{"id":"https://openalex.org/W4392931801","doi":"https://doi.org/10.1109/icassp48485.2024.10446546","title":"Introducing Multilingual Phonetic Information to Speaker Embedding for Speaker Verification","display_name":"Introducing Multilingual Phonetic Information to Speaker Embedding for Speaker Verification","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392931801","doi":"https://doi.org/10.1109/icassp48485.2024.10446546"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446546","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446546","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":"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/A5020817636","display_name":"Zhida Song","orcid":"https://orcid.org/0000-0002-4987-5962"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhida Song","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,China","School of Computer Science and Technology, Xinjiang University, China","Xinjiang Key Laboratory of Signal Detection and Processing, China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Xinjiang Key Laboratory of Signal Detection and Processing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010540039","display_name":"Liang He","orcid":"https://orcid.org/0000-0002-4723-5486"},"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"]},{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang He","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,China","Xinjiang Key Laboratory of Signal Detection and Processing, China","School of Computer Science and Technology, Xinjiang University, China","Department of Electronic Engineering, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Xinjiang Key Laboratory of Signal Detection and Processing, China","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101510763","display_name":"Penghao Wang","orcid":"https://orcid.org/0009-0005-8431-5388"},"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":"Penghao Wang","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,China","Department of Electronic Engineering, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042363663","display_name":"Ying Hu","orcid":"https://orcid.org/0000-0001-7505-1767"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Hu","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,China","School of Computer Science and Technology, Xinjiang University, China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100757355","display_name":"Hao Huang","orcid":"https://orcid.org/0009-0005-7353-3072"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Huang","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,China","School of Computer Science and Technology, Xinjiang University, China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University, China","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5020817636"],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":null,"apc_paid":null,"fwci":1.6724,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.85513034,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"10091","last_page":"10095"},"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":0.9965999722480774,"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":0.9921000003814697,"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/computer-science","display_name":"Computer science","score":0.8579292297363281},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5860208868980408},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5663172006607056},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5451646447181702},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5294895768165588},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4963744282722473},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49032261967658997},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.45537954568862915},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.434085488319397},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.05824127793312073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8579292297363281},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5860208868980408},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5663172006607056},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5451646447181702},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5294895768165588},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4963744282722473},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49032261967658997},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.45537954568862915},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.434085488319397},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.05824127793312073},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446546","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446546","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2224866389","display_name":null,"funder_award_id":"62366051","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2219249508","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2747165665","https://openalex.org/W2808631503","https://openalex.org/W2963250244","https://openalex.org/W2964110616","https://openalex.org/W2964247977","https://openalex.org/W2969985801","https://openalex.org/W2972743990","https://openalex.org/W2993724474","https://openalex.org/W3036601975","https://openalex.org/W3094374485","https://openalex.org/W3095410713","https://openalex.org/W3097777922","https://openalex.org/W3197478142","https://openalex.org/W3202370288","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4205654098","https://openalex.org/W4221154745","https://openalex.org/W4319862271","https://openalex.org/W4366147765","https://openalex.org/W4372262420","https://openalex.org/W4372271885","https://openalex.org/W4375868932","https://openalex.org/W4375869323","https://openalex.org/W4385822503","https://openalex.org/W4385823321","https://openalex.org/W6688816777","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W66821593","https://openalex.org/W4297807400","https://openalex.org/W4313854686","https://openalex.org/W2249138175","https://openalex.org/W1521299571","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W1516392727","https://openalex.org/W2140022733"],"abstract_inverted_index":{"Incorporating":[0],"frame-level":[1],"phonetic":[2,28,112],"information":[3,29,113],"during":[4],"the":[5,15,64,68,87,96,104,107,126],"extraction":[6],"of":[7,17,34,47,106],"speaker":[8,18,42,91],"embeddings":[9],"has":[10],"been":[11],"shown":[12],"to":[13,85],"enhance":[14],"performance":[16,105],"verification":[19,43],"systems.":[20],"However,":[21],"previous":[22],"studies":[23],"have":[24],"primarily":[25],"relied":[26],"on":[27,95,132],"obtained":[30],"from":[31],"pre-trained":[32,80],"models":[33],"monolingual":[35],"automatic":[36],"speech":[37],"recognition":[38],"(ASR).":[39],"Considering":[40],"that":[41,109],"datasets":[44],"typically":[45],"consist":[46],"multiple":[48,58],"languages,":[49,59],"there":[50],"are":[51,55],"instances":[52],"where":[53],"speakers":[54],"proficient":[56],"in":[57,61,67,103],"resulting":[60],"discrepancies":[62],"between":[63],"languages":[65],"used":[66],"enrolled":[69],"and":[70,121],"test":[71],"utterances.":[72],"To":[73],"address":[74],"these":[75],"challenges,":[76],"we":[77],"employ":[78],"a":[79,100],"multilingual":[81,111,133],"ASR":[82],"Conformer":[83],"encoder":[84],"initialize":[86],"MFA-Conformer":[88],"network":[89],"for":[90],"verification.":[92,134],"Experimental":[93],"results":[94],"VoxCeleb":[97],"dataset":[98],"demonstrate":[99],"significant":[101],"improvement":[102],"system":[108],"incorporates":[110],"across":[114],"different":[115],"evaluation":[116],"sets,":[117],"including":[118],"VoxCeleb1-O,":[119],"E,":[120],"H,":[122],"as":[123,125],"well":[124],"VoxSRC21":[127],"validation":[128],"set,":[129],"which":[130],"focuses":[131],"The":[135],"source":[136],"code":[137],"is":[138],"released":[139],"at":[140],"https://github.com/zds-potato/multilingual-phonetic-sv.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
