{"id":"https://openalex.org/W4392904635","doi":"https://doi.org/10.1109/icassp48485.2024.10446990","title":"Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adapter","display_name":"Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adapter","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904635","doi":"https://doi.org/10.1109/icassp48485.2024.10446990"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446990","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446990","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/A5100448208","display_name":"Song Li","orcid":"https://orcid.org/0000-0002-7961-8502"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Song Li","raw_affiliation_strings":["Meituan"],"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029259399","display_name":"Yongbin You","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongbin You","raw_affiliation_strings":["Meituan"],"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024842018","display_name":"Xuezhi Wang","orcid":"https://orcid.org/0000-0001-7592-2358"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuezhi Wang","raw_affiliation_strings":["Meituan"],"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101687273","display_name":"Ke Ding","orcid":"https://orcid.org/0000-0002-0476-2710"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ke Ding","raw_affiliation_strings":["Meituan"],"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072537055","display_name":"Guanglu Wan","orcid":"https://orcid.org/0009-0003-1061-3724"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guanglu Wan","raw_affiliation_strings":["Meituan"],"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100448208"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4548,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.83450905,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"10941","last_page":"10945"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T12031","display_name":"Speech and dialogue systems","score":0.9997000098228455,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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/computer-science","display_name":"Computer science","score":0.8771456480026245},{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.7351563572883606},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5044823884963989},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5030280947685242},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4874315559864044},{"id":"https://openalex.org/keywords/multilingualism","display_name":"Multilingualism","score":0.4712163507938385},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47074681520462036},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47014716267585754},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4325616955757141},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.43010199069976807},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08335137367248535},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.08333346247673035}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8771456480026245},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.7351563572883606},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5044823884963989},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5030280947685242},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4874315559864044},{"id":"https://openalex.org/C2780035574","wikidata":"https://www.wikidata.org/wiki/Q30081","display_name":"Multilingualism","level":2,"score":0.4712163507938385},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47074681520462036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47014716267585754},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4325616955757141},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.43010199069976807},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08335137367248535},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.08333346247673035},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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/icassp48485.2024.10446990","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446990","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":18,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2204007436","https://openalex.org/W2786835190","https://openalex.org/W2963242190","https://openalex.org/W2964303773","https://openalex.org/W2964309797","https://openalex.org/W2971840980","https://openalex.org/W3030437843","https://openalex.org/W3096032230","https://openalex.org/W3174770825","https://openalex.org/W3198429080","https://openalex.org/W4205991051","https://openalex.org/W4226502599","https://openalex.org/W4234380012","https://openalex.org/W4287726212","https://openalex.org/W4291566970","https://openalex.org/W4297841565","https://openalex.org/W4372349677"],"related_works":["https://openalex.org/W2368605798","https://openalex.org/W2518037665","https://openalex.org/W2348524959","https://openalex.org/W2477036161","https://openalex.org/W2368049389","https://openalex.org/W2384861574","https://openalex.org/W4294565801","https://openalex.org/W2170801710","https://openalex.org/W2952704802","https://openalex.org/W4321593827"],"abstract_inverted_index":{"Multilingual":[0],"intelligent":[1],"assistants,":[2],"such":[3],"as":[4],"ChatGPT,":[5],"have":[6],"recently":[7],"gained":[8],"popularity.":[9],"To":[10],"further":[11],"expand":[12],"the":[13,30,73],"applications":[14],"of":[15,32,41,75],"multilingual":[16,33,67],"artificial":[17],"intelligence":[18],"(AI)":[19],"assistants":[20],"and":[21,51,57,65],"facilitate":[22],"international":[23],"communication,":[24],"it":[25],"is":[26,37],"essential":[27],"to":[28,61],"enhance":[29,63],"performance":[31,88],"speech":[34,42,68],"recognition,":[35],"which":[36],"a":[38],"crucial":[39],"component":[40],"interaction.":[43],"In":[44],"this":[45],"paper,":[46],"we":[47,71],"propose":[48],"two":[49,78],"simple":[50],"parameter-efficient":[52,81],"methods:":[53],"language":[54,59],"prompt":[55],"tuning":[56],"frame-level":[58],"adapter,":[60],"respectively":[62],"language-configurable":[64],"language-agnostic":[66],"recognition.":[69],"Additionally,":[70],"explore":[72],"feasibility":[74],"integrating":[76],"these":[77],"approaches":[79],"using":[80,93],"fine-tuning":[82],"methods.":[83,96],"Our":[84],"experiments":[85],"demonstrate":[86],"significant":[87],"improvements":[89],"across":[90],"seven":[91],"languages":[92],"our":[94],"proposed":[95]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
