{"id":"https://openalex.org/W3096338464","doi":"https://doi.org/10.21437/interspeech.2020-1800","title":"Iterative Pseudo-Labeling for Speech Recognition","display_name":"Iterative Pseudo-Labeling for Speech Recognition","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096338464","doi":"https://doi.org/10.21437/interspeech.2020-1800","mag":"3096338464"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1800","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1800","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5102647000","display_name":"Qiantong Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiantong Xu","raw_affiliation_strings":["Facebook AI Research, Menlo Park & New York, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research, Menlo Park & New York, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106542588","display_name":"Tatiana Likhomanenko","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tatiana Likhomanenko","raw_affiliation_strings":["Facebook AI Research, Menlo Park & New York, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research, Menlo Park & New York, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027275703","display_name":"Jacob Kahn","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob Kahn","raw_affiliation_strings":["Facebook AI Research, Menlo Park & New York, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research, Menlo Park & New York, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087325198","display_name":"Awni Hannun","orcid":"https://orcid.org/0000-0003-3080-4002"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Awni Hannun","raw_affiliation_strings":["Facebook AI Research, Menlo Park & New York, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research, Menlo Park & New York, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"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/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gabriel Synnaeve","raw_affiliation_strings":["Facebook AI Research, Menlo Park & New York, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research, Menlo Park & New York, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053915453","display_name":"Ronan Collobert","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ronan Collobert","raw_affiliation_strings":["Facebook AI Research, Menlo Park & New York, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research, Menlo Park & New York, USA","institution_ids":["https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210114444"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":100,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1006","last_page":"1010"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9927999973297119,"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":0.6530277729034424},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.640632152557373},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37388813495635986},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3270455002784729}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6530277729034424},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.640632152557373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37388813495635986},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3270455002784729}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-1800","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1800","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W82886505","https://openalex.org/W1494198834","https://openalex.org/W1975113979","https://openalex.org/W2033256038","https://openalex.org/W2046932483","https://openalex.org/W2095705004","https://openalex.org/W2134800885","https://openalex.org/W2139453310","https://openalex.org/W2146502635","https://openalex.org/W2171761326","https://openalex.org/W2404463488","https://openalex.org/W2904818793","https://openalex.org/W2936774411","https://openalex.org/W2941814890","https://openalex.org/W2963250244","https://openalex.org/W2963400424","https://openalex.org/W2972818416","https://openalex.org/W2975381464","https://openalex.org/W2976223659","https://openalex.org/W2981857663","https://openalex.org/W2988736778","https://openalex.org/W2991213871","https://openalex.org/W2995181338","https://openalex.org/W2998532468","https://openalex.org/W3006827623","https://openalex.org/W3015265920","https://openalex.org/W3015522062","https://openalex.org/W3026041220","https://openalex.org/W3035160371","https://openalex.org/W3036601975","https://openalex.org/W3095350795","https://openalex.org/W4286784498","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2789919619","https://openalex.org/W2293457016","https://openalex.org/W3169305685","https://openalex.org/W2351428524","https://openalex.org/W2368779261","https://openalex.org/W1551406738","https://openalex.org/W2610387714","https://openalex.org/W2369308426","https://openalex.org/W1569841287","https://openalex.org/W1512718085"],"abstract_inverted_index":{"Pseudo-labeling":[0],"has":[1],"recently":[2],"shown":[3],"promise":[4],"in":[5,83,128],"end-to-end":[6],"automatic":[7],"speech":[8],"recognition":[9],"(ASR).We":[10],"study":[11,53,90],"Iterative":[12],"Pseudo-Labeling":[13],"(IPL),":[14],"a":[15,48,61,110],"semi-supervised":[16,130],"algorithm":[17],"which":[18,116],"efficiently":[19],"performs":[20],"multiple":[21],"iterations":[22],"of":[23,50,57,71,93],"pseudo-labeling":[24],"on":[25,78,97],"unlabeled":[26,51],"data":[27,46,65],"as":[28],"the":[29,54,69,79,91,121],"acoustic":[30],"model":[31,39,63],"evolves.In":[32],"particular,":[33],"IPL":[34,72,102],"fine":[35],"tunes":[36],"an":[37],"existing":[38],"at":[40],"each":[41],"iteration":[42],"using":[43],"both":[44,84],"labeled":[45],"and":[47,64,86],"subset":[49],"data.We":[52],"main":[55],"components":[56],"IPL:":[58],"decoding":[59],"with":[60,120],"language":[62,94],"augmentation.We":[66],"then":[67],"demonstrate":[68],"effectiveness":[70],"by":[73],"achieving":[74],"state-of-the-art":[75],"word-error":[76],"rate":[77],"LIBRISPEECH":[80,122],"test":[81],"sets":[82],"standard":[85],"low-resource":[87],"setting.We":[88],"also":[89],"effect":[92],"models":[95],"trained":[96],"different":[98],"corpora":[99],"to":[100,125],"show":[101],"can":[103],"effectively":[104],"utilize":[105],"additional":[106],"text.Finally,":[107],"we":[108],"release":[109],"new":[111],"large":[112],"in-domain":[113],"text":[114],"corpus":[115],"does":[117],"not":[118],"overlap":[119],"training":[123],"transcriptions":[124],"foster":[126],"research":[127],"low-resource,":[129],"ASR.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":29},{"year":2021,"cited_by_count":23},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}