{"id":"https://openalex.org/W4408716059","doi":"https://doi.org/10.1109/access.2025.3552790","title":"Generalized Score Comparison-Based Learning Objective for Deep Speaker Embedding","display_name":"Generalized Score Comparison-Based Learning Objective for Deep Speaker Embedding","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4408716059","doi":"https://doi.org/10.1109/access.2025.3552790"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3552790","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3552790","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3552790","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009851092","display_name":"Min Hyun Han","orcid":"https://orcid.org/0000-0002-8086-5009"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Min Hyun Han","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Institute of New Media and Communications, Seoul National University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-8086-5009","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Institute of New Media and Communications, Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061659301","display_name":"Sung Hwan Mun","orcid":"https://orcid.org/0000-0003-2554-8294"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sung Hwan Mun","raw_affiliation_strings":["Samsung Research, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051356511","display_name":"Nam Soo Kim","orcid":"https://orcid.org/0000-0002-0568-4902"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nam Soo Kim","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Institute of New Media and Communications, Seoul National University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-0568-4902","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Institute of New Media and Communications, Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.396,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82761768,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"13","issue":null,"first_page":"51194","last_page":"51207"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9071000218391418,"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":0.9071000218391418,"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/computer-science","display_name":"Computer science","score":0.7503907680511475},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5441734194755554},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5041414499282837},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49375542998313904},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46739113330841064},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4222533702850342},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.2524052858352661}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7503907680511475},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5441734194755554},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5041414499282837},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49375542998313904},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46739113330841064},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4222533702850342},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2524052858352661}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3552790","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3552790","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:30bce44a31fb48cf81b018819dc5561f","is_oa":true,"landing_page_url":"https://doaj.org/article/30bce44a31fb48cf81b018819dc5561f","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 51194-51207 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3552790","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3552790","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G7816651363","display_name":null,"funder_award_id":"No.2021-0-00456","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W2046056978","https://openalex.org/W2114925438","https://openalex.org/W2584329820","https://openalex.org/W2587150483","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2747165665","https://openalex.org/W2747238065","https://openalex.org/W2748488820","https://openalex.org/W2784163702","https://openalex.org/W2802973008","https://openalex.org/W2808631503","https://openalex.org/W2888968865","https://openalex.org/W2889045432","https://openalex.org/W2890964092","https://openalex.org/W2962788625","https://openalex.org/W2962898354","https://openalex.org/W2963040451","https://openalex.org/W2963386851","https://openalex.org/W2963466847","https://openalex.org/W2963902346","https://openalex.org/W2969985801","https://openalex.org/W2972986505","https://openalex.org/W2973149080","https://openalex.org/W3013020904","https://openalex.org/W3015598461","https://openalex.org/W3015893497","https://openalex.org/W3021717829","https://openalex.org/W3024039722","https://openalex.org/W3024869864","https://openalex.org/W3046698617","https://openalex.org/W3090254849","https://openalex.org/W3094813571","https://openalex.org/W3109225549","https://openalex.org/W3137249133","https://openalex.org/W3169129566","https://openalex.org/W3209984917","https://openalex.org/W4206499725","https://openalex.org/W4221154745","https://openalex.org/W4297841773","https://openalex.org/W4372259963","https://openalex.org/W4372341266","https://openalex.org/W4375869323","https://openalex.org/W4392903601","https://openalex.org/W4400617062","https://openalex.org/W4402111799","https://openalex.org/W6688816777","https://openalex.org/W6751593755","https://openalex.org/W6771467084","https://openalex.org/W6778102432","https://openalex.org/W6801723603","https://openalex.org/W6840886625"],"related_works":["https://openalex.org/W2731899572","https://openalex.org/W3215138031","https://openalex.org/W3009238340","https://openalex.org/W4360585206","https://openalex.org/W4321369474","https://openalex.org/W4285208911","https://openalex.org/W3082895349","https://openalex.org/W4213079790","https://openalex.org/W2248239756","https://openalex.org/W3086377361"],"abstract_inverted_index":{"In":[0,77],"state-of-the-art":[1],"speaker":[2,5,15,54,74,175],"verification":[3,75,98,176],"systems,":[4],"embeddings":[6],"are":[7,48],"trained":[8],"to":[9,12,43,51,65,92,104,110,172],"be":[10,33,93],"closer":[11],"the":[13,22,39,45,52,56,63,89,97,101,143,147,159,164,168],"target":[14],"prototype,":[16],"which":[17,87],"is":[18,41,140],"either":[19],"obtained":[20],"from":[21,55],"other":[23],"speech":[24],"samples":[25],"or":[26],"constructed":[27],"with":[28,96,142],"trainable":[29],"parameters.":[30],"This":[31],"can":[32,162],"considered":[34],"a":[35,82,121],"classification":[36],"task":[37],"since":[38],"network":[40],"trying":[42],"learn":[44],"features":[46],"that":[47,158],"most":[49],"relevant":[50],"corresponding":[53],"input":[57],"speech.":[58],"Although":[59],"classification-based":[60],"learning":[61,85],"demonstrates":[62],"ability":[64],"extract":[66],"speaker-related":[67],"information,":[68],"it":[69],"does":[70],"not":[71],"guarantee":[72],"optimal":[73],"performance.":[76],"this":[78],"paper,":[79],"we":[80,119],"propose":[81,120],"score":[83,126],"comparison-based":[84,127],"objective,":[86],"guides":[88],"training":[90,132],"framework":[91],"more":[94,170],"consistent":[95],"task,":[99],"enforcing":[100],"embedding":[102],"space":[103],"have":[105],"lower":[106],"intra-class":[107],"variance":[108,112],"compared":[109,141],"inter-class":[111],"in":[113,174],"terms":[114],"of":[115],"similarity":[116],"scores.":[117],"Furthermore,":[118],"generalized":[122],"loss":[123],"function":[124],"for":[125],"learning,":[128],"encompassing":[129],"many":[130],"conventional":[131,144],"losses":[133],"and":[134,151,166],"regularization":[135],"techniques.":[136],"The":[137],"proposed":[138,160],"technique":[139],"methods":[145],"using":[146],"VoxCeleb,":[148],"VOiCES,":[149],"CN-Celeb,":[150],"Common":[152],"Voice":[153],"datasets.":[154],"Experimental":[155],"results":[156],"demonstrate":[157],"method":[161],"boost":[163],"performance":[165],"make":[167],"system":[169],"robust":[171],"over-fitting":[173],"tasks.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}