{"id":"https://openalex.org/W4391021634","doi":"https://doi.org/10.1109/asru57964.2023.10389744","title":"Audio-Adapterfusion: A Task-Id-Free Approach for Efficient and Non-Destructive Multi-Task Speech Recognition","display_name":"Audio-Adapterfusion: A Task-Id-Free Approach for Efficient and Non-Destructive Multi-Task Speech Recognition","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021634","doi":"https://doi.org/10.1109/asru57964.2023.10389744"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389744","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asru57964.2023.10389744","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5034225316","display_name":"Hillary Ngai","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":true,"raw_author_name":"Hillary Ngai","raw_affiliation_strings":["Google LLC"],"affiliations":[{"raw_affiliation_string":"Google LLC","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022334466","display_name":"Rohan Agrawal","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":"Rohan Agrawal","raw_affiliation_strings":["Google LLC"],"affiliations":[{"raw_affiliation_string":"Google LLC","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016601028","display_name":"Neeraj Gaur","orcid":"https://orcid.org/0000-0002-5926-9966"},"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":"Neeraj Gaur","raw_affiliation_strings":["Google LLC"],"affiliations":[{"raw_affiliation_string":"Google LLC","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006141298","display_name":"Ronny Huang","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":"Ronny Huang","raw_affiliation_strings":["Google LLC"],"affiliations":[{"raw_affiliation_string":"Google LLC","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037705635","display_name":"Parisa Haghani","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":"Parisa Haghani","raw_affiliation_strings":["Google LLC"],"affiliations":[{"raw_affiliation_string":"Google LLC","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048766619","display_name":"Pedro Moreno Mengibar","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":"Pedro Moreno Mengibar","raw_affiliation_strings":["Google LLC"],"affiliations":[{"raw_affiliation_string":"Google LLC","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5034225316"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19178041,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"abs/2012.15419","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.8189953565597534},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6387428641319275},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6185124516487122},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.5734136700630188},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5623924136161804},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.44184187054634094},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.4212642014026642},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3836615979671478},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35781314969062805},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06860318779945374}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8189953565597534},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6387428641319275},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6185124516487122},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5734136700630188},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5623924136161804},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.44184187054634094},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4212642014026642},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3836615979671478},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35781314969062805},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06860318779945374},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389744","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asru57964.2023.10389744","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W2127141656","https://openalex.org/W2526425061","https://openalex.org/W2560647685","https://openalex.org/W2624871570","https://openalex.org/W2810421208","https://openalex.org/W2936774411","https://openalex.org/W2963303951","https://openalex.org/W2975043431","https://openalex.org/W2990138404","https://openalex.org/W3016234571","https://openalex.org/W3093579165","https://openalex.org/W3097777922","https://openalex.org/W3120441516","https://openalex.org/W3122503268","https://openalex.org/W3153675281","https://openalex.org/W3156323585","https://openalex.org/W3162037819","https://openalex.org/W3163793923","https://openalex.org/W3163907627","https://openalex.org/W3165404421","https://openalex.org/W3197530164","https://openalex.org/W4225274946","https://openalex.org/W4285119752","https://openalex.org/W4306955484","https://openalex.org/W4322614701","https://openalex.org/W4372260573","https://openalex.org/W4375868763","https://openalex.org/W4385823224","https://openalex.org/W6638749077","https://openalex.org/W6739365718","https://openalex.org/W6755862295","https://openalex.org/W6758026734","https://openalex.org/W6759579507","https://openalex.org/W6780226713","https://openalex.org/W6784614252","https://openalex.org/W6788389576","https://openalex.org/W6789747651","https://openalex.org/W6803156713"],"related_works":["https://openalex.org/W2948333011","https://openalex.org/W4386619269","https://openalex.org/W1942758450","https://openalex.org/W2994972936","https://openalex.org/W2922338626","https://openalex.org/W4303645333","https://openalex.org/W4312745891","https://openalex.org/W3088045114","https://openalex.org/W2108010283","https://openalex.org/W4221067497"],"abstract_inverted_index":{"Adapters":[0],"are":[1,112,140],"an":[2,129],"efficient,":[3],"composable":[4],"alternative":[5],"to":[6,21,32,37,39,80,136],"full":[7,137],"fine-tuning":[8,138],"of":[9,17,50,121],"pre-trained":[10],"models":[11,20],"and":[12,87,107,114,139],"help":[13],"scale":[14],"the":[15,33,43,55,122],"deployment":[16],"large":[18],"ASR":[19,86,105],"many":[22],"tasks.":[23],"In":[24],"practice,":[25],"a":[26],"task":[27,56],"ID":[28,57],"is":[29,53],"commonly":[30],"prepended":[31],"input":[34],"during":[35,62],"inference":[36],"route":[38],"single-task":[40,82],"adapters":[41,83],"for":[42,67,92],"specified":[44],"task.":[45],"However,":[46],"one":[47],"major":[48],"limitation":[49],"this":[51],"approach":[52],"that":[54,109],"may":[58],"not":[59],"be":[60],"known":[61],"inference,":[63],"rendering":[64],"it":[65],"unsuitable":[66],"most":[68],"multi-task":[69,85],"settings.":[70],"To":[71],"address":[72],"this,":[73],"we":[74],"propose":[75],"three":[76],"novel":[77],"task-ID-free":[78],"methods":[79,97,111,126],"combine":[81],"in":[84],"investigate":[88],"two":[89],"learning":[90],"algorithms":[91],"training.":[93],"We":[94],"evaluate":[95],"our":[96,110,125],"on":[98],"10":[99],"test":[100],"sets":[101],"from":[102],"4":[103],"diverse":[104],"tasks":[106],"show":[108],"non-destructive":[113],"parameter-efficient.":[115],"While":[116],"only":[117],"updating":[118],"17":[119],"%":[120,131],"model":[123],"parameters,":[124],"can":[127],"achieve":[128],"8":[130],"mean":[132],"WER":[133],"improvement":[134],"relative":[135],"on-par":[141],"with":[142],"task-ID":[143],"adapter":[144],"routing.":[145]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}