],"enriches":[21],"training":[22],"data":[23],"by":[24,62],"simulating":[25],"real-life":[26],"acoustic":[27,40],"variations,":[28,41],"enabling":[29],"neural":[31],"networks":[32],"learn":[34],"speaker-related":[35],"representations":[36],"while":[37],"disregarding":[38],"irrelevant":[39],"thereby":[42],"improving":[43],"robustness":[44],"generalization.":[46],"However,":[47],"a":[48],"potential":[49],"issue":[50],"with":[51],"the":[52],"vanilla":[53],"DA":[54],"is":[55],"residual,":[57],"i.e.,":[58],"unwanted":[59],"distortion":[60],"caused":[61],"different":[63],"types":[64],"augmentation.":[66]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}