{"id":"https://openalex.org/W4392931779","doi":"https://doi.org/10.1109/icassp48485.2024.10447141","title":"Gmm-Resnext: Combining Generative and Discriminative Models for Speaker Verification","display_name":"Gmm-Resnext: Combining Generative and Discriminative Models for Speaker Verification","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392931779","doi":"https://doi.org/10.1109/icassp48485.2024.10447141"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447141","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447141","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2407.03135","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100657114","display_name":"Hui Yan","orcid":"https://orcid.org/0009-0009-0475-433X"},"institutions":[{"id":"https://openalex.org/I53592917","display_name":"Jiangxi Normal University","ror":"https://ror.org/05nkgk822","country_code":"CN","type":"education","lineage":["https://openalex.org/I53592917"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Yan","raw_affiliation_strings":["Jiangxi Normal University,School of Computer and Information Engineering,Nanchang,China","School of Computer and Information Engineering, Jiangxi Normal University, Nanchang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangxi Normal University,School of Computer and Information Engineering,Nanchang,China","institution_ids":["https://openalex.org/I53592917"]},{"raw_affiliation_string":"School of Computer and Information Engineering, Jiangxi Normal University, Nanchang, China","institution_ids":["https://openalex.org/I53592917"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069470708","display_name":"Zhenchun Lei","orcid":"https://orcid.org/0000-0001-5846-7402"},"institutions":[{"id":"https://openalex.org/I53592917","display_name":"Jiangxi Normal University","ror":"https://ror.org/05nkgk822","country_code":"CN","type":"education","lineage":["https://openalex.org/I53592917"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenchun Lei","raw_affiliation_strings":["Jiangxi Normal University,School of Computer and Information Engineering,Nanchang,China","School of Computer and Information Engineering, Jiangxi Normal University, Nanchang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangxi Normal University,School of Computer and Information Engineering,Nanchang,China","institution_ids":["https://openalex.org/I53592917"]},{"raw_affiliation_string":"School of Computer and Information Engineering, Jiangxi Normal University, Nanchang, China","institution_ids":["https://openalex.org/I53592917"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101859009","display_name":"Changhong Liu","orcid":"https://orcid.org/0000-0003-4673-5806"},"institutions":[{"id":"https://openalex.org/I53592917","display_name":"Jiangxi Normal University","ror":"https://ror.org/05nkgk822","country_code":"CN","type":"education","lineage":["https://openalex.org/I53592917"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changhong Liu","raw_affiliation_strings":["Jiangxi Normal University,School of Computer and Information Engineering,Nanchang,China","School of Computer and Information Engineering, Jiangxi Normal University, Nanchang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangxi Normal University,School of Computer and Information Engineering,Nanchang,China","institution_ids":["https://openalex.org/I53592917"]},{"raw_affiliation_string":"School of Computer and Information Engineering, Jiangxi Normal University, Nanchang, China","institution_ids":["https://openalex.org/I53592917"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016943819","display_name":"Yong Zhou","orcid":"https://orcid.org/0000-0002-4099-8077"},"institutions":[{"id":"https://openalex.org/I53592917","display_name":"Jiangxi Normal University","ror":"https://ror.org/05nkgk822","country_code":"CN","type":"education","lineage":["https://openalex.org/I53592917"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Zhou","raw_affiliation_strings":["Jiangxi Normal University,School of Computer and Information Engineering,Nanchang,China","School of Computer and Information Engineering, Jiangxi Normal University, Nanchang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangxi Normal University,School of Computer and Information Engineering,Nanchang,China","institution_ids":["https://openalex.org/I53592917"]},{"raw_affiliation_string":"School of Computer and Information Engineering, Jiangxi Normal University, Nanchang, China","institution_ids":["https://openalex.org/I53592917"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I53592917"],"apc_list":null,"apc_paid":null,"fwci":1.0668,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.76068315,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"11706","last_page":"11710"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9976999759674072,"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":0.9900000095367432,"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":0.8761360049247742},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.7086794376373291},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.689774751663208},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.576208770275116},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.44423699378967285},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4435771107673645},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42905086278915405},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4168916940689087}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8761360049247742},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7086794376373291},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.689774751663208},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.576208770275116},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.44423699378967285},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4435771107673645},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42905086278915405},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4168916940689087}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447141","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447141","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2407.03135","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.03135","pdf_url":"https://arxiv.org/pdf/2407.03135","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2407.03135","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.03135","pdf_url":"https://arxiv.org/pdf/2407.03135","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.800000011920929}],"awards":[{"id":"https://openalex.org/G1203572025","display_name":"\u9762\u5411\u865a\u62df\u6559\u5e08\u7684\u8bed\u97f3\u9a71\u52a8\u6559\u5b66\u52a8\u4f5c\u5e8f\u5217\u7684\u6df1\u5ea6\u751f\u6210\u6a21\u578b\u7814\u7a76","funder_award_id":"62067004","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":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392931779.pdf"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1589137271","https://openalex.org/W2041823554","https://openalex.org/W2150769028","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2344822617","https://openalex.org/W2549139847","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2752782242","https://openalex.org/W2808631503","https://openalex.org/W2889151164","https://openalex.org/W2890964092","https://openalex.org/W2928165649","https://openalex.org/W2969985801","https://openalex.org/W2972441390","https://openalex.org/W3024869864","https://openalex.org/W3137249133","https://openalex.org/W3141035251","https://openalex.org/W3142516134","https://openalex.org/W3201127328","https://openalex.org/W4221154745","https://openalex.org/W4226090390","https://openalex.org/W4288091954","https://openalex.org/W4297841636","https://openalex.org/W4297841826","https://openalex.org/W4312443924","https://openalex.org/W4372271885","https://openalex.org/W4375869393","https://openalex.org/W4385822954","https://openalex.org/W4385823425","https://openalex.org/W6688816777","https://openalex.org/W6704529918","https://openalex.org/W6769178842"],"related_works":["https://openalex.org/W4396941953","https://openalex.org/W2093104230","https://openalex.org/W2987280934","https://openalex.org/W4390874210","https://openalex.org/W4384918963","https://openalex.org/W4365211920","https://openalex.org/W2128027845","https://openalex.org/W3014948380","https://openalex.org/W4386184937","https://openalex.org/W4394728283"],"abstract_inverted_index":{"With":[0],"the":[1,45,56,69,78,85,94,98,109,146],"development":[2],"of":[3,59,112,152],"deep":[4,24,113],"learning,":[5],"many":[6],"different":[7,31],"network":[8,18,92],"architectures":[9,19,32],"have":[10,33],"been":[11,34,139],"explored":[12],"in":[13,37,156],"speaker":[14,49,99],"verification.":[15,50],"However,":[16],"most":[17],"rely":[20],"on":[21,84,125,133,163],"a":[22],"single":[23],"learning":[25,114],"architecture,":[26],"and":[27,67,89,104,116,154,161],"hybrid":[28],"networks":[29],"combining":[30],"little":[35],"studied":[36],"ASV":[38],"task.":[39],"In":[40],"this":[41],"paper,":[42],"we":[43,76],"propose":[44],"GMM-ResNext":[46,101,130,148],"model":[47,126,131],"for":[48],"Conventional":[51],"GMM":[52],"does":[53],"not":[54],"consider":[55],"score":[57],"distribution":[58],"each":[60],"frame":[61],"feature":[62],"over":[63],"all":[64],"Gaussian":[65,80],"components":[66],"ignores":[68],"relationship":[70],"between":[71],"neighboring":[72],"speech":[73],"frames.":[74],"So,":[75],"extract":[77,97],"log":[79],"probability":[81],"features":[82,88],"based":[83,132],"raw":[86],"acoustic":[87],"use":[90],"ResNext-based":[91],"as":[93],"backbone":[95],"to":[96,107,119],"embedding.":[100],"combines":[102],"generative":[103],"discriminative":[105],"models":[106,115],"improve":[108],"generalization":[110],"ability":[111],"allows":[117],"one":[118],"more":[120],"easily":[121],"specify":[122],"meaningful":[123],"priors":[124],"parameters.":[127],"A":[128],"two-path":[129],"two":[134],"gender-related":[135],"GMMs":[136],"has":[137],"also":[138],"proposed.":[140],"The":[141],"experimental":[142],"results":[143],"show":[144],"that":[145],"proposed":[147],"achieves":[149],"relative":[150],"improvements":[151],"48.1%":[153],"11.3%":[155],"EER":[157],"compared":[158],"with":[159],"ResNet34":[160],"ECAPA-TDNN":[162],"VoxCeleb1-O.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}