{"id":"https://openalex.org/W3206886023","doi":"https://doi.org/10.1109/icassp43922.2022.9747166","title":"Real Additive Margin Softmax for Speaker Verification","display_name":"Real Additive Margin Softmax for Speaker Verification","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3206886023","doi":"https://doi.org/10.1109/icassp43922.2022.9747166","mag":"3206886023"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747166","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101744768","display_name":"Lantian Li","orcid":"https://orcid.org/0000-0002-5546-8060"},"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":true,"raw_author_name":"Lantian Li","raw_affiliation_strings":["Tsinghua University,Center for Speech and Language Technologies, BNRist,China","Center for Speech and Language Technologies, BNRist, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Center for Speech and Language Technologies, BNRist,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Center for Speech and Language Technologies, BNRist, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059647416","display_name":"Ruiqian Nai","orcid":null},"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":"Ruiqian Nai","raw_affiliation_strings":["Tsinghua University,Center for Speech and Language Technologies, BNRist,China","Center for Speech and Language Technologies, BNRist, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Center for Speech and Language Technologies, BNRist,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Center for Speech and Language Technologies, BNRist, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100391494","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-6992-7950"},"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,Center for Speech and Language Technologies, BNRist,China","Center for Speech and Language Technologies, BNRist, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Center for Speech and Language Technologies, BNRist,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Center for Speech and Language Technologies, BNRist, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101744768"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.9998,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.88252134,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7527","last_page":"7531"},"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":0.9986000061035156,"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":0.9945999979972839,"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/softmax-function","display_name":"Softmax function","score":0.996108889579773},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.8450589776039124},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6289374828338623},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.436929851770401},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40457361936569214},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3505759835243225},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.16637718677520752},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.15579620003700256}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.996108889579773},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.8450589776039124},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6289374828338623},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.436929851770401},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40457361936569214},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3505759835243225},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.16637718677520752},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.15579620003700256}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747166","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6200000047683716}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2114925438","https://openalex.org/W2119821739","https://openalex.org/W2395750323","https://openalex.org/W2516764878","https://openalex.org/W2612434969","https://openalex.org/W2784163702","https://openalex.org/W2808631503","https://openalex.org/W2884412522","https://openalex.org/W2888897023","https://openalex.org/W2890964092","https://openalex.org/W2932691488","https://openalex.org/W2962788625","https://openalex.org/W2963181813","https://openalex.org/W2963371159","https://openalex.org/W2963382494","https://openalex.org/W2963386851","https://openalex.org/W2963702081","https://openalex.org/W2972986505","https://openalex.org/W2981461916","https://openalex.org/W3010925296","https://openalex.org/W3013020904","https://openalex.org/W3080134564","https://openalex.org/W3096431026","https://openalex.org/W3103152812","https://openalex.org/W3111759753","https://openalex.org/W3115097893","https://openalex.org/W3137249133","https://openalex.org/W4239510810","https://openalex.org/W4288091954","https://openalex.org/W4289750118","https://openalex.org/W6737575990","https://openalex.org/W6745415975","https://openalex.org/W6753575415","https://openalex.org/W6769178842","https://openalex.org/W6782256564","https://openalex.org/W6787743207"],"related_works":["https://openalex.org/W2743258233","https://openalex.org/W4307834408","https://openalex.org/W4320925816","https://openalex.org/W2610906757","https://openalex.org/W3208883981","https://openalex.org/W2997969508","https://openalex.org/W4214883769","https://openalex.org/W2921182884","https://openalex.org/W2938746851","https://openalex.org/W4321091470"],"abstract_inverted_index":{"The":[0,104],"additive":[1],"margin":[2,35,80],"softmax":[3,84],"(AM-Softmax)":[4],"loss":[5,59,75,98],"has":[6,106],"delivered":[7],"remarkable":[8],"performance":[9],"in":[10,32,82],"speaker":[11],"verification.":[12],"A":[13],"supposed":[14],"behavior":[15,51],"of":[16,52],"AM-Softmax":[17,53,74,97],"is":[18],"that":[19,57,94],"it":[20],"can":[21],"shrink":[22],"within-class":[23],"variation":[24],"by":[25],"putting":[26],"emphasis":[27],"on":[28,49,67,88],"target":[29,37],"logits,":[30],"which":[31,76],"turn":[33],"improves":[34],"between":[36],"and":[38,55,91],"non-target":[39],"classes.":[40],"In":[41],"this":[42,58,68],"paper,":[43],"we":[44,70],"conduct":[45],"a":[46,72,78],"careful":[47],"analysis":[48],"the":[50,83,95,101],"loss,":[54],"show":[56],"does":[60],"not":[61],"implement":[62],"real":[63],"max-margin":[64],"training.":[65,85],"Based":[66],"observation,":[69],"present":[71],"Real":[73],"involves":[77],"true":[79],"function":[81],"Experiments":[86],"conducted":[87],"VoxCeleb1,":[89],"SITW":[90],"CNCeleb":[92],"demonstrated":[93],"corrected":[96],"consistently":[99],"outperforms":[100],"original":[102],"one.":[103],"code":[105],"been":[107],"released":[108],"at":[109],"https://gitlab.com/csltstu/sunine.":[110]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3}],"updated_date":"2026-03-05T09:29:38.588285","created_date":"2025-10-10T00:00:00"}