{"id":"https://openalex.org/W4409362590","doi":"https://doi.org/10.1609/aaai.v39i23.34617","title":"LAMA-UT: Language Agnostic Multilingual ASR Through Orthography Unification and Language-Specific Transliteration","display_name":"LAMA-UT: Language Agnostic Multilingual ASR Through Orthography Unification and Language-Specific Transliteration","publication_year":2025,"publication_date":"2025-04-11","ids":{"openalex":"https://openalex.org/W4409362590","doi":"https://doi.org/10.1609/aaai.v39i23.34617"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v39i23.34617","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i23.34617","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/34617/36772","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/34617/36772","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100319634","display_name":"Sangmin Lee","orcid":"https://orcid.org/0000-0003-1693-1152"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sangmin Lee","raw_affiliation_strings":["Yonsei University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yonsei University","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054584660","display_name":"Woojin Chung","orcid":"https://orcid.org/0000-0003-0736-3624"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Woojin Chung","raw_affiliation_strings":["Yonsei University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yonsei University","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056128107","display_name":"Hong-Goo Kang","orcid":"https://orcid.org/0000-0002-6554-0783"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hong-Goo Kang","raw_affiliation_strings":["Yonsei University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yonsei University","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I193775966"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11630037,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"39","issue":"23","first_page":"24393","last_page":"24401"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9354000091552734,"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":0.9354000091552734,"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/transliteration","display_name":"Transliteration","score":0.8970204591751099},{"id":"https://openalex.org/keywords/orthography","display_name":"Orthography","score":0.8232783079147339},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.6062270998954773},{"id":"https://openalex.org/keywords/unification","display_name":"Unification","score":0.5734190344810486},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5187276005744934},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49664026498794556},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4305555522441864},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.11403617262840271},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1010025143623352}],"concepts":[{"id":"https://openalex.org/C520968082","wikidata":"https://www.wikidata.org/wiki/Q134550","display_name":"Transliteration","level":2,"score":0.8970204591751099},{"id":"https://openalex.org/C150670947","wikidata":"https://www.wikidata.org/wiki/Q43091","display_name":"Orthography","level":3,"score":0.8232783079147339},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.6062270998954773},{"id":"https://openalex.org/C96146094","wikidata":"https://www.wikidata.org/wiki/Q609057","display_name":"Unification","level":2,"score":0.5734190344810486},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5187276005744934},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49664026498794556},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4305555522441864},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.11403617262840271},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1010025143623352},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v39i23.34617","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i23.34617","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/34617/36772","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v39i23.34617","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i23.34617","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/34617/36772","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409362590.pdf","grobid_xml":"https://content.openalex.org/works/W4409362590.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3153459181","https://openalex.org/W2147866274","https://openalex.org/W2350015575","https://openalex.org/W2371976984","https://openalex.org/W2352160949","https://openalex.org/W2378436233","https://openalex.org/W2251148428","https://openalex.org/W2907809867","https://openalex.org/W2522857523","https://openalex.org/W2069398544"],"abstract_inverted_index":{"Building":[0],"a":[1,17,30,57,72,94,125,185],"universal":[2,73,95,100,116],"multilingual":[3,120,189],"automatic":[4],"speech":[5],"recognition":[6],"(ASR)":[7],"model":[8],"that":[9,192],"performs":[10,137,163],"equitably":[11],"across":[12,88],"languages":[13],"has":[14],"long":[15],"been":[16],"challenge":[18],"due":[19],"to":[20,76,97,134,139,182,196],"its":[21],"inherent":[22],"difficulties.":[23],"To":[24],"address":[25],"this":[26,180],"task":[27],"we":[28,70,92,107],"introduce":[29],"Language-Agnostic":[31],"Multilingual":[32],"ASR":[33,168,190],"pipeline":[34,63,123,153],"through":[35],"orthography":[36],"Unification":[37],"and":[38,83,136,175],"language-specific":[39,46,103,159,173],"Transliteration":[40],"(LAMA-UT).":[41],"LAMA-UT":[42],"operates":[43],"without":[44],"any":[45,158],"modules":[47],"while":[48],"matching":[49],"the":[50,109],"performance":[51],"of":[52,60,65,111,130,147],"state-of-the-art":[53],"models":[54],"trained":[55,143],"on":[56,144,157,164],"minimal":[58],"amount":[59],"data.":[61,150],"Our":[62,122],"consists":[64],"two":[66],"key":[67],"steps.":[68],"First,":[69],"utilize":[71,93,171],"transcription":[74],"generator":[75],"unify":[77],"orthographic":[78],"features":[79],"into":[80,102],"Romanized":[81],"form":[82],"capture":[84],"common":[85],"phonetic":[86],"characteristics":[87],"diverse":[89],"languages.":[90,198],"Second,":[91],"converter":[96],"transform":[98],"these":[99],"transcriptions":[101,117],"ones.":[104],"In":[105],"experiments,":[106],"demonstrate":[108],"effectiveness":[110],"our":[112,152],"proposed":[113],"method":[114],"leveraging":[115],"for":[118,187],"massively":[119],"ASR.":[121],"achieves":[124],"relative":[126],"error":[127],"reduction":[128],"rate":[129],"45%":[131],"when":[132],"compared":[133],"Whisper":[135],"comparably":[138],"MMS,":[140],"despite":[141],"being":[142],"only":[145],"0.1%":[146],"Whisper's":[148],"training":[149],"Furthermore,":[151],"does":[154],"not":[155],"rely":[156],"modules.":[160],"However,":[161],"it":[162],"par":[165],"with":[166],"zero-shot":[167],"approaches":[169],"which":[170],"additional":[172],"lexicons":[174],"language":[176],"models.":[177],"We":[178],"expect":[179],"framework":[181],"serve":[183],"as":[184],"cornerstone":[186],"flexible":[188],"systems":[191],"are":[193],"generalizable":[194],"even":[195],"unseen":[197]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
