{"id":"https://openalex.org/W3209976096","doi":"https://doi.org/10.1109/icassp43922.2022.9746832","title":"Pseudo-Labeling for Massively Multilingual Speech Recognition","display_name":"Pseudo-Labeling for Massively Multilingual Speech Recognition","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3209976096","doi":"https://doi.org/10.1109/icassp43922.2022.9746832","mag":"3209976096"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746832","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746832","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":"conference-paper","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/A5040757409","display_name":"Loren Lugosch","orcid":"https://orcid.org/0000-0002-5024-8667"},"institutions":[{"id":"https://openalex.org/I4210155582","display_name":"Centre Universitaire de Mila","ror":"https://ror.org/05s3cw058","country_code":"DZ","type":"education","lineage":["https://openalex.org/I4210155582"]},{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA","DZ"],"is_corresponding":false,"raw_author_name":"Loren Lugosch","raw_affiliation_strings":["McGill University/ Mila"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McGill University/ Mila","institution_ids":["https://openalex.org/I4210155582","https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106542588","display_name":"Tatiana Likhomanenko","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Tatiana Likhomanenko","raw_affiliation_strings":["Facebook AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041907084","display_name":"Gabriel Synnaeve","orcid":"https://orcid.org/0000-0003-1715-3356"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Gabriel Synnaeve","raw_affiliation_strings":["Facebook AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053915453","display_name":"Ronan Collobert","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ronan Collobert","raw_affiliation_strings":["Facebook AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5304,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.90985681,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7687","last_page":"7691"},"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/T10860","display_name":"Speech 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/T11309","display_name":"Music 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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8425214290618896},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5583582520484924},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5512307286262512},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5059723258018494},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4985651969909668}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8425214290618896},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5583582520484924},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5512307286262512},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5059723258018494},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4985651969909668}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746832","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746832","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":[{"id":"https://metadata.un.org/sdg/4","score":0.8299999833106995,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W47568227","https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W2127141656","https://openalex.org/W2327501763","https://openalex.org/W2750499125","https://openalex.org/W2769639994","https://openalex.org/W2891816510","https://openalex.org/W2894835365","https://openalex.org/W2900819823","https://openalex.org/W2936774411","https://openalex.org/W2951816288","https://openalex.org/W2962760690","https://openalex.org/W2963431393","https://openalex.org/W2963925437","https://openalex.org/W2964002616","https://openalex.org/W2964309797","https://openalex.org/W2971840980","https://openalex.org/W2991213871","https://openalex.org/W3015522062","https://openalex.org/W3026041220","https://openalex.org/W3030437843","https://openalex.org/W3036601975","https://openalex.org/W3037057938","https://openalex.org/W3093579165","https://openalex.org/W3096032230","https://openalex.org/W3096215352","https://openalex.org/W3096338464","https://openalex.org/W3099782249","https://openalex.org/W3119308075","https://openalex.org/W3149629662","https://openalex.org/W3160525311","https://openalex.org/W3173814445","https://openalex.org/W3197223534","https://openalex.org/W3198098585","https://openalex.org/W3198270883","https://openalex.org/W3198429080","https://openalex.org/W3204397973","https://openalex.org/W3214457259","https://openalex.org/W4221149170","https://openalex.org/W4287124724","https://openalex.org/W6601939441","https://openalex.org/W6623517193","https://openalex.org/W6638749077","https://openalex.org/W6756000814","https://openalex.org/W6770506093","https://openalex.org/W6771467084","https://openalex.org/W6779919476","https://openalex.org/W6780218876","https://openalex.org/W6784614252","https://openalex.org/W6797264745","https://openalex.org/W6809739816"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Semi-supervised":[0],"learning":[1,50],"through":[2],"pseudo-labeling":[3,19,32],"has":[4],"become":[5],"a":[6,30,42,52,62,92],"staple":[7],"of":[8],"state-of-the-art":[9],"monolingual":[10],"speech":[11,23],"recognition":[12,24],"systems.":[13],"In":[14],"this":[15],"work,":[16],"we":[17],"extend":[18],"to":[20,104],"massively":[21],"multilingual":[22,44],"with":[25,38,48,94],"60":[26],"languages.":[27],"We":[28],"propose":[29],"simple":[31],"recipe":[33,89],"that":[34,58,87,100],"works":[35],"well":[36,103],"even":[37],"low-resource":[39],"languages:":[40],"train":[41,61],"supervised":[43],"model,":[45],"fine-tune":[46],"it":[47],"semi-supervised":[49],"on":[51,77],"target":[53],"language,":[54,59],"generate":[55],"pseudo-labels":[56,66],"for":[57,67,97],"and":[60,82],"final":[63],"model":[64,93],"using":[65],"all":[68],"languages,":[69],"either":[70],"from":[71],"scratch":[72],"or":[73],"by":[74],"fine-tuning.":[75],"Experiments":[76],"the":[78],"labeled":[79],"Common":[80],"Voice":[81],"unlabeled":[83],"VoxPopuli":[84],"datasets":[85],"show":[86],"our":[88],"can":[90],"yield":[91],"better":[95],"performance":[96],"many":[98],"languages":[99],"also":[101],"transfers":[102],"LibriSpeech.":[105]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}