{"id":"https://openalex.org/W4392910290","doi":"https://doi.org/10.1109/icassp48485.2024.10448240","title":"An Adapter-Based Unified Model for Multiple Spoken Language Processing Tasks","display_name":"An Adapter-Based Unified Model for Multiple Spoken Language Processing Tasks","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910290","doi":"https://doi.org/10.1109/icassp48485.2024.10448240"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448240","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448240","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":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.14747","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073103551","display_name":"Varsha Suresh","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Varsha Suresh","raw_affiliation_strings":["National University of Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087093293","display_name":"Salah A\u0131\u0308t-Mokhtar","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Salah A\u00eft-Mokhtar","raw_affiliation_strings":["Naver Labs Europe"],"affiliations":[{"raw_affiliation_string":"Naver Labs Europe","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105462436","display_name":"Caroline Brun","orcid":"https://orcid.org/0000-0003-2824-5221"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Caroline Brun","raw_affiliation_strings":["Naver Labs Europe"],"affiliations":[{"raw_affiliation_string":"Naver Labs Europe","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034647649","display_name":"Ioan Calapodescu","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ioan Calapodescu","raw_affiliation_strings":["Naver Labs Europe"],"affiliations":[{"raw_affiliation_string":"Naver Labs Europe","institution_ids":["https://openalex.org/I60922564"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5073103551"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":0.7205,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.73316889,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"10676","last_page":"10680"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9991000294685364,"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/T12031","display_name":"Speech and dialogue systems","score":0.9991000294685364,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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/T10028","display_name":"Topic Modeling","score":0.9984999895095825,"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":0.8346828818321228},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8009939193725586},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.5150010585784912},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4282418191432953},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4199334383010864},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3881237506866455},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34609895944595337},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.105653315782547}],"concepts":[{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.8346828818321228},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8009939193725586},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.5150010585784912},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4282418191432953},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4199334383010864},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3881237506866455},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34609895944595337},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.105653315782547}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448240","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448240","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"},{"id":"pmh:oai:arXiv.org:2406.14747","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.14747","pdf_url":"https://arxiv.org/pdf/2406.14747","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2406.14747","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.14747","pdf_url":"https://arxiv.org/pdf/2406.14747","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392910290.pdf"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2146334809","https://openalex.org/W2766219058","https://openalex.org/W2884584040","https://openalex.org/W2972584841","https://openalex.org/W3036601975","https://openalex.org/W3037465386","https://openalex.org/W3096147072","https://openalex.org/W3098598562","https://openalex.org/W3099793224","https://openalex.org/W3122866338","https://openalex.org/W3161463965","https://openalex.org/W3161940574","https://openalex.org/W3162037819","https://openalex.org/W3172698324","https://openalex.org/W3197580070","https://openalex.org/W3198528147","https://openalex.org/W3205644108","https://openalex.org/W3208480086","https://openalex.org/W3217767527","https://openalex.org/W4224903522","https://openalex.org/W4225274946","https://openalex.org/W4293350112","https://openalex.org/W4297683418","https://openalex.org/W4297841873","https://openalex.org/W4311000453","https://openalex.org/W4385245566","https://openalex.org/W4385570643","https://openalex.org/W4385573307","https://openalex.org/W4385822952","https://openalex.org/W6739901393","https://openalex.org/W6751425476","https://openalex.org/W6752542827","https://openalex.org/W6759579507","https://openalex.org/W6780218876","https://openalex.org/W6785772365","https://openalex.org/W6795200824","https://openalex.org/W6847363464"],"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/W2160602540","https://openalex.org/W2485605994","https://openalex.org/W4385571108","https://openalex.org/W4321593827"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1],"models":[2,16],"have":[3],"revolutionized":[4],"the":[5,11,36,83,112],"field":[6],"of":[7,13,38,47,80,108,121],"speech":[8,101],"processing.":[9],"However,":[10],"process":[12],"fine-tuning":[14,40,92],"these":[15],"on":[17,82],"downstream":[18],"tasks":[19,56,103,115],"requires":[20],"substantial":[21],"computational":[22],"resources,":[23],"particularly":[24],"when":[25],"dealing":[26],"with":[27,104],"multiple":[28,50,100],"speech-processing":[29],"tasks.":[30,54],"In":[31],"this":[32],"paper,":[33],"we":[34,57],"explore":[35],"potential":[37],"adapter-based":[39,91],"in":[41,119],"developing":[42],"a":[43,78,94],"unified":[44],"model":[45,97],"capable":[46],"effectively":[48],"handling":[49],"spoken":[51],"language":[52],"processing":[53,102],"The":[55],"investigate":[58],"are":[59],"Automatic":[60],"Speech":[61],"Recognition,":[62,64],"Phoneme":[63],"Intent":[65],"Classification,":[66],"Slot":[67],"Filling,":[68],"and":[69,86],"Spoken":[70],"Emotion":[71],"Recognition.":[72],"We":[73],"validate":[74],"our":[75,87],"approach":[76],"through":[77],"series":[79],"experiments":[81],"SUPERB":[84],"benchmark,":[85],"results":[88],"indicate":[89],"that":[90],"enables":[93],"single":[95],"encoder-decoder":[96],"to":[98],"perform":[99],"an":[105],"average":[106],"improvement":[107],"18.4":[109],"%":[110],"across":[111],"five":[113],"target":[114],"while":[116],"staying":[117],"efficient":[118],"terms":[120],"parameter":[122],"updates.":[123]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}
