{"id":"https://openalex.org/W4413944826","doi":"https://doi.org/10.1109/lsp.2025.3605293","title":"Neural Scoring: A Refreshed End-to-End Approach for Speaker Verification in Complex Conditions","display_name":"Neural Scoring: A Refreshed End-to-End Approach for Speaker Verification in Complex Conditions","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4413944826","doi":"https://doi.org/10.1109/lsp.2025.3605293"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2025.3605293","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3605293","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5109097339","display_name":"Wan Lin","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":"Wan Lin","raw_affiliation_strings":["Center for Speech and Language Technologies (CSLT), BNRist at Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-5923-5979","affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies (CSLT), BNRist at Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102714190","display_name":"Junhui Chen","orcid":"https://orcid.org/0009-0006-9097-0167"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junhui Chen","raw_affiliation_strings":["School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-9097-0167","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tianhao Wang","orcid":"https://orcid.org/0009-0004-9915-1235"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianhao Wang","raw_affiliation_strings":["School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-9915-1235","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103279839","display_name":"Zhenyu Zhou","orcid":"https://orcid.org/0009-0009-8492-5222"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyu Zhou","raw_affiliation_strings":["School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-8492-5222","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101744768","display_name":"Lantian Li","orcid":"https://orcid.org/0000-0002-5546-8060"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lantian Li","raw_affiliation_strings":["School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5546-8060","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100776545","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-1286-0644"},"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":["Center for Speech and Language Technologies (CSLT), BNRist at Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1286-0644","affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies (CSLT), BNRist at Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1160694,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"3575","last_page":"3579"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9937999844551086,"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":0.9937999844551086,"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":0.9767000079154968,"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":0.9203000068664551,"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":0.7461601495742798},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7338916063308716},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6891705989837646},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5170405507087708},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42130279541015625},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4102552533149719},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4091131389141083},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32741811871528625}],"concepts":[{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.7461601495742798},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7338916063308716},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6891705989837646},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5170405507087708},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42130279541015625},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4102552533149719},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4091131389141083},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32741811871528625}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2025.3605293","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3605293","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2673175451","display_name":null,"funder_award_id":"62301075","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4491952354","display_name":null,"funder_award_id":"62171250","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":30,"referenced_works":["https://openalex.org/W111477576","https://openalex.org/W2114925438","https://openalex.org/W2158703410","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2938358845","https://openalex.org/W2972961496","https://openalex.org/W2973054998","https://openalex.org/W2979593053","https://openalex.org/W3150964372","https://openalex.org/W3161158930","https://openalex.org/W3206287456","https://openalex.org/W4206908380","https://openalex.org/W4297841751","https://openalex.org/W4297841827","https://openalex.org/W4313033198","https://openalex.org/W4372269848","https://openalex.org/W4372341266","https://openalex.org/W4375868932","https://openalex.org/W4375869323","https://openalex.org/W4375869393","https://openalex.org/W4385245566","https://openalex.org/W4385823104","https://openalex.org/W4385823321","https://openalex.org/W4386608742","https://openalex.org/W4389664670","https://openalex.org/W4392903478","https://openalex.org/W4400033122","https://openalex.org/W4408347299"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W66821593","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W1521299571","https://openalex.org/W4313854686","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2140022733"],"abstract_inverted_index":{"Modern":[0],"speaker":[1,7],"verification":[2,11,55,109],"systems":[3],"primarily":[4],"rely":[5],"on":[6,13,60,114],"embeddings,":[8,62],"followed":[9],"by":[10],"based":[12],"cosine":[14],"similarity":[15],"between":[16],"the":[17,21,36,76,124,143],"embedding":[18,39],"vectors":[19],"of":[20,38,78,101,107],"enrollment":[22],"and":[23,126],"test":[24,95],"utterances.":[25],"While":[26],"effective,":[27],"these":[28],"methods":[29,128],"struggle":[30],"with":[31,71,98],"multi-talker":[32],"speech":[33],"due":[34],"to":[35,67,142],"unidentifiability":[37],"vectors.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44,85],"propose":[45],"Neural":[46,119],"Scoring,":[47],"a":[48,87,99],"refreshed":[49],"end-to-end":[50,81],"framework":[51],"that":[52,118],"directly":[53],"estimates":[54],"posterior":[56],"probabilities":[57],"without":[58],"relying":[59],"test-side":[61],"making":[63],"it":[64],"more":[65,83],"robust":[66],"complex":[68],"conditions,":[69,131],"e.g.,":[70],"multiple":[72],"talkers.":[73],"To":[74],"make":[75],"training":[77,91],"such":[79],"an":[80,133],"model":[82],"efficient,":[84],"introduce":[86],"large-scale":[88,108],"trial":[89],"e2e":[90],"strategy,":[92],"where":[93],"each":[94],"utterance":[96],"pairs":[97],"set":[100],"enrolled":[102],"speakers,":[103],"thus":[104],"enabling":[105],"processing":[106],"trials":[110],"per":[111],"batch.":[112],"Experiments":[113],"VoxCeleb":[115],"dataset":[116],"demonstrate":[117],"Scoring":[120],"consistently":[121],"outperforms":[122],"both":[123],"baseline":[125],"competitive":[127],"across":[129],"various":[130],"achieving":[132],"overall":[134],"70.36%":[135],"reduction":[136],"in":[137],"Equal":[138],"Error":[139],"Rate":[140],"compared":[141],"baseline.":[144]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}