{"id":"https://openalex.org/W4415539785","doi":"https://doi.org/10.1145/3746027.3755682","title":"Adaspeaker: Learning Discriminative Speaker Representations with Gradient-Aware Adaptive Scaling","display_name":"Adaspeaker: Learning Discriminative Speaker Representations with Gradient-Aware Adaptive Scaling","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539785","doi":"https://doi.org/10.1145/3746027.3755682"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755682","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755682","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5105308605","display_name":"Jinghan Liu","orcid":"https://orcid.org/0009-0009-4354-2946"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jinghan Liu","raw_affiliation_strings":["College of Computer Science and Technology, Harbin Engineering University, Harbin, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101573668","display_name":"Xingmei Wang","orcid":"https://orcid.org/0000-0002-0281-0336"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingmei Wang","raw_affiliation_strings":["College of Computer Science and Technology, Harbin Engineering University, Harbin, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066812239","display_name":"Jiaxiang Meng","orcid":"https://orcid.org/0000-0003-1395-3962"},"institutions":[{"id":"https://openalex.org/I9086337","display_name":"Taiyuan University of Technology","ror":"https://ror.org/03kv08d37","country_code":"CN","type":"education","lineage":["https://openalex.org/I9086337"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxiang Meng","raw_affiliation_strings":["College of Software, Taiyuan University of Technology, Taiyuan, China"],"affiliations":[{"raw_affiliation_string":"College of Software, Taiyuan University of Technology, Taiyuan, China","institution_ids":["https://openalex.org/I9086337"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5105308605"],"corresponding_institution_ids":["https://openalex.org/I151727225"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17078352,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"660","last_page":"668"},"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":0.9995999932289124,"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":0.9991999864578247,"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/discriminative-model","display_name":"Discriminative model","score":0.8766000270843506},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5587999820709229},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5349000096321106},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.5329999923706055},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5322999954223633},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.48399999737739563},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4767000079154968},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.453900009393692}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8766000270843506},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6990000009536743},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5587999820709229},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5349000096321106},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.5329999923706055},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5322999954223633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5084999799728394},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.48399999737739563},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4767000079154968},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.453900009393692},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.42309999465942383},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.415800005197525},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37220001220703125},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.367900013923645},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3634999990463257},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.34299999475479126},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32260000705718994},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.28130000829696655},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.26570001244544983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755682","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755682","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W125553504","https://openalex.org/W2154278880","https://openalex.org/W2726515241","https://openalex.org/W2890964092","https://openalex.org/W2998469040","https://openalex.org/W3013020904","https://openalex.org/W3137249133","https://openalex.org/W4285219088","https://openalex.org/W4372341266","https://openalex.org/W4386608742","https://openalex.org/W4388452001","https://openalex.org/W4394744939","https://openalex.org/W4400617062","https://openalex.org/W4402704779"],"related_works":[],"abstract_inverted_index":{"Learning":[0],"discriminative":[1],"representations":[2,38],"of":[3,67,153,183],"different":[4],"speakers":[5],"is":[6,140,186],"a":[7,109,122],"key":[8,62],"challenge":[9],"in":[10,75],"open-set":[11,22],"speaker":[12,37,76],"recognition.":[13],"To":[14,102],"mitigate":[15],"the":[16,33,50,65,85,90,150],"mismatch":[17],"between":[18,36],"closed-set":[19],"training":[20],"and":[21,39,88,132],"testing,":[23],"margin-based":[24,79,176],"losses":[25],"have":[26,46],"been":[27],"widely":[28],"adopted":[29],"to":[30,71,135,143],"directly":[31],"optimize":[32],"cosine":[34,146],"similarity":[35],"proxy":[40],"class":[41],"vectors.":[42],"While":[43],"recent":[44],"studies":[45],"shown":[47],"that":[48,113,163],"enhancing":[49,149],"margin":[51],"for":[52,148],"hard":[53,97],"samples":[54,98],"can":[55,171],"improve":[56],"representation":[57],"learning,":[58],"we":[59,106],"observe":[60],"three":[61],"limitations:":[63],"(1)":[64],"measurement":[66],"sample":[68,117,137],"hardness":[69,118,134],"fails":[70],"fully":[72],"capture":[73],"differences":[74],"representations,":[77],"(2)":[78],"emphasis":[80],"does":[81],"not":[82],"significantly":[83],"increase":[84],"gradient":[86,151],"magnitude,":[87],"(3)":[89],"potential":[91],"performance":[92,181],"degradation":[93],"caused":[94],"by":[95],"emphasizing":[96],"are":[99],"rarely":[100],"considered.":[101],"address":[103],"these":[104],"issues,":[105],"propose":[107],"Adaspeaker,":[108],"novel":[110],"loss":[111,167],"framework":[112],"combines":[114],"an":[115,179],"Intra-Inter":[116],"coefficient":[119],"(Int2H)":[120],"with":[121],"gradient-aware":[123],"adaptive":[124],"scaling":[125],"strategy.":[126],"Specifically,":[127],"Int2H":[128],"jointly":[129],"models":[130],"inter-class":[131],"intra-class":[133],"estimate":[136],"importance,":[138],"which":[139],"subsequently":[141],"used":[142],"adaptively":[144],"scale":[145],"similarities":[147],"contribution":[152],"important":[154],"samples.":[155],"Experiments":[156],"conducted":[157],"on":[158],"five":[159],"evaluation":[160],"settings":[161],"show":[162],"Adaspeaker":[164,170],"outperforms":[165],"existing":[166],"functions.":[168],"Moreover,":[169],"be":[172],"seamlessly":[173],"integrated":[174],"into":[175],"losses,":[177],"yielding":[178],"average":[180],"improvement":[182],"12.6%.":[184],"Code":[185],"available":[187],"at":[188],"https://github.com/LiuJinghan2001/Adaspeaker.":[189]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-25T00:00:00"}