{"id":"https://openalex.org/W3015564377","doi":"https://doi.org/10.1109/icassp40776.2020.9053443","title":"Language-Agnostic Multilingual Modeling","display_name":"Language-Agnostic Multilingual Modeling","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015564377","doi":"https://doi.org/10.1109/icassp40776.2020.9053443","mag":"3015564377"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053443","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053443","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5036200604","display_name":"Arindrima Datta","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Arindrima Datta","raw_affiliation_strings":["NYC, Google Inc, USA"],"affiliations":[{"raw_affiliation_string":"NYC, Google Inc, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["NYC, Google Inc, USA"],"affiliations":[{"raw_affiliation_string":"NYC, Google Inc, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027399854","display_name":"Jesse Emond","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jesse Emond","raw_affiliation_strings":["NYC, Google Inc, USA"],"affiliations":[{"raw_affiliation_string":"NYC, Google Inc, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023098355","display_name":"Anjuli Kannan","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anjuli Kannan","raw_affiliation_strings":["NYC, Google Inc, USA"],"affiliations":[{"raw_affiliation_string":"NYC, Google Inc, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020068498","display_name":"Brian Roark","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Roark","raw_affiliation_strings":["NYC, Google Inc, USA"],"affiliations":[{"raw_affiliation_string":"NYC, Google Inc, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5036200604"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":3.0489,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.92835407,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"8239","last_page":"8243"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8818769454956055},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.67740398645401},{"id":"https://openalex.org/keywords/transliteration","display_name":"Transliteration","score":0.6682929992675781},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6049678921699524},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.575320303440094},{"id":"https://openalex.org/keywords/hindi","display_name":"Hindi","score":0.5357528924942017},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.42259445786476135},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3301458954811096}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8818769454956055},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.67740398645401},{"id":"https://openalex.org/C520968082","wikidata":"https://www.wikidata.org/wiki/Q134550","display_name":"Transliteration","level":2,"score":0.6682929992675781},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6049678921699524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.575320303440094},{"id":"https://openalex.org/C519982507","wikidata":"https://www.wikidata.org/wiki/Q1568","display_name":"Hindi","level":2,"score":0.5357528924942017},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.42259445786476135},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3301458954811096}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053443","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053443","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W126852431","https://openalex.org/W1496070437","https://openalex.org/W1828163288","https://openalex.org/W1975550806","https://openalex.org/W2048985487","https://openalex.org/W2090755665","https://openalex.org/W2094147890","https://openalex.org/W2127982613","https://openalex.org/W2134054733","https://openalex.org/W2153433699","https://openalex.org/W2184170932","https://openalex.org/W2606722458","https://openalex.org/W2617258110","https://openalex.org/W2633884958","https://openalex.org/W2697044473","https://openalex.org/W2716988359","https://openalex.org/W2746762542","https://openalex.org/W2769437540","https://openalex.org/W2786835190","https://openalex.org/W2889533859","https://openalex.org/W2891616026","https://openalex.org/W2900169601","https://openalex.org/W2913244614","https://openalex.org/W2914699162","https://openalex.org/W2928941594","https://openalex.org/W2962760690","https://openalex.org/W2962893195","https://openalex.org/W2971840980","https://openalex.org/W2972347614","https://openalex.org/W3008434450","https://openalex.org/W6605147687","https://openalex.org/W6638749077","https://openalex.org/W6746041127","https://openalex.org/W6759290872","https://openalex.org/W6760633627"],"related_works":["https://openalex.org/W2147866274","https://openalex.org/W2350015575","https://openalex.org/W3153459181","https://openalex.org/W2371976984","https://openalex.org/W2352160949","https://openalex.org/W2378436233","https://openalex.org/W2354361711","https://openalex.org/W2096393573","https://openalex.org/W190438618","https://openalex.org/W4385625167"],"abstract_inverted_index":{"Multilingual":[0],"Automated":[1],"Speech":[2],"Recognition":[3],"(ASR)":[4],"systems":[5],"allow":[6],"for":[7,32,73],"the":[8,33,42,134,152],"joint":[9],"training":[10],"of":[11,44,130],"data-rich":[12],"and":[13,23,47,68,136,149],"data-scarce":[14,34],"languages":[15,78,108],"in":[16,162],"a":[17,95,100,114,125,168],"single":[18],"model.":[19,171],"This":[20],"enables":[21],"data":[22],"parameter":[24],"sharing":[25],"across":[26],"languages,":[27,144],"which":[28,105],"is":[29],"especially":[30],"beneficial":[31],"languages.":[35,59],"However,":[36],"most":[37],"state-of-the-art":[38],"multilingual":[39,61,102,154,170],"models":[40,62],"require":[41],"encoding":[43],"language":[45],"information":[46],"therefore":[48],"are":[49,69,79,122],"not":[50],"as":[51],"flexible":[52],"or":[53],"scalable":[54],"when":[55],"expanding":[56],"to":[57,64,98,109,124,158],"newer":[58],"Language-independent":[60],"help":[63],"address":[65],"this":[66,91],"issue,":[67],"also":[70],"better":[71],"suited":[72],"multicultural":[74],"societies":[75],"where":[76],"several":[77],"frequently":[80],"used":[81],"together":[82],"(but":[83],"often":[84],"rendered":[85],"with":[86,141],"different":[87],"writing":[88,111],"systems).":[89],"In":[90],"paper,":[92],"we":[93],"propose":[94],"new":[96],"approach":[97],"building":[99],"language-agnostic":[101,153],"ASR":[103],"system":[104,112],"transforms":[106],"all":[107],"one":[110],"through":[113],"many-to-one":[115],"transliteration":[116],"transducer.":[117],"Thus,":[118],"similar":[119],"sounding":[120],"acoustics":[121],"mapped":[123],"single,":[126],"canonical":[127],"target":[128],"sequence":[129],"graphemes,":[131],"effectively":[132],"separating":[133],"modeling":[135],"rendering":[137],"problems.":[138],"We":[139],"show":[140],"four":[142],"Indic":[143],"namely,":[145],"Hindi,":[146],"Bengali,":[147],"Tamil":[148],"Kannada,":[150],"that":[151],"model":[155],"achieves":[156],"up":[157],"10%":[159],"relative":[160],"reduction":[161],"Word":[163],"Error":[164],"Rate":[165],"(WER)":[166],"over":[167],"language-dependent":[169]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}