{"id":"https://openalex.org/W3015678397","doi":"https://doi.org/10.1109/icassp40776.2020.9054333","title":"Text Adaptation for Speaker Verification with Speaker-Text Factorized Embeddings","display_name":"Text Adaptation for Speaker Verification with Speaker-Text Factorized Embeddings","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015678397","doi":"https://doi.org/10.1109/icassp40776.2020.9054333","mag":"3015678397"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054333","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054333","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/2508.04425","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057050425","display_name":"Yexin Yang","orcid":"https://orcid.org/0000-0001-9597-9829"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yexin Yang","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328272","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0002-1595-3619"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086338661","display_name":"Xun Gong","orcid":"https://orcid.org/0000-0002-3364-8407"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xun Gong","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6454","last_page":"6458"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.995199978351593,"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/T11309","display_name":"Music and Audio Processing","score":0.989300012588501,"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":0.8292108774185181},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6433336734771729},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6219093799591064},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5596094727516174},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5152011513710022},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.47596997022628784},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4722021520137787},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4588393270969391},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.44849491119384766},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4361254870891571},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10428634285926819}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8292108774185181},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6433336734771729},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6219093799591064},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5596094727516174},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5152011513710022},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.47596997022628784},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4722021520137787},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4588393270969391},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.44849491119384766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4361254870891571},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10428634285926819},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054333","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054333","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.04425","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.04425","pdf_url":"https://arxiv.org/pdf/2508.04425","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:2508.04425","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.04425","pdf_url":"https://arxiv.org/pdf/2508.04425","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":[{"score":0.800000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1006777433","https://openalex.org/W1996512145","https://openalex.org/W2046056978","https://openalex.org/W2114925438","https://openalex.org/W2584329820","https://openalex.org/W2747238065","https://openalex.org/W2748488820","https://openalex.org/W2808631503","https://openalex.org/W2888968865","https://openalex.org/W2890654588","https://openalex.org/W2890964092","https://openalex.org/W2899771611","https://openalex.org/W2916104401","https://openalex.org/W2937033898","https://openalex.org/W2962788625","https://openalex.org/W2962959915","https://openalex.org/W2964247977","https://openalex.org/W2972743990","https://openalex.org/W3010925296","https://openalex.org/W6756040250"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W66821593","https://openalex.org/W2149220986","https://openalex.org/W1521299571","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W3141593045","https://openalex.org/W2144470400","https://openalex.org/W2911612049"],"abstract_inverted_index":{"Text":[0],"mismatch":[1,62,137],"between":[2],"pre-collected":[3],"data,":[4,10],"either":[5],"training":[6],"data":[7,15,34,41],"or":[8],"enrollment":[9],"and":[11,46,79,82,111],"the":[12,36,60,73,91,115,133],"actual":[13],"test":[14],"can":[16,28,108,130],"significantly":[17,131],"hurt":[18],"text-dependent":[19],"speaker":[20,77,117,121],"verification":[21],"(SV)":[22],"system":[23],"performance.":[24],"Although":[25],"this":[26,49],"problem":[27],"be":[29,44,109],"solved":[30],"by":[31],"carefully":[32],"collecting":[33],"with":[35],"target":[37,105],"speech":[38,75,106],"content,":[39],"such":[40],"collection":[42],"could":[43],"costly":[45],"inflexible.":[47],"In":[48],"paper,":[50],"we":[51],"propose":[52],"a":[53,65,87,95],"novel":[54],"text":[55,61,80,102,128,136],"adaptation":[56,100,129],"framework":[57],"to":[58,71,113,119],"address":[59],"issue.":[63],"Here,":[64],"speaker-text":[66],"factorization":[67],"network":[68],"is":[69],"proposed":[70],"factorize":[72],"input":[74],"into":[76,86],"embeddings":[78,81,103,118],"then":[83],"integrate":[84],"them":[85],"single":[88],"representation":[89],"in":[90],"later":[92],"stage.":[93],"Given":[94],"small":[96],"amount":[97],"of":[98,104,135],"speaker-independent":[99],"utterances,":[101],"content":[107],"extracted":[110],"used":[112],"adapt":[114],"text-independent":[116],"text-customized":[120],"embeddings.":[122],"Experiments":[123],"on":[124],"RSR2015":[125],"show":[126],"that":[127],"improve":[132],"performance":[134],"conditions.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}