{"id":"https://openalex.org/W4412623465","doi":"https://doi.org/10.1109/tnnls.2025.3589086","title":"VB-Adapter: Variational Bayesian Adapter for Cross-Domain Speech Representation Learning","display_name":"VB-Adapter: Variational Bayesian Adapter for Cross-Domain Speech Representation Learning","publication_year":2025,"publication_date":"2025-07-24","ids":{"openalex":"https://openalex.org/W4412623465","doi":"https://doi.org/10.1109/tnnls.2025.3589086","pmid":"https://pubmed.ncbi.nlm.nih.gov/40705578"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2025.3589086","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3589086","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5065846668","display_name":"Jing Zhao","orcid":"https://orcid.org/0000-0003-0158-5330"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jing Zhao","raw_affiliation_strings":["School of Computer Science and Technology, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-0158-5330","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036297817","display_name":"Qimin Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qimin Huang","raw_affiliation_strings":["School of Computer Science and Technology, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-0597-8053","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045952944","display_name":"Shanhu Wang","orcid":"https://orcid.org/0000-0003-3436-1253"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shanhu Wang","raw_affiliation_strings":["School of Computer Science and Technology, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3436-1253","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047846625","display_name":"Shiliang Sun","orcid":"https://orcid.org/0000-0001-7069-3752"},"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":"Shiliang Sun","raw_affiliation_strings":["Department of Automation, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-7069-3752","affiliations":[{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5065846668"],"corresponding_institution_ids":["https://openalex.org/I66867065"],"apc_list":null,"apc_paid":null,"fwci":1.9702,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.88657243,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"36","issue":"10","first_page":"18300","last_page":"18311"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9976999759674072,"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":0.9976999759674072,"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":0.957099974155426,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9559000134468079,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.9541893005371094},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5890627503395081},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5770846009254456},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4605940580368042},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3710763454437256},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3263838291168213},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1545521318912506},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.14296329021453857}],"concepts":[{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.9541893005371094},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5890627503395081},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5770846009254456},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4605940580368042},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3710763454437256},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3263838291168213},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1545521318912506},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.14296329021453857},{"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},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D049250","descriptor_name":"Speech Recognition Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D049250","descriptor_name":"Speech Recognition Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D049250","descriptor_name":"Speech Recognition Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2025.3589086","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3589086","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:40705578","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40705578","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6487037979","display_name":null,"funder_award_id":"62476089","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"},{"id":"https://openalex.org/F4320332588","display_name":"Shanghai Key Laboratory of Intelligent Information Processing","ror":"https://ror.org/013q1eq08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2018363392","https://openalex.org/W2526425061","https://openalex.org/W2801581493","https://openalex.org/W2936774411","https://openalex.org/W2962684181","https://openalex.org/W2962959469","https://openalex.org/W2963242190","https://openalex.org/W2963364041","https://openalex.org/W3005485628","https://openalex.org/W3108655343","https://openalex.org/W3116256056","https://openalex.org/W3161716720","https://openalex.org/W3180849682","https://openalex.org/W3209059054","https://openalex.org/W4220678054","https://openalex.org/W4221140371","https://openalex.org/W4224931267","https://openalex.org/W4224932111","https://openalex.org/W4226548933","https://openalex.org/W4281395113","https://openalex.org/W4282916552","https://openalex.org/W4293057192","https://openalex.org/W4295886387","https://openalex.org/W4311415873","https://openalex.org/W4375869343","https://openalex.org/W4380875839","https://openalex.org/W4383503423","https://openalex.org/W4385245566","https://openalex.org/W4388999498","https://openalex.org/W4392909624","https://openalex.org/W4402811983","https://openalex.org/W4408352300"],"related_works":["https://openalex.org/W2133028525","https://openalex.org/W4229060448","https://openalex.org/W4306381730","https://openalex.org/W2981692913","https://openalex.org/W3044188621","https://openalex.org/W3184035966","https://openalex.org/W2485605994","https://openalex.org/W2160602540","https://openalex.org/W4385571108","https://openalex.org/W4200251711"],"abstract_inverted_index":{"To":[0,43],"leverage":[1],"the":[2,28,33,80,83,96,100,121,125,132,142,156,162,170],"abundant":[3],"speech":[4,24,56,138,150,173],"data":[5],"available":[6],"for":[7,54,136,148],"pretraining,":[8],"current":[9],"models":[10],"excel":[11],"in":[12,160],"generalization":[13],"across":[14],"diverse":[15],"tasks.":[16],"Nevertheless,":[17],"real-world":[18],"challenges":[19],"emerge":[20],"when":[21],"addressing":[22],"unfamiliar":[23],"scenarios":[25],"far":[26],"from":[27,165],"pretrained":[29],"speech,":[30],"owing":[31],"to":[32,68,78,94,108,119],"domain":[34,166],"shift":[35,167],"between":[36,82],"pretraining":[37],"(source)":[38],"and":[39,85,104,141,146,168],"fine-tuning":[40],"(target)":[41],"data.":[42],"overcome":[44],"this":[45],"barrier,":[46],"we":[47,62,113],"propose":[48],"a":[49,64,70],"variational":[50],"Bayesian":[51],"adapter":[52],"(VB-Adapter)":[53],"cross-domain":[55],"representation":[57],"learning":[58,116],"during":[59],"fine-tuning.":[60],"First,":[61],"establish":[63],"latent":[65,101],"variable":[66],"model":[67,110],"construct":[69],"desired":[71],"posterior":[72],"distribution":[73],"after":[74],"incorporating":[75],"domain-specific":[76,106],"knowledge":[77,107],"bridge":[79],"gap":[81],"source":[84],"target":[86],"domains.":[87],"Then,":[88],"an":[89],"adaptive":[90,127],"objective":[91],"is":[92],"presented":[93],"maximize":[95],"mutual":[97],"information":[98],"of":[99,124,144,158,172],"variables":[102],"with":[103],"without":[105],"facilitate":[109],"adaptation.":[111],"Finally,":[112],"introduce":[114],"contrastive":[115],"on":[117,134],"samples":[118],"optimize":[120],"lower":[122],"bound":[123],"above":[126],"objective.":[128],"Our":[129],"experiments":[130],"apply":[131],"VB-Adapter":[133,159],"transformers":[135],"dysarthric":[137],"recognition":[139,151],"(DSR)":[140],"integration":[143],"Whisper-encoder":[145],"Llama":[147],"Mandarin":[149],"(MSR).":[152],"The":[153],"results":[154],"reveal":[155],"effectiveness":[157],"modeling":[161],"uncertainties":[163],"arising":[164],"enhancing":[169],"robustness":[171],"representations.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-14T06:09:40.864956","created_date":"2025-10-10T00:00:00"}