{"id":"https://openalex.org/W4416799023","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249170","title":"Multi-level Adversarial Training with Data Augmentation for Robust Speaker Verification","display_name":"Multi-level Adversarial Training with Data Augmentation for Robust Speaker Verification","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799023","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249170"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249170","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249170","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5100450111","display_name":"Xiaolei Zhang","orcid":"https://orcid.org/0000-0002-6431-0169"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolei Zhang","raw_affiliation_strings":["School of Software, Xinjiang University,Urumqi,China,830091"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Xinjiang University,Urumqi,China,830091","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000449705","display_name":"Zhihua Fang","orcid":"https://orcid.org/0000-0002-3018-7414"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihua Fang","raw_affiliation_strings":["Xinjiang Multimodal Information Technology Engineering Research Center,Urumqi,China,830017"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang Multimodal Information Technology Engineering Research Center,Urumqi,China,830017","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100317908","display_name":"Liang He","orcid":"https://orcid.org/0000-0003-1523-067X"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang He","raw_affiliation_strings":["Xinjiang Multimodal Information Technology Engineering Research Center,Urumqi,China,830017"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang Multimodal Information Technology Engineering Research Center,Urumqi,China,830017","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17287156,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"613","last_page":"618"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8931000232696533,"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":0.8931000232696533,"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":0.025699999183416367,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.008299999870359898,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.9516000151634216},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.590499997138977},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5785999894142151},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5676000118255615},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5633000135421753},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5594000220298767},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5065000057220459},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5054000020027161}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.9516000151634216},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7591999769210815},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6115000247955322},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.590499997138977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5825999975204468},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5785999894142151},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5676000118255615},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5633000135421753},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5594000220298767},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5065000057220459},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5054000020027161},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.47920000553131104},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3756999969482422},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.37389999628067017},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3714999854564667},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36160001158714294},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.35339999198913574},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.32269999384880066},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2558000087738037}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249170","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249170","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2224866389","display_name":null,"funder_award_id":"62366051","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2936774411","https://openalex.org/W2973190269","https://openalex.org/W3006741730","https://openalex.org/W3015555484","https://openalex.org/W3015598461","https://openalex.org/W3015611708","https://openalex.org/W3015737406","https://openalex.org/W3024869864","https://openalex.org/W3099825973","https://openalex.org/W3196373842","https://openalex.org/W3196650842","https://openalex.org/W4221154745","https://openalex.org/W4292976050","https://openalex.org/W4296068606","https://openalex.org/W4321780088","https://openalex.org/W4385823104","https://openalex.org/W4385823321","https://openalex.org/W4395057330","https://openalex.org/W4402116008","https://openalex.org/W4408355031"],"related_works":[],"abstract_inverted_index":{"Data":[0],"augmentation":[1,43,66,72,86,97],"(DA)":[2],"is":[3,88],"extensively":[4],"utilized":[5],"in":[6],"deep":[7,26],"speaker":[8,106,117],"models":[9],"and":[10,33,74,115,140,144],"significantly":[11],"enhances":[12],"their":[13],"performance.":[14],"This":[15],"process":[16],"not":[17],"only":[18],"enriches":[19],"the":[20,37,81,91,110,131,145],"training":[21,63],"dataset":[22,128],"but":[23],"also":[24],"enables":[25],"neural":[27],"networks":[28],"to":[29,47,94,108,153],"acquire":[30],"more":[31,113],"robust":[32,114],"generalizable":[34,116],"features.":[35],"However,":[36],"diverse":[38],"augmentations":[39],"from":[40],"conventional":[41],"data":[42,65],"methods":[44],"can":[45],"lead":[46],"unwanted":[48],"distortions.":[49],"To":[50],"tackle":[51],"this":[52,54],"problem,":[53],"study":[55],"introduces":[56],"a":[57,148],"new":[58],"strategy":[59],"named":[60],"multi-level":[61],"adversarial":[62],"with":[64],"(MAT-DA).":[67],"In":[68],"particular,":[69],"both":[70,138],"an":[71,75,85,102],"discriminator":[73,77,87],"augmentation-type":[76],"are":[78],"incorporated":[79,89],"at":[80,90],"frame":[82],"level,":[83],"while":[84],"embedding":[92,107],"level":[93],"classify":[95],"various":[96],"types.":[98],"Additionally,":[99],"we":[100],"impose":[101],"extra":[103],"constraint":[104],"on":[105,126],"help":[109],"network":[111],"achieve":[112],"embeddings":[118],"when":[119],"encountering":[120],"different":[121],"acoustic":[122],"variations.":[123],"Experiments":[124],"conducted":[125],"VoxCeleb":[127],"indicate":[129],"that":[130],"proposed":[132],"method":[133],"outperforms":[134],"standard":[135],"DA":[136],"under":[137],"augmentation-matched":[139],"mismatched":[141],"test":[142],"conditions":[143],"results":[146],"show":[147],"performance":[149],"improvement":[150],"of":[151],"up":[152],"13.7":[154],"%.":[155]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}