{"id":"https://openalex.org/W3096490862","doi":"https://doi.org/10.21437/interspeech.2020-2938","title":"Self-Training for End-to-End Speech Translation","display_name":"Self-Training for End-to-End Speech Translation","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096490862","doi":"https://doi.org/10.21437/interspeech.2020-2938","mag":"3096490862"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2938","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2938","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":"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/A5058915697","display_name":"Juan Pino","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":true,"raw_author_name":"Juan Pino","raw_affiliation_strings":["Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","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, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054878003","display_name":"Xutai Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"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":"Xutai Ma","raw_affiliation_strings":["Facebook AI, USA","Johns Hopkins University, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001927789","display_name":"Mohammad Javad Dousti","orcid":"https://orcid.org/0000-0002-8537-2916"},"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":"Mohammad Javad Dousti","raw_affiliation_strings":["Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033437280","display_name":"Yun Tang","orcid":"https://orcid.org/0000-0002-3122-5881"},"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":"Yun Tang","raw_affiliation_strings":["Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5058915697"],"corresponding_institution_ids":["https://openalex.org/I4210114444"],"apc_list":null,"apc_paid":null,"fwci":4.2419,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.95177394,"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":"1476","last_page":"1480"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9966999888420105,"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":0.9531999826431274,"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":0.8062576055526733},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7289934754371643},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6875603199005127},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6600985527038574},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5563122630119324},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.5543199181556702},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5245647430419922},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5090296268463135},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48940959572792053},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4743539094924927},{"id":"https://openalex.org/keywords/cascade","display_name":"Cascade","score":0.465646356344223},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4598480463027954},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4333268404006958},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.42979931831359863},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07968628406524658}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8062576055526733},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7289934754371643},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6875603199005127},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6600985527038574},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5563122630119324},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.5543199181556702},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5245647430419922},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5090296268463135},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48940959572792053},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4743539094924927},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.465646356344223},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4598480463027954},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4333268404006958},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.42979931831359863},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07968628406524658},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C42360764","wikidata":"https://www.wikidata.org/wiki/Q83588","display_name":"Chemical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-2938","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2938","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2111316763","https://openalex.org/W2121879602","https://openalex.org/W2134800885","https://openalex.org/W2605131327","https://openalex.org/W2941814890","https://openalex.org/W2943152387","https://openalex.org/W2963250244","https://openalex.org/W2963532001","https://openalex.org/W2963807318","https://openalex.org/W2964161387","https://openalex.org/W2964172053","https://openalex.org/W2964213727","https://openalex.org/W2976223659","https://openalex.org/W2995181338","https://openalex.org/W3006988520","https://openalex.org/W3008125272","https://openalex.org/W3008549139","https://openalex.org/W3015522062","https://openalex.org/W3015633994","https://openalex.org/W3032433061","https://openalex.org/W4300558631","https://openalex.org/W4385245566","https://openalex.org/W4394649814"],"related_works":["https://openalex.org/W2990025607","https://openalex.org/W3045103338","https://openalex.org/W3007142233","https://openalex.org/W2338806053","https://openalex.org/W2916997151","https://openalex.org/W3037186962","https://openalex.org/W4385571610","https://openalex.org/W2949174760","https://openalex.org/W3177132412","https://openalex.org/W3198731777"],"abstract_inverted_index":{"One":[0],"of":[1,50,53,79,90],"the":[2,39,51,54,68,71,77],"main":[3],"challenges":[4],"for":[5],"end-to-end":[6,23,87],"speech":[7,24,72],"translation":[8,25],"is":[9,56,59],"data":[10],"scarcity.We":[11],"leverage":[12],"pseudo-labels":[13,55,84],"generated":[14],"from":[15],"unlabeled":[16],"audio":[17],"by":[18,81],"a":[19,34,91],"cascade":[20,92],"and":[21,29,42],"an":[22,86],"model.This":[26],"provides":[27],"8.3":[28],"5.7":[30],"BLEU":[31],"gains":[32],"over":[33],"strong":[35],"semi-supervised":[36],"baseline":[37],"on":[38,70],"MuST-C":[40],"English-French":[41],"English-German":[43],"datasets,":[44],"reaching":[45],"state-of-the":[46],"art":[47],"performance.The":[48],"effect":[49],"quality":[52],"investigated.Our":[57],"approach":[58],"shown":[60],"to":[61],"be":[62],"more":[63],"effective":[64],"than":[65],"simply":[66],"pre-training":[67],"encoder":[69],"recognition":[73],"task.Finally,":[74],"we":[75],"demonstrate":[76],"effectiveness":[78],"self-training":[80],"directly":[82],"generating":[83],"with":[85],"model":[88],"instead":[89],"model.":[93]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}