{"id":"https://openalex.org/W3160525311","doi":"https://doi.org/10.1109/icassp39728.2021.9414641","title":"Self-Training and Pre-Training are Complementary for Speech Recognition","display_name":"Self-Training and Pre-Training are Complementary for Speech Recognition","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160525311","doi":"https://doi.org/10.1109/icassp39728.2021.9414641","mag":"3160525311"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414641","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/A5102647000","display_name":"Qiantong Xu","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":true,"raw_author_name":"Qiantong Xu","raw_affiliation_strings":["Facebook AI Research"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031979802","display_name":"Alexei Baevski","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":"Alexei Baevski","raw_affiliation_strings":["Facebook AI Research"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]},{"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"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027043104","display_name":"Paden Tomasello","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":"Paden Tomasello","raw_affiliation_strings":["Facebook AI Research"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068394403","display_name":"Alexis Conneau","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":"Alexis Conneau","raw_affiliation_strings":["Facebook AI Research"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","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"],"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"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083212922","display_name":"Michael Auli","orcid":"https://orcid.org/0000-0001-5974-4459"},"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":"Michael Auli","raw_affiliation_strings":["Facebook AI Research"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5102647000"],"corresponding_institution_ids":["https://openalex.org/I2252078561"],"apc_list":null,"apc_paid":null,"fwci":15.0925,"has_fulltext":false,"cited_by_count":120,"citation_normalized_percentile":{"value":0.99228898,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3030","last_page":"3034"},"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/T10181","display_name":"Natural Language Processing Techniques","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/training","display_name":"Training (meteorology)","score":0.7738184928894043},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.7445313930511475},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6489979028701782},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6369542479515076},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.5706954002380371},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5697603225708008},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5206448435783386},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5137863755226135},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4393070936203003},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.4345241189002991},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3253442943096161},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15820080041885376}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.7738184928894043},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.7445313930511475},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6489979028701782},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6369542479515076},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.5706954002380371},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5697603225708008},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5206448435783386},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5137863755226135},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4393070936203003},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4345241189002991},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3253442943096161},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15820080041885376},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414641","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":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2101210369","https://openalex.org/W2111316763","https://openalex.org/W2124509324","https://openalex.org/W2124634352","https://openalex.org/W2127141656","https://openalex.org/W2547875792","https://openalex.org/W2811079561","https://openalex.org/W2842511635","https://openalex.org/W2896457183","https://openalex.org/W2933138175","https://openalex.org/W2936774411","https://openalex.org/W2953190524","https://openalex.org/W2962907457","https://openalex.org/W2962942158","https://openalex.org/W2963250244","https://openalex.org/W2963341956","https://openalex.org/W2963400424","https://openalex.org/W2963403868","https://openalex.org/W2963631907","https://openalex.org/W2972889948","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2979476256","https://openalex.org/W2981991061","https://openalex.org/W2988736778","https://openalex.org/W2991213871","https://openalex.org/W2995181338","https://openalex.org/W2996383576","https://openalex.org/W2998532468","https://openalex.org/W3003875258","https://openalex.org/W3015522062","https://openalex.org/W3016181583","https://openalex.org/W3021469861","https://openalex.org/W3025165719","https://openalex.org/W3026041220","https://openalex.org/W3027083471","https://openalex.org/W3036601975","https://openalex.org/W3090196146","https://openalex.org/W3095173472","https://openalex.org/W3096338464","https://openalex.org/W3097777922","https://openalex.org/W3099782249","https://openalex.org/W3102342027","https://openalex.org/W3168921237","https://openalex.org/W4297808394","https://openalex.org/W4385245566","https://openalex.org/W6678794661","https://openalex.org/W6729448088","https://openalex.org/W6739901393","https://openalex.org/W6753018729","https://openalex.org/W6754905691","https://openalex.org/W6755207826","https://openalex.org/W6755638308","https://openalex.org/W6760911985","https://openalex.org/W6769196770","https://openalex.org/W6769238691","https://openalex.org/W6770506093","https://openalex.org/W6770514103","https://openalex.org/W6772883055","https://openalex.org/W6780218876","https://openalex.org/W6783934668"],"related_works":["https://openalex.org/W2944691285","https://openalex.org/W2130553454","https://openalex.org/W3022007134","https://openalex.org/W4317548404","https://openalex.org/W2146197305","https://openalex.org/W2087783760","https://openalex.org/W1509924131","https://openalex.org/W3096273170","https://openalex.org/W3045896262","https://openalex.org/W4287241967"],"abstract_inverted_index":{"Self-training":[0],"and":[1,41,84],"unsupervised":[2],"pre-training":[3,42],"have":[4],"emerged":[5],"as":[6,64,66],"effective":[7],"approaches":[8],"to":[9],"improve":[10],"speech":[11],"recognition":[12],"systems":[13,95],"using":[14],"unlabeled":[15,70],"data.":[16],"However,":[17],"it":[18],"is":[19],"not":[20],"clear":[21],"whether":[22],"they":[23,29],"learn":[24],"similar":[25],"patterns":[26],"or":[27],"if":[28],"can":[30],"be":[31],"effectively":[32],"combined.":[33],"In":[34],"this":[35],"paper,":[36],"we":[37],"show":[38],"that":[39],"pseudo-labeling":[40],"with":[43],"wav2vec":[44],"2.0":[45],"are":[46],"complementary":[47],"in":[48],"a":[49,104],"variety":[50],"of":[51,59,69,79,88,100,112,116],"labeled":[52,60,101,110],"data":[53,61,71,102,111],"setups.":[54],"Using":[55],"just":[56],"10":[57],"minutes":[58],"from":[62,72],"Libri-light":[63],"well":[65],"53k":[67],"hours":[68,99],"LibriVox":[73],"achieves":[74,114],"word":[75],"error":[76],"rates":[77],"(WER)":[78],"2.8%/4.8%":[80],"on":[81,97,108],"the":[82,92],"clean":[83],"other":[85],"test":[86],"sets":[87],"Librispeech":[89,113],"\u2013":[90],"rivaling":[91],"best":[93],"published":[94],"trained":[96],"960":[98],"only":[103],"year":[105],"ago.":[106],"Training":[107],"all":[109],"WERs":[115],"1.5%/3.1%.":[117]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":37},{"year":2022,"cited_by_count":37},{"year":2021,"cited_by_count":23}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}