{"id":"https://openalex.org/W3178647810","doi":"https://doi.org/10.1109/icassp43922.2022.9747905","title":"A Configurable Multilingual Model is All You Need to Recognize All Languages","display_name":"A Configurable Multilingual Model is All You Need to Recognize All Languages","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3178647810","doi":"https://doi.org/10.1109/icassp43922.2022.9747905","mag":"3178647810"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747905","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747905","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5106557565","display_name":"Long Zhou","orcid":"https://orcid.org/0009-0006-1919-4943"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Long Zhou","raw_affiliation_strings":["Microsoft Research Asia"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365056","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-5206-8600"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Microsoft Speech and Language Group"],"affiliations":[{"raw_affiliation_string":"Microsoft Speech and Language Group","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090360853","display_name":"Eric Sun","orcid":"https://orcid.org/0000-0001-8805-9864"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Sun","raw_affiliation_strings":["Microsoft Speech and Language Group"],"affiliations":[{"raw_affiliation_string":"Microsoft Speech and Language Group","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101635405","display_name":"Shujie Liu","orcid":"https://orcid.org/0009-0008-0785-8882"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shujie Liu","raw_affiliation_strings":["Microsoft Research Asia"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5106557565"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":2.5051,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.90910055,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6422","last_page":"6426"},"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/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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":0.9993000030517578,"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":0.8709307312965393},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6031981706619263},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5746621489524841},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5445578098297119},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5317292213439941},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4278614819049835},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.42142626643180847},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.30635276436805725},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15223297476768494}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8709307312965393},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6031981706619263},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5746621489524841},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5445578098297119},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5317292213439941},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4278614819049835},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.42142626643180847},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.30635276436805725},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15223297476768494},{"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/icassp43922.2022.9747905","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747905","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W1978660892","https://openalex.org/W1982774639","https://openalex.org/W1994606281","https://openalex.org/W2025198378","https://openalex.org/W2127141656","https://openalex.org/W2160815625","https://openalex.org/W2327501763","https://openalex.org/W2622203030","https://openalex.org/W2786835190","https://openalex.org/W2908510526","https://openalex.org/W2939069254","https://openalex.org/W2950541952","https://openalex.org/W2962704885","https://openalex.org/W2962824709","https://openalex.org/W2962893195","https://openalex.org/W2963403868","https://openalex.org/W2963523217","https://openalex.org/W2964309797","https://openalex.org/W2971840980","https://openalex.org/W2982413405","https://openalex.org/W3008434450","https://openalex.org/W3015194534","https://openalex.org/W3016010032","https://openalex.org/W3022526310","https://openalex.org/W3036313961","https://openalex.org/W3094667432","https://openalex.org/W3095311338","https://openalex.org/W3096032230","https://openalex.org/W3137976833","https://openalex.org/W3146505093","https://openalex.org/W3156323585","https://openalex.org/W3157697407","https://openalex.org/W3161873870","https://openalex.org/W3163865502","https://openalex.org/W3211278025","https://openalex.org/W4210463634","https://openalex.org/W4288088457","https://openalex.org/W4385245566","https://openalex.org/W6638749077","https://openalex.org/W6739901393","https://openalex.org/W6757817989","https://openalex.org/W6769806307"],"related_works":["https://openalex.org/W1569283511","https://openalex.org/W2169518243","https://openalex.org/W4236193183","https://openalex.org/W2053866214","https://openalex.org/W2607505004","https://openalex.org/W2231795205","https://openalex.org/W2523632547","https://openalex.org/W2143882141","https://openalex.org/W2944691285","https://openalex.org/W4226278401"],"abstract_inverted_index":{"Multilingual":[0],"automatic":[1],"speech":[2],"recognition":[3,45],"models":[4,115],"have":[5],"shown":[6],"great":[7],"promise":[8],"in":[9],"recent":[10],"years":[11],"because":[12],"of":[13,46,151,157],"the":[14,44,47,73,78,81,130,145,169,174,188],"simple":[15],"model":[16,28,67,83,102,177],"training":[17],"and":[18,163,181],"deployment":[19],"process.":[20],"Conventional":[21],"methods":[22],"either":[23],"train":[24],"a":[25,36,52,98,126,134],"universal":[26,127,175],"multilingual":[27,53,66,82,101,161,176],"without":[29,68],"taking":[30],"any":[31,141,149],"language":[32,38,74],"information":[33,75],"or":[34,193],"with":[35,84,125,154,165],"1-hot":[37,85],"ID":[39],"(LID)":[40],"vector":[41],"to":[42,58,140],"guide":[43],"target":[48],"language.":[49,92],"In":[50,93],"practice,":[51],"user":[54,79,142,189],"can":[55,63,87,110,137,147],"be":[56,111,138],"prompted":[57],"preselect":[59],"several":[60],"languages":[61],"he/she":[62],"speak.":[64],"The":[65],"LID":[69,86],"cannot":[70],"well":[71],"utilize":[72],"set":[76],"by":[77,120,178],"while":[80],"only":[88,107],"handle":[89],"one":[90],"pre-selected":[91],"this":[94],"paper,":[95],"we":[96],"propose":[97],"novel":[99],"configurable":[100],"(CMM)":[103],"which":[104],"is":[105],"trained":[106,131],"once":[108],"but":[109],"configured":[112],"as":[113],"different":[114],"based":[116],"on":[117],"users\u2019":[118],"choices":[119],"extracting":[121],"language-specific":[122],"modules":[123],"together":[124],"module":[128],"from":[129,173],"CMM.":[132],"Particularly,":[133],"single":[135],"CMM":[136,171],"deployed":[139],"scenario":[143],"where":[144],"users":[146],"pre-select":[148],"combination":[150],"languages.":[152],"Trained":[153],"75K":[155],"hours":[156],"transcribed":[158],"anonymized":[159],"Microsoft":[160],"data":[162],"evaluated":[164],"10-language":[166],"test":[167],"sets,":[168],"proposed":[170],"improves":[172],"26.0%,":[179],"16.9%,":[180],"10.4%":[182],"relative":[183],"word":[184],"error":[185],"reduction":[186],"when":[187],"selects":[190],"1,":[191],"2,":[192],"3":[194],"languages,":[195],"respectively.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}