{"id":"https://openalex.org/W4392904112","doi":"https://doi.org/10.1109/icassp48485.2024.10445894","title":"A Comparison of Parameter-Efficient ASR Domain Adaptation Methods for Universal Speech and Language Models","display_name":"A Comparison of Parameter-Efficient ASR Domain Adaptation Methods for Universal Speech and Language Models","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904112","doi":"https://doi.org/10.1109/icassp48485.2024.10445894"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445894","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445894","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/A5032798707","display_name":"Khe Chai Sim","orcid":"https://orcid.org/0000-0002-0866-2223"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Khe Chai Sim","raw_affiliation_strings":["Google,USA","Google, USA"],"affiliations":[{"raw_affiliation_string":"Google,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069872293","display_name":"Zhouyuan Huo","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhouyuan Huo","raw_affiliation_strings":["Google,USA","Google, USA"],"affiliations":[{"raw_affiliation_string":"Google,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062473985","display_name":"Tsendsuren Munkhdalai","orcid":"https://orcid.org/0000-0002-8783-4993"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tsendsuren Munkhdalai","raw_affiliation_strings":["Google,USA","Google, USA"],"affiliations":[{"raw_affiliation_string":"Google,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057946983","display_name":"Nikhil Siddhartha","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikhil Siddhartha","raw_affiliation_strings":["Google,USA","Google, USA"],"affiliations":[{"raw_affiliation_string":"Google,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008253072","display_name":"Adam Stooke","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Stooke","raw_affiliation_strings":["Google,USA","Google, USA"],"affiliations":[{"raw_affiliation_string":"Google,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101749753","display_name":"Zhong Meng","orcid":"https://orcid.org/0000-0001-7814-5929"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhong Meng","raw_affiliation_strings":["Google,USA","Google, USA"],"affiliations":[{"raw_affiliation_string":"Google,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374448","display_name":"Bo Li","orcid":"https://orcid.org/0000-0002-6711-3603"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Li","raw_affiliation_strings":["Google,USA","Google, USA"],"affiliations":[{"raw_affiliation_string":"Google,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tara Sainath","raw_affiliation_strings":["Google,USA","Google, USA"],"affiliations":[{"raw_affiliation_string":"Google,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5032798707"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":2.1903,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.88533694,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6900","last_page":"6904"},"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/T11309","display_name":"Music and Audio Processing","score":0.9904999732971191,"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/T10860","display_name":"Speech and Audio Processing","score":0.9902999997138977,"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":0.8264880180358887},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7002644538879395},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.554243803024292},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5105177164077759},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5096786022186279},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.4959612786769867},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46801483631134033},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.43902215361595154},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35538920760154724},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.22177258133888245},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15049871802330017},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.07769778370857239}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8264880180358887},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7002644538879395},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.554243803024292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5105177164077759},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5096786022186279},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.4959612786769867},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46801483631134033},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.43902215361595154},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35538920760154724},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.22177258133888245},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15049871802330017},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.07769778370857239},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10445894","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445894","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2033256038","https://openalex.org/W2127141656","https://openalex.org/W2508162385","https://openalex.org/W2889423969","https://openalex.org/W2963122170","https://openalex.org/W2963211188","https://openalex.org/W3036601975","https://openalex.org/W3168867926","https://openalex.org/W3174770825","https://openalex.org/W3176828726","https://openalex.org/W3195577433","https://openalex.org/W3202037040","https://openalex.org/W3204696009","https://openalex.org/W3205717164","https://openalex.org/W4205991051","https://openalex.org/W4225529283","https://openalex.org/W4226033575","https://openalex.org/W4313483544","https://openalex.org/W4313680121","https://openalex.org/W4322718191","https://openalex.org/W4323066695","https://openalex.org/W4375850650","https://openalex.org/W4375869211","https://openalex.org/W4378105483","https://openalex.org/W4385245566","https://openalex.org/W4385823224","https://openalex.org/W6738045163","https://openalex.org/W6759579507","https://openalex.org/W6780218876","https://openalex.org/W6780226713","https://openalex.org/W6796581206","https://openalex.org/W6800751262","https://openalex.org/W6802614535","https://openalex.org/W6810673746","https://openalex.org/W6847363464","https://openalex.org/W6848909144","https://openalex.org/W6848918270","https://openalex.org/W6850218400","https://openalex.org/W6850625674","https://openalex.org/W6852800892","https://openalex.org/W6852909395"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W1761388607","https://openalex.org/W1997922073","https://openalex.org/W2604685715","https://openalex.org/W2412160900","https://openalex.org/W2136453575","https://openalex.org/W1596913645","https://openalex.org/W1024498263","https://openalex.org/W4394775207"],"abstract_inverted_index":{"A":[0],"recent":[1],"paradigm":[2],"shift":[3],"in":[4,62],"artificial":[5],"intelligence":[6],"has":[7],"seen":[8],"the":[9,16,21,55,98,117,125,129,147,169],"rise":[10],"of":[11,27,36,119,124,149,152],"foundation":[12,39,60],"models,":[13],"such":[14,78],"as":[15,79],"large":[17],"language":[18,113,131],"models":[19,40,61],"and":[20,30,87,107,128,146,161],"universal":[22,112,130],"speech":[23,91],"models.":[24],"With":[25],"billions":[26],"model":[28,103],"parameters":[29],"trained":[31],"with":[32,104,110,164],"a":[33,45,63,111],"wide":[34],"range":[35],"data,":[37],"these":[38,59,140,153],"are":[41],"expected":[42],"to":[43,48,57,138],"have":[44],"better":[46],"generalization":[47],"different":[49,143],"downstream":[50],"tasks.":[51],"Efficient":[52],"adaptation":[53,160],"is":[54],"key":[56],"leveraging":[58],"new":[64],"task":[65],"or":[66,122],"domain.":[67],"In":[68],"this":[69],"paper,":[70],"we":[71],"compare":[72],"several":[73],"popular":[74],"parameter-efficient":[75],"tuning":[76],"methods,":[77],"vector":[80,159],"adaptation,":[81],"residual":[82,162],"adapters,":[83],"low-rank":[84],"adapter":[85],"(LoRA)":[86],"prompt-tuning,":[88],"for":[89],"automatic":[90],"recognition":[92],"(ASR)":[93],"domain":[94],"adaptation.":[95],"We":[96,115,133,155],"use":[97],"connectionist":[99],"temporal":[100],"classification":[101],"(CTC)":[102],"Conformer":[105,126],"encoder":[106,127],"fused":[108],"it":[109],"model.":[114,132],"study":[116,139],"effect":[118,148],"adapting":[120],"either":[121],"both":[123],"carry":[134],"out":[135],"extensive":[136],"experiments":[137],"methods":[141],"under":[142],"hyper-parameter":[144],"settings":[145],"combining":[150,158],"some":[151],"methods.":[154],"find":[156],"that":[157],"adapters":[163],"increasing":[165],"bottleneck":[166],"dimension":[167],"achieved":[168],"best":[170],"performance.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}