{"id":"https://openalex.org/W3156323585","doi":"https://doi.org/10.1109/icassp39728.2021.9414379","title":"Mixture of Informed Experts for Multilingual Speech Recognition","display_name":"Mixture of Informed Experts for Multilingual Speech Recognition","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3156323585","doi":"https://doi.org/10.1109/icassp39728.2021.9414379","mag":"3156323585"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414379","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414379","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5016601028","display_name":"Neeraj Gaur","orcid":"https://orcid.org/0000-0002-5926-9966"},"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":"Neeraj Gaur","raw_affiliation_strings":["Google Inc"],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068291585","display_name":"Brian Farris","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 Farris","raw_affiliation_strings":["Google Inc"],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037705635","display_name":"Parisa Haghani","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":"Parisa Haghani","raw_affiliation_strings":["Google Inc"],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004422622","display_name":"Isabel Leal","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":"Isabel Leal","raw_affiliation_strings":["Google Inc"],"affiliations":[{"raw_affiliation_string":"Google Inc","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 J. Moreno","raw_affiliation_strings":["Google Inc"],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113960780","display_name":"Manasa Prasad","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":"Manasa Prasad","raw_affiliation_strings":["Google Inc"],"affiliations":[{"raw_affiliation_string":"Google Inc","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":["Google Inc"],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061165176","display_name":"Yun Zhu","orcid":"https://orcid.org/0000-0001-6734-8202"},"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":"Yun Zhu","raw_affiliation_strings":["Google Inc"],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5016601028"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":3.1274,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.92853316,"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":"6234","last_page":"6238"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9990000128746033,"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":0.9984999895095825,"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":0.8138254880905151},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7449095249176025},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.7114884853363037},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.6588922142982483},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6424460411071777},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.609449028968811},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5390694737434387},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4755299389362335},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3763432800769806},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.23139077425003052}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8138254880905151},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7449095249176025},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.7114884853363037},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6588922142982483},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6424460411071777},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.609449028968811},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5390694737434387},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4755299389362335},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3763432800769806},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.23139077425003052},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414379","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414379","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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","id":"https://metadata.un.org/sdg/4","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W1994606281","https://openalex.org/W2025198378","https://openalex.org/W2150884987","https://openalex.org/W2617258110","https://openalex.org/W2936774411","https://openalex.org/W2952339051","https://openalex.org/W2962704885","https://openalex.org/W2962760690","https://openalex.org/W2962893195","https://openalex.org/W2971840980","https://openalex.org/W2972539100","https://openalex.org/W3008434450","https://openalex.org/W3096032230","https://openalex.org/W3096091920","https://openalex.org/W3096122506","https://openalex.org/W3096215352","https://openalex.org/W3097338456","https://openalex.org/W3144493448","https://openalex.org/W4293718192","https://openalex.org/W6638749077","https://openalex.org/W6732520560"],"related_works":["https://openalex.org/W4319453497","https://openalex.org/W1989705153","https://openalex.org/W2166245164","https://openalex.org/W4205820553","https://openalex.org/W3037322406","https://openalex.org/W2395078704","https://openalex.org/W2359001871","https://openalex.org/W3117847293","https://openalex.org/W4212780371","https://openalex.org/W3120762062"],"abstract_inverted_index":{"When":[0],"trained":[1],"on":[2,83],"related":[3],"or":[4,28,105],"low-resource":[5],"languages,":[6,113],"multilingual":[7,128],"speech":[8],"recognition":[9],"models":[10,18,109],"often":[11],"outperform":[12],"their":[13],"monolingual":[14,108],"counterparts.":[15],"However,":[16],"these":[17,77],"can":[19],"suffer":[20],"from":[21,73],"loss":[22],"in":[23,43,50,76],"performance":[24],"for":[25,110,130],"high":[26],"resource":[27],"unrelated":[29],"languages.":[30],"We":[31,54,80],"investigate":[32],"the":[33,44,97,107,126],"use":[34],"of":[35,59,93,99,116],"a":[36,51,56,84],"mixture-of-experts":[37],"approach":[38],"to":[39,46,66,95,135],"assign":[40],"per-language":[41],"parameters":[42],"model":[45,103,123,129],"increase":[47],"network":[48],"capacity":[49],"structured":[52],"fashion.":[53],"introduce":[55],"novel":[57],"variant":[58],"this":[60],"approach,":[61],"\u2018informed":[62],"experts\u2019,":[63],"which":[64],"attempts":[65],"tackle":[67],"inter-task":[68],"conflicts":[69],"by":[70,133],"eliminating":[71],"gradients":[72],"other":[74],"tasks":[75],"task-specific":[78],"parameters.":[79],"conduct":[81],"experiments":[82],"real-world":[85],"task":[86],"with":[87,114],"English,":[88],"French":[89],"and":[90],"four":[91],"dialects":[92],"Arabic":[94],"show":[96],"effectiveness":[98],"our":[100],"approach.":[101],"Our":[102,122],"matches":[104],"outperforms":[106,125],"almost":[111],"all":[112,131],"gains":[115],"as":[117,119],"much":[118],"31%":[120],"relative.":[121,137],"also":[124],"baseline":[127],"languages":[132],"up":[134],"9%":[136]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}