{"id":"https://openalex.org/W4406461659","doi":"https://doi.org/10.1109/slt61566.2024.10832233","title":"Romanization Encoding For Multilingual ASR","display_name":"Romanization Encoding For Multilingual ASR","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461659","doi":"https://doi.org/10.1109/slt61566.2024.10832233"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832233","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832233","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5103671085","display_name":"Ding Wen","orcid":"https://orcid.org/0009-0005-2256-8857"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wen Ding","raw_affiliation_strings":["NVIDIA Corporation"],"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011196247","display_name":"Fei Jia","orcid":"https://orcid.org/0000-0001-5212-6551"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fei Jia","raw_affiliation_strings":["NVIDIA Corporation"],"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100409299","display_name":"Xu H","orcid":"https://orcid.org/0009-0001-1201-443X"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hainan Xu","raw_affiliation_strings":["NVIDIA Corporation"],"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102383536","display_name":"Yu Xi","orcid":"https://orcid.org/0009-0002-8918-3829"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Xi","raw_affiliation_strings":["NVIDIA Corporation"],"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103287856","display_name":"Junjie Lai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junjie Lai","raw_affiliation_strings":["NVIDIA Corporation"],"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032957280","display_name":"Boris Ginsburg","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boris Ginsburg","raw_affiliation_strings":["NVIDIA Corporation"],"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5103671085"],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2383835,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"468","last_page":"475"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9976000189781189,"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":0.9828000068664551,"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/romanization","display_name":"Romanization","score":0.8870639801025391},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7644388675689697},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.6713228821754456},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5013675689697266},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37182512879371643},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34929364919662476},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2312985360622406}],"concepts":[{"id":"https://openalex.org/C106930687","wikidata":"https://www.wikidata.org/wiki/Q976327","display_name":"Romanization","level":2,"score":0.8870639801025391},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7644388675689697},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6713228821754456},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5013675689697266},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37182512879371643},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34929364919662476},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2312985360622406},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832233","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832233","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4699999988079071,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W197277712","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2804732445","https://openalex.org/W2889048668","https://openalex.org/W2936774411","https://openalex.org/W2939757332","https://openalex.org/W2944852028","https://openalex.org/W2963242190","https://openalex.org/W2963382687","https://openalex.org/W2963850025","https://openalex.org/W2963979492","https://openalex.org/W2964084554","https://openalex.org/W2972417954","https://openalex.org/W2989143494","https://openalex.org/W3007376164","https://openalex.org/W3015615177","https://openalex.org/W3096122506","https://openalex.org/W3096767609","https://openalex.org/W3097306574","https://openalex.org/W3160201895","https://openalex.org/W4210423654","https://openalex.org/W4221157256","https://openalex.org/W4224919682","https://openalex.org/W4226440507","https://openalex.org/W4283700324","https://openalex.org/W4297727296","https://openalex.org/W4311000453","https://openalex.org/W4323066695","https://openalex.org/W4366197103","https://openalex.org/W4372189025","https://openalex.org/W4375869049","https://openalex.org/W4377116057","https://openalex.org/W4378105483","https://openalex.org/W4385822890","https://openalex.org/W4389518416","https://openalex.org/W4389520101","https://openalex.org/W4391021542","https://openalex.org/W6631190155","https://openalex.org/W6754473786","https://openalex.org/W6785049136","https://openalex.org/W6787069835","https://openalex.org/W6810058749","https://openalex.org/W6847363464","https://openalex.org/W6850218400","https://openalex.org/W6851766456","https://openalex.org/W6852909395"],"related_works":["https://openalex.org/W2170685659","https://openalex.org/W2899224223","https://openalex.org/W2376933048","https://openalex.org/W4238918564","https://openalex.org/W2294494798","https://openalex.org/W3184806679","https://openalex.org/W1974228456","https://openalex.org/W4280493291","https://openalex.org/W4281717551","https://openalex.org/W3204019825"],"abstract_inverted_index":{"We":[0],"introduce":[1],"romanization":[2,19],"encoding":[3,20],"for":[4,116],"script-heavy":[5,111],"languages":[6],"to":[7,72,105],"optimize":[8],"multilingual":[9,121],"and":[10,39,46,55,61,82,88,98,119],"code-switching":[11,92],"Automatic":[12],"Speech":[13],"Recognition":[14],"(ASR)":[15],"systems.":[16,123],"By":[17],"adopting":[18],"alongside":[21],"a":[22,27,32,77],"balanced":[23],"concatenated":[24],"tokenizer":[25],"within":[26],"FastConformer-RNNT":[28],"framework":[29],"equipped":[30],"with":[31],"Roman2Char":[33],"module,":[34],"we":[35],"significantly":[36],"reduce":[37],"vocabulary":[38,80],"output":[40],"dimensions,":[41],"enabling":[42],"larger":[43],"training":[44],"batches":[45],"reduced":[47],"memory":[48],"consumption.":[49],"Our":[50],"method":[51,71],"decouples":[52],"acoustic":[53],"modeling":[54],"language":[56],"modeling,":[57],"enhancing":[58],"the":[59,64,107,114],"flexibility":[60],"adaptability":[62],"of":[63,86,109],"system.":[65],"In":[66],"our":[67,101],"study,":[68],"applying":[69],"this":[70],"Mandarin-English":[73],"ASR":[74,122],"resulted":[75],"in":[76],"remarkable":[78],"63.51%":[79],"reduction":[81],"notable":[83],"performance":[84],"gains":[85],"13.72%":[87],"15.03%":[89],"on":[90,96],"SEAME":[91],"benchmarks.":[93],"Ablation":[94],"studies":[95],"MandarinKorean":[97],"Mandarin-Japanese":[99],"highlight":[100],"method\u2019s":[102],"strong":[103],"capability":[104],"address":[106],"complexities":[108],"other":[110],"languages,":[112],"paving":[113],"way":[115],"more":[117],"versatile":[118],"effective":[120]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}