{"id":"https://openalex.org/W7148391750","doi":"https://doi.org/10.1109/asru65441.2025.11434786","title":"Towards Scalable and Robust Multilingual ASR for Indian Languages with MixLoRA-Whisper","display_name":"Towards Scalable and Robust Multilingual ASR for Indian Languages with MixLoRA-Whisper","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148391750","doi":"https://doi.org/10.1109/asru65441.2025.11434786"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434786","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434786","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5086441837","display_name":"Yeseul Park","orcid":"https://orcid.org/0000-0001-9168-1064"},"institutions":[{"id":"https://openalex.org/I191879574","display_name":"Inha University","ror":"https://ror.org/01easw929","country_code":"KR","type":"education","lineage":["https://openalex.org/I191879574"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Yeseul Park","raw_affiliation_strings":["Inha University,Department of Electrical and Computer Engineering,Incheon,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Inha University,Department of Electrical and Computer Engineering,Incheon,Republic of Korea","institution_ids":["https://openalex.org/I191879574"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089545632","display_name":"Bowon Lee","orcid":"https://orcid.org/0000-0001-5417-5699"},"institutions":[{"id":"https://openalex.org/I191879574","display_name":"Inha University","ror":"https://ror.org/01easw929","country_code":"KR","type":"education","lineage":["https://openalex.org/I191879574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Bowon Lee","raw_affiliation_strings":["Inha University,Department of Electrical and Computer Engineering,Incheon,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Inha University,Department of Electrical and Computer Engineering,Incheon,Republic of Korea","institution_ids":["https://openalex.org/I191879574"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5086441837"],"corresponding_institution_ids":["https://openalex.org/I191879574"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87561307,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.4138999879360199,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.4138999879360199,"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":0.23240000009536743,"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":0.07559999823570251,"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/scalability","display_name":"Scalability","score":0.4131999909877777},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.30799999833106995},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.28139999508857727},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.2720000147819519},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.27000001072883606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6796000003814697},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48919999599456787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44179999828338623},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4131999909877777},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2913999855518341},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2759000062942505},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2720000147819519},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434786","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434786","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8101761937141418,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2789316633","https://openalex.org/W3213029956","https://openalex.org/W3213618310","https://openalex.org/W4319862635","https://openalex.org/W4402112032","https://openalex.org/W4405709593","https://openalex.org/W4409642688","https://openalex.org/W4411203695"],"related_works":[],"abstract_inverted_index":{"India":[0],"exhibits":[1],"extensive":[2],"linguistic":[3,69],"diversity,":[4],"with":[5,90],"many":[6],"regional":[7],"languages":[8,89,120],"and":[9,25,56,124],"dialects,":[10,92],"yet":[11],"current":[12],"multilingual":[13],"automatic":[14],"speech":[15,123],"recognition":[16],"(ASR)":[17],"models":[18],"provide":[19],"limited":[20],"support,":[21],"especially":[22],"for":[23,41,138],"low-income":[24],"rural":[26],"populations":[27],"who":[28],"rely":[29],"on":[30,81,102],"spoken":[31],"communication.":[32],"We":[33],"apply":[34],"MixLoRA,":[35],"a":[36,95,107],"parameterefficient":[37],"fine-tuning":[38,72],"method":[39],"proposed":[40],"large":[42],"language":[43],"models,":[44],"to":[45,47,75],"Whisper":[46],"improve":[48],"ASR":[49,137],"performance.":[50],"MixLoRA":[51,133],"employs":[52],"multiple":[53],"LoRA":[54],"experts":[55,62],"dynamically":[57],"selects":[58],"the":[59,79,82,103,114],"most":[60],"relevant":[61],"per":[63],"token,":[64],"enabling":[65],"better":[66],"modeling":[67],"of":[68,78],"variation.":[70],"By":[71],"only":[73],"up":[74],"25.03":[76],"%":[77],"parameters":[80],"RESPIN":[83],"dataset,":[84],"which":[85],"covers":[86],"eight":[87],"Indian":[88],"33":[91],"it":[93],"achieves":[94],"$4.98":[96],"\\%$":[97,109],"character":[98],"error":[99],"rate":[100],"(CER)":[101],"read":[104,122],"speech,":[105],"yielding":[106],"$7.09":[108],"relative":[110],"CER":[111],"reduction":[112],"over":[113],"baseline.":[115],"Performance":[116],"improved":[117],"across":[118],"all":[119],"in":[121,126],"five":[125],"spontaneous":[127],"speech.":[128],"These":[129],"results":[130],"demonstrate":[131],"that":[132],"can":[134],"effectively":[135],"enhance":[136],"low-resource,":[139],"dialect-rich":[140],"languages.":[141]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}