{"id":"https://openalex.org/W4408352997","doi":"https://doi.org/10.1109/icassp49660.2025.10889245","title":"Improved Cross-Lingual Speaker Verification Using Speaker Sensitive Feature Guidance and Fine-grained Phonetic Information","display_name":"Improved Cross-Lingual Speaker Verification Using Speaker Sensitive Feature Guidance and Fine-grained Phonetic Information","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352997","doi":"https://doi.org/10.1109/icassp49660.2025.10889245"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889245","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889245","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5033499563","display_name":"Ying Ji","orcid":"https://orcid.org/0000-0001-8850-2184"},"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":"Yongtai Ji","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054686996","display_name":"Guang-Xing Li","orcid":"https://orcid.org/0000-0003-3144-1952"},"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":"Guangxing Li","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024772368","display_name":"Hao Huang","orcid":"https://orcid.org/0000-0001-6604-0951"},"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,Urumqi,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100673041","display_name":"Yanbing Li","orcid":"https://orcid.org/0000-0001-5368-6921"},"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":"Yanbing Li","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063120015","display_name":"Wushour Silamu","orcid":"https://orcid.org/0000-0003-4592-7806"},"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":"Wushour Silamu","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":null,"apc_paid":null,"fwci":1.492,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.77368254,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9883000254631042,"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":0.9883000254631042,"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":0.921500027179718,"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":0.8353376388549805},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.7580541968345642},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7411307692527771},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6988155841827393},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6746417284011841},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5839335918426514},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42205095291137695},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3570719361305237},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06799834966659546}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8353376388549805},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.7580541968345642},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7411307692527771},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6988155841827393},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6746417284011841},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5839335918426514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42205095291137695},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3570719361305237},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06799834966659546},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889245","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889245","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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","id":"https://metadata.un.org/sdg/4","score":0.6899999976158142}],"awards":[],"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":29,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2295107390","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2765793020","https://openalex.org/W2794506738","https://openalex.org/W2801581493","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2916058012","https://openalex.org/W2936780106","https://openalex.org/W2962858109","https://openalex.org/W2963450999","https://openalex.org/W2964247977","https://openalex.org/W2969985801","https://openalex.org/W3015443711","https://openalex.org/W3015598461","https://openalex.org/W3015737406","https://openalex.org/W3024869864","https://openalex.org/W3095862185","https://openalex.org/W3135815897","https://openalex.org/W3160646455","https://openalex.org/W4296068606","https://openalex.org/W4372340947","https://openalex.org/W4406858676","https://openalex.org/W6637618735","https://openalex.org/W6769178842","https://openalex.org/W6797525515"],"related_works":["https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939","https://openalex.org/W2144470400","https://openalex.org/W1516392727","https://openalex.org/W2140022733","https://openalex.org/W2911612049"],"abstract_inverted_index":{"Speaker":[0],"verification":[1,97],"performance":[2,119],"significantly":[3],"degrades":[4],"when":[5],"there":[6],"exists":[7],"a":[8],"language":[9,75,123],"mismatch":[10],"between":[11],"training":[12,31,109],"and":[13,47,110],"evaluation.":[14,111],"Domain":[15],"Adversarial":[16],"Training":[17],"(DAT)":[18],"has":[19],"shown":[20],"to":[21,45,51,90],"be":[22],"effective":[23],"in":[24],"mitigating":[25],"this":[26],"gap":[27],"by":[28,38,70,122],"incorporating":[29],"adversarial":[30,108],"with":[32,77],"domain":[33,56],"information":[34],"(language":[35],"id).":[36],"Inspired":[37],"recent":[39],"research":[40],"of":[41,79],"DAT,":[42],"we":[43,66],"propose":[44],"decompose":[46],"locate":[48],"features":[49],"sensitive":[50],"speaker":[52,62,96],"identity,":[53],"so":[54],"that":[55],"adaptation":[57],"can":[58],"better":[59],"serve":[60],"the":[61,114,118],"classification":[63],"task.":[64],"Additionally,":[65],"further":[67],"promote":[68],"DAT":[69],"replacing":[71],"alignment":[72,78],"based":[73],"on":[74,101],"identification":[76],"fine-grained":[80],"phonetic":[81,93],"information,":[82],"where":[83],"pre-trained":[84],"speech":[85],"recognition":[86],"models":[87],"are":[88],"utilized":[89],"provide":[91],"frame-level":[92],"labels.":[94],"The":[95],"model":[98],"is":[99,105],"trained":[100],"VoxCeleb,":[102],"while":[103],"CnCeleb":[104],"used":[106],"for":[107],"Results":[112],"show":[113],"methods":[115],"effectively":[116],"mitigate":[117],"degradation":[120],"caused":[121],"mismatch.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}