{"id":"https://openalex.org/W3198299542","doi":"https://doi.org/10.21437/interspeech.2021-1912","title":"Large-Scale Self- and Semi-Supervised Learning for Speech Translation","display_name":"Large-Scale Self- and Semi-Supervised Learning for Speech Translation","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3198299542","doi":"https://doi.org/10.21437/interspeech.2021-1912","mag":"3198299542"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1912","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5087491225","display_name":"Changhan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Changhan Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084629623","display_name":"Anne Wu","orcid":"https://orcid.org/0000-0003-2436-8486"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anne Wu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058915697","display_name":"Juan Pino","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juan Pino","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031979802","display_name":"Alexei Baevski","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexei Baevski","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083212922","display_name":"Michael Auli","orcid":"https://orcid.org/0000-0001-5974-4459"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Auli","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5068394403","display_name":"Alexis Conneau","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexis Conneau","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5087491225"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7677,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.87586881,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2242","last_page":"2246"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.995199978351593,"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":0.9751999974250793,"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":0.7565523982048035},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.583777666091919},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.5446053147315979},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5405108332633972},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.513300359249115},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5118259787559509},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5070703029632568},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.2711585760116577}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7565523982048035},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.583777666091919},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.5446053147315979},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5405108332633972},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.513300359249115},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5118259787559509},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5070703029632568},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.2711585760116577},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-1912","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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":0,"referenced_works":[],"related_works":["https://openalex.org/W4301342010","https://openalex.org/W158465921","https://openalex.org/W2261315194","https://openalex.org/W2520872336","https://openalex.org/W2339399820","https://openalex.org/W2099033952","https://openalex.org/W2338806053","https://openalex.org/W2759521758","https://openalex.org/W2890785942","https://openalex.org/W2102118225"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"improve":[4,45],"speech":[5,15,35],"translation":[6],"(ST)":[7],"through":[8],"effectively":[9],"leveraging":[10],"large":[11,33],"quantities":[12],"of":[13,50,70,78],"unlabeled":[14],"and":[16,21,28,38,80,102],"text":[17],"data":[18],"in":[19],"different":[20],"complementary":[22],"ways.":[23],"We":[24],"explore":[25],"both":[26],"pretraining":[27],"self-training":[29,79],"by":[30,53],"using":[31],"the":[32,47,51],"Libri-Light":[34],"audio":[36],"corpus":[37],"language":[39,64,84],"modeling":[40],"with":[41,82],"CommonCrawl.":[42],"Our":[43],"experiments":[44],"over":[46],"previous":[48],"state":[49],"art":[52],"2.6":[54],"BLEU":[55],"on":[56,58],"average":[57],"all":[59],"four":[60],"considered":[61],"CoVoST":[62],"2":[63],"pairs":[65],"via":[66],"a":[67,75,83],"simple":[68],"recipe":[69],"combining":[71],"wav2vec":[72],"2.0":[73],"pretraining,":[74],"single":[76],"iteration":[77],"decoding":[81],"model.":[85],"Different":[86],"to":[87],"existing":[88],"work,":[89],"our":[90],"approach":[91],"does":[92],"not":[93],"leverage":[94],"any":[95],"other":[96],"supervision":[97],"than":[98],"ST":[99],"data.":[100],"Code":[101],"models":[103],"will":[104],"be":[105],"publicly":[106],"released.":[107]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
