{"id":"https://openalex.org/W2964309797","doi":"https://doi.org/10.1109/icassp.2018.8461972","title":"Multilingual Speech Recognition with a Single End-to-End Model","display_name":"Multilingual Speech Recognition with a Single End-to-End Model","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2964309797","doi":"https://doi.org/10.1109/icassp.2018.8461972","mag":"2964309797"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461972","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461972","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5073890145","display_name":"Shubham Toshniwal","orcid":null},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shubham Toshniwal","raw_affiliation_strings":["Toyota Technological Institute at Chicago"],"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute at Chicago","institution_ids":["https://openalex.org/I160992636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"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":"Tara N. Sainath","raw_affiliation_strings":["Google Inc., U.S.A"],"affiliations":[{"raw_affiliation_string":"Google Inc., U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103273436","display_name":"Ron J. Weiss","orcid":"https://orcid.org/0000-0003-2010-4053"},"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":"Ron J. Weiss","raw_affiliation_strings":["Google Inc., U.S.A"],"affiliations":[{"raw_affiliation_string":"Google Inc., U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100677409","display_name":"Bo Li","orcid":"https://orcid.org/0000-0003-4883-7267"},"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":"Bo Li","raw_affiliation_strings":["Google Inc., U.S.A"],"affiliations":[{"raw_affiliation_string":"Google Inc., U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103874391","display_name":"Pedro J. Moreno","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":"Pedro Moreno","raw_affiliation_strings":["Google Inc., U.S.A"],"affiliations":[{"raw_affiliation_string":"Google Inc., U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058585526","display_name":"Eugene Weinstein","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":"Eugene Weinstein","raw_affiliation_strings":["Google Inc., U.S.A"],"affiliations":[{"raw_affiliation_string":"Google Inc., U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111514705","display_name":"Kanishka Rao","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":"Kanishka Rao","raw_affiliation_strings":["Google Inc., U.S.A"],"affiliations":[{"raw_affiliation_string":"Google Inc., U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5073890145"],"corresponding_institution_ids":["https://openalex.org/I160992636"],"apc_list":null,"apc_paid":null,"fwci":20.6862,"has_fulltext":false,"cited_by_count":220,"citation_normalized_percentile":{"value":0.99423324,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4904","last_page":"4908"},"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/T11309","display_name":"Music and Audio Processing","score":0.9986000061035156,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9980999827384949,"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":0.8650305867195129},{"id":"https://openalex.org/keywords/grapheme","display_name":"Grapheme","score":0.7690417766571045},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6902933120727539},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6781173944473267},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.6097985506057739},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6027103066444397},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5908153653144836},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5603191256523132},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.5598416924476624},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5594719648361206},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4854610562324524},{"id":"https://openalex.org/keywords/phonotactics","display_name":"Phonotactics","score":0.46394893527030945},{"id":"https://openalex.org/keywords/cache-language-model","display_name":"Cache language model","score":0.45987385511398315},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.43686652183532715},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.32628485560417175},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1866428554058075},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14647206664085388},{"id":"https://openalex.org/keywords/universal-networking-language","display_name":"Universal Networking Language","score":0.1346535086631775}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8650305867195129},{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.7690417766571045},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6902933120727539},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6781173944473267},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.6097985506057739},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6027103066444397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5908153653144836},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5603191256523132},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.5598416924476624},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5594719648361206},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4854610562324524},{"id":"https://openalex.org/C4768521","wikidata":"https://www.wikidata.org/wiki/Q512366","display_name":"Phonotactics","level":3,"score":0.46394893527030945},{"id":"https://openalex.org/C39608478","wikidata":"https://www.wikidata.org/wiki/Q5015979","display_name":"Cache language model","level":5,"score":0.45987385511398315},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.43686652183532715},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.32628485560417175},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1866428554058075},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14647206664085388},{"id":"https://openalex.org/C83479923","wikidata":"https://www.wikidata.org/wiki/Q2063748","display_name":"Universal Networking Language","level":4,"score":0.1346535086631775},{"id":"https://openalex.org/C129353971","wikidata":"https://www.wikidata.org/wiki/Q5156949","display_name":"Comprehension approach","level":3,"score":0.0},{"id":"https://openalex.org/C148934300","wikidata":"https://www.wikidata.org/wiki/Q40998","display_name":"Phonology","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C30080830","wikidata":"https://www.wikidata.org/wiki/Q169917","display_name":"Graphene","level":2,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461972","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461972","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W73572011","https://openalex.org/W1489125746","https://openalex.org/W1605308203","https://openalex.org/W1968147312","https://openalex.org/W1975550806","https://openalex.org/W1978660892","https://openalex.org/W1994606281","https://openalex.org/W2025198378","https://openalex.org/W2025401819","https://openalex.org/W2033436836","https://openalex.org/W2064675550","https://openalex.org/W2091746061","https://openalex.org/W2106440210","https://openalex.org/W2108677974","https://openalex.org/W2123798005","https://openalex.org/W2127982613","https://openalex.org/W2130414229","https://openalex.org/W2131774270","https://openalex.org/W2138992227","https://openalex.org/W2168231600","https://openalex.org/W2327501763","https://openalex.org/W2577366047","https://openalex.org/W2633221078","https://openalex.org/W2750499125","https://openalex.org/W2913340405","https://openalex.org/W6644703941","https://openalex.org/W6649207683","https://openalex.org/W6656670161","https://openalex.org/W6675791022","https://openalex.org/W6676315081","https://openalex.org/W6678250534","https://openalex.org/W6679081875","https://openalex.org/W6679469922","https://openalex.org/W6743440867"],"related_works":["https://openalex.org/W2766568248","https://openalex.org/W4255155614","https://openalex.org/W2394860946","https://openalex.org/W761725120","https://openalex.org/W2009170886","https://openalex.org/W2071315630","https://openalex.org/W2897427480","https://openalex.org/W1508853749","https://openalex.org/W1745277","https://openalex.org/W2787311093"],"abstract_inverted_index":{"Training":[0],"a":[1,47,55,77,85,132],"conventional":[2],"automatic":[3],"speech":[4],"recognition":[5,111],"(ASR)":[6],"system":[7],"to":[8,117,130],"support":[9],"multiple":[10],"languages":[11],"is":[12,101],"challenging":[13],"because":[14,36],"the":[15,128],"sub-word":[16],"unit,":[17],"lexicon":[18],"and":[19,42,83,149],"word":[20],"inventories":[21],"are":[22,30],"typically":[23],"language":[24,43,108,124,133],"specific.":[25],"In":[26,50],"contrast,":[27],"sequence-to-sequence":[28,57,87,119],"models":[29,120],"well":[31],"suited":[32],"for":[33],"multilingual":[34],"ASR":[35,58],"they":[37],"encapsulate":[38],"an":[39,136,145],"acoustic,":[40],"pronunciation":[41],"model":[44,59,88,129],"jointly":[45,89],"in":[46,71],"single":[48,56],"network.":[49],"this":[51,98],"work":[52],"we":[53,75,140],"present":[54],"trained":[60,121],"on":[61,90,122],"9":[62],"different":[63,153],"Indian":[64],"languages,":[65],"which":[66,100],"have":[67],"very":[68],"little":[69],"overlap":[70],"their":[72],"scripts.":[73],"Specifically,":[74],"take":[76],"union":[78],"of":[79],"language-specific":[80],"grapheme":[81],"sets":[82],"train":[84],"grapheme-based":[86],"data":[91],"from":[92],"all":[93],"languages.":[94,154],"We":[95],"find":[96],"that":[97],"model,":[99],"not":[102],"explicitly":[103],"given":[104],"any":[105],"information":[106],"about":[107],"identity,":[109],"improves":[110],"performance":[112,143],"by":[113,144],"21%":[114],"relative":[115,148],"compared":[116],"analogous":[118],"each":[123],"individually.":[125],"By":[126],"modifying":[127],"accept":[131],"identifier":[134],"as":[135],"additional":[137,146],"input":[138],"feature,":[139],"further":[141],"improve":[142],"7%":[147],"eliminate":[150],"confusion":[151],"between":[152]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":33},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":44},{"year":2020,"cited_by_count":42},{"year":2019,"cited_by_count":30},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}