{"id":"https://openalex.org/W4401016696","doi":"https://doi.org/10.1109/taslp.2024.3434445","title":"ELP-Adapters: Parameter Efficient Adapter Tuning for Various Speech Processing Tasks","display_name":"ELP-Adapters: Parameter Efficient Adapter Tuning for Various Speech Processing Tasks","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4401016696","doi":"https://doi.org/10.1109/taslp.2024.3434445"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3434445","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3434445","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5101261291","display_name":"Nakamasa Inoue","orcid":"https://orcid.org/0009-0006-1145-0914"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nakamasa Inoue","raw_affiliation_strings":["Department of Computer Science, Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0006-1145-0914","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044298727","display_name":"Shinta Otake","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinta Otake","raw_affiliation_strings":["Department of Computer Science, Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113319829","display_name":"Takumi Hirose","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takumi Hirose","raw_affiliation_strings":["Department of Computer Science, Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105100173","display_name":"Masanari Ohi","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masanari Ohi","raw_affiliation_strings":["Department of Computer Science, Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113695192","display_name":"Rei Kawakami","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Rei Kawakami","raw_affiliation_strings":["Department of Systems and Control Engineering, Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems and Control Engineering, Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.327,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.93069433,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"3867","last_page":"3880"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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/T12031","display_name":"Speech and dialogue systems","score":0.9968000054359436,"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":0.9554283618927002},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6343933343887329},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5224277377128601},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.287904292345047}],"concepts":[{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.9554283618927002},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6343933343887329},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5224277377128601},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.287904292345047}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3434445","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3434445","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W125553504","https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2146334809","https://openalex.org/W2157161740","https://openalex.org/W2602034649","https://openalex.org/W2726515241","https://openalex.org/W2784163702","https://openalex.org/W2890964092","https://openalex.org/W2896457183","https://openalex.org/W2899663614","https://openalex.org/W2971840980","https://openalex.org/W2972584841","https://openalex.org/W2973049979","https://openalex.org/W2995181338","https://openalex.org/W3103152812","https://openalex.org/W3103616906","https://openalex.org/W3119308075","https://openalex.org/W3121914243","https://openalex.org/W3161686170","https://openalex.org/W3162226363","https://openalex.org/W3163162786","https://openalex.org/W3165404421","https://openalex.org/W3172698324","https://openalex.org/W3175898847","https://openalex.org/W3191850102","https://openalex.org/W3196464216","https://openalex.org/W3196863408","https://openalex.org/W3197032408","https://openalex.org/W3197580070","https://openalex.org/W3197642003","https://openalex.org/W3197763626","https://openalex.org/W3197845195","https://openalex.org/W3198275944","https://openalex.org/W3198608154","https://openalex.org/W3198694222","https://openalex.org/W3202370288","https://openalex.org/W3206252155","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4225274946","https://openalex.org/W4225303417","https://openalex.org/W4226380987","https://openalex.org/W4285250921","https://openalex.org/W4292387508","https://openalex.org/W4297841635","https://openalex.org/W4319862642","https://openalex.org/W4322731117","https://openalex.org/W4372270069","https://openalex.org/W4385823373","https://openalex.org/W4385823432","https://openalex.org/W4388181563","https://openalex.org/W4392969497","https://openalex.org/W4394862910","https://openalex.org/W6755977528","https://openalex.org/W6759579507","https://openalex.org/W6779230768","https://openalex.org/W6780218876","https://openalex.org/W6780226713","https://openalex.org/W6781368565","https://openalex.org/W6788328058","https://openalex.org/W6788335241","https://openalex.org/W6796581206","https://openalex.org/W6839738141"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1,9],"has":[2],"emerged":[3],"as":[4,22],"a":[5,30,52,71],"key":[6],"approach":[7],"for":[8,40,55,93,121],"generic":[10],"representations":[11,89],"from":[12,100,114],"speech":[13,23,88,94,151],"data.":[14],"Despite":[15],"promising":[16],"results":[17],"in":[18],"downstream":[19,106,158],"tasks":[20,159,189],"such":[21],"recognition,":[24,29],"speaker":[25,122],"verification,":[26],"and":[27,70,83,108,124,139],"emotion":[28,125],"significant":[31],"number":[32],"of":[33,61,167,184],"parameters":[34],"is":[35],"required,":[36],"which":[37],"makes":[38],"fine-tuning":[39,57,186],"each":[41,101],"task":[42],"memory-inefficient.":[43],"To":[44],"address":[45],"this":[46],"limitation,":[47],"we":[48],"introduce":[49],"ELP-adapter":[50],"tuning,":[51],"novel":[53],"method":[54],"parameter-efficient":[56],"using":[58,160],"three":[59],"types":[60],"adapter,":[62],"namely":[63],"encoder":[64,81,102,116],"adapters":[65,68],"(E-adapters),":[66],"layer":[67,103],"(L-adapters),":[69],"prompt":[72],"adapter":[73],"(P-adapter).":[74],"The":[75,96,127],"E-adapters":[76],"are":[77,91,119],"integrated":[78],"into":[79],"transformer-based":[80],"layers":[82,117],"help":[84,109],"to":[85,104,110,132,135,149,179],"learn":[86],"finegrained":[87],"that":[90,118,183],"effective":[92,120],"recognition.":[95,126],"L-adapters":[97],"create":[98],"paths":[99],"the":[105,165,168,172],"head":[107],"extract":[111],"non-linguistic":[112],"features":[113,131,134],"lower":[115],"verification":[123],"P-adapter":[128],"appends":[129],"pseudo":[130],"CNN":[133],"further":[136],"improve":[137],"effectiveness":[138,166],"efficiency.":[140],"With":[141,171],"these":[142],"adapters,":[143],"models":[144,163],"can":[145],"be":[146],"quickly":[147],"adapted":[148],"various":[150],"processing":[152],"tasks.":[153],"Our":[154],"evaluation":[155],"across":[156],"four":[157],"five":[161],"backbone":[162],"demonstrated":[164],"proposed":[169],"method.":[170],"WavLM":[173],"backbone,":[174],"its":[175],"performance":[176],"was":[177],"comparable":[178],"or":[180],"better":[181],"than":[182],"full":[185],"on":[187],"all":[188],"while":[190],"requiring":[191],"90%":[192],"fewer":[193],"learnable":[194],"parameters.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8}],"updated_date":"2026-06-17T08:01:34.144755","created_date":"2025-10-10T00:00:00"}