{"id":"https://openalex.org/W4375869323","doi":"https://doi.org/10.1109/icassp49357.2023.10094744","title":"Adaptive Large Margin Fine-Tuning For Robust Speaker Verification","display_name":"Adaptive Large Margin Fine-Tuning For Robust Speaker Verification","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869323","doi":"https://doi.org/10.1109/icassp49357.2023.10094744"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094744","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101675228","display_name":"Leying Zhang","orcid":"https://orcid.org/0009-0008-1424-9604"},"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":"Leying Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101416769","display_name":"Zhengyang Chen","orcid":"https://orcid.org/0000-0003-1293-8146"},"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":"Zhengyang Chen","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","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":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, 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":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9983999729156494,"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":0.9957000017166138,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.852023720741272},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.8149697780609131},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7884039282798767},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.6790273785591125},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.5243028402328491},{"id":"https://openalex.org/keywords/degradation","display_name":"Degradation (telecommunications)","score":0.4260128140449524},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.41899335384368896},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4134168028831482},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3364236652851105},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.28102391958236694},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.23123684525489807},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11554637551307678},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08321067690849304}],"concepts":[{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.852023720741272},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.8149697780609131},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7884039282798767},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.6790273785591125},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.5243028402328491},{"id":"https://openalex.org/C2779679103","wikidata":"https://www.wikidata.org/wiki/Q5251805","display_name":"Degradation (telecommunications)","level":2,"score":0.4260128140449524},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.41899335384368896},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4134168028831482},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3364236652851105},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.28102391958236694},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.23123684525489807},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11554637551307678},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08321067690849304},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094744","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.550000011920929,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2066310381","https://openalex.org/W2219249508","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2794506738","https://openalex.org/W2808631503","https://openalex.org/W2888968865","https://openalex.org/W2889519245","https://openalex.org/W2890964092","https://openalex.org/W2901312569","https://openalex.org/W2949007385","https://openalex.org/W2963466847","https://openalex.org/W2969985801","https://openalex.org/W2972986505","https://openalex.org/W2973032144","https://openalex.org/W3010925296","https://openalex.org/W3013020904","https://openalex.org/W3024869864","https://openalex.org/W3094374485","https://openalex.org/W3095079700","https://openalex.org/W3158395175","https://openalex.org/W3198698812","https://openalex.org/W3199528201","https://openalex.org/W4288091954","https://openalex.org/W4297841751","https://openalex.org/W6688816777","https://openalex.org/W6769178842","https://openalex.org/W6801723603"],"related_works":["https://openalex.org/W2348837382","https://openalex.org/W746329893","https://openalex.org/W4205872570","https://openalex.org/W4245971243","https://openalex.org/W1922805944","https://openalex.org/W4253588120","https://openalex.org/W2383732295","https://openalex.org/W3125011624","https://openalex.org/W3094374485","https://openalex.org/W4300685083"],"abstract_inverted_index":{"Large":[0],"margin":[1,27,101],"fine-tuning":[2,102],"(LMFT)":[3],"is":[4,16],"an":[5],"effective":[6,129],"strategy":[7],"to":[8,45],"improve":[9],"the":[10,25,29,34,52,61,66,95],"speaker":[11,20],"verification":[12,21,67,87,116],"system\u2019s":[13],"performance":[14,148],"and":[15,85,97,114,130,153],"widely":[17],"used":[18],"in":[19,28,49,82,140,151],"challenge":[22],"systems.":[23],"Because":[24],"large":[26,100],"loss":[30],"function":[31],"could":[32,55],"make":[33],"training":[35,43],"task":[36],"too":[37],"difficult,":[38],"people":[39],"usually":[40],"use":[41],"longer":[42],"segments":[44],"alleviate":[46],"this":[47,91],"problem":[48],"LMFT.":[50],"However,":[51],"LMFT":[53,80,139],"model":[54],"have":[56],"a":[57],"duration":[58,84],"mismatch":[59],"with":[60,138],"real":[62],"scenario":[63],"verification,":[64],"where":[65],"speech":[68],"may":[69],"be":[70],"very":[71,128],"short.":[72],"In":[73],"our":[74],"experiments,":[75],"we":[76,93,109],"also":[77,146],"find":[78],"that":[79,124],"fails":[81],"short":[83],"other":[86],"scenarios.":[88],"To":[89,105],"solve":[90],"problem,":[92],"propose":[94],"duration-based":[96],"similarity-based":[98],"adaptive":[99],"(ALMFT)":[103],"strategy.":[104],"verify":[106],"its":[107],"effectiveness,":[108],"constructed":[110],"fixed,":[111],"variable":[112],"length,":[113],"asymmetric":[115,154],"trials":[117,144],"based":[118],"on":[119],"VoxCeleb1.":[120],"Experimental":[121],"results":[122],"demonstrate":[123],"ALMFT":[125],"algorithms":[126],"are":[127],"robust,":[131],"which":[132],"not":[133],"only":[134],"achieve":[135],"comparable":[136],"improvement":[137],"official":[141],"VoxCeleb":[142],"evaluation":[143],"but":[145],"overcome":[147],"degradation":[149],"problems":[150],"short-duration":[152],"scenarios":[155],"respectively.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}