{"id":"https://openalex.org/W3097787369","doi":"https://doi.org/10.21437/interspeech.2020-3094","title":"Self-Supervised Representations Improve End-to-End Speech Translation","display_name":"Self-Supervised Representations Improve End-to-End Speech Translation","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3097787369","doi":"https://doi.org/10.21437/interspeech.2020-3094","mag":"3097787369"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-3094","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-3094","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/A5084629623","display_name":"Anne Wu","orcid":"https://orcid.org/0000-0003-2436-8486"},"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":"Anne Wu","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/A5087491225","display_name":"Changhan Wang","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":"Changhan Wang","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/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":false,"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":"last","author":{"id":"https://openalex.org/A5112542984","display_name":"Jiatao Gu","orcid":"https://orcid.org/0000-0003-3578-2711"},"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":"Jiatao Gu","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":4,"corresponding_author_ids":["https://openalex.org/A5084629623"],"corresponding_institution_ids":["https://openalex.org/I4210114444"],"apc_list":null,"apc_paid":null,"fwci":4.5529,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.95561665,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1491","last_page":"1495"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.998199999332428,"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":0.998199999332428,"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":0.9980000257492065,"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":0.9966999888420105,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.8114423751831055},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7011620402336121},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.6353843808174133},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5388588309288025},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5045226812362671},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4149465560913086},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40821364521980286},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4032030701637268},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.3254659175872803}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8114423751831055},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7011620402336121},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.6353843808174133},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5388588309288025},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5045226812362671},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4149465560913086},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40821364521980286},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4032030701637268},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.3254659175872803},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-3094","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-3094","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.75}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2466918907","https://openalex.org/W2605131327","https://openalex.org/W2896457183","https://openalex.org/W2901607128","https://openalex.org/W2933138175","https://openalex.org/W2936774411","https://openalex.org/W2949328740","https://openalex.org/W2962739339","https://openalex.org/W2963250244","https://openalex.org/W2963532001","https://openalex.org/W2964172053","https://openalex.org/W2970119519","https://openalex.org/W2973049979","https://openalex.org/W2979476256","https://openalex.org/W2997436923","https://openalex.org/W3005680577","https://openalex.org/W3006988520","https://openalex.org/W3008549139","https://openalex.org/W3015440307","https://openalex.org/W3016181583","https://openalex.org/W3030437843","https://openalex.org/W3032433061","https://openalex.org/W3034999214","https://openalex.org/W3102342027","https://openalex.org/W3103029570","https://openalex.org/W4297808394","https://openalex.org/W4300558631"],"related_works":["https://openalex.org/W2990025607","https://openalex.org/W3045103338","https://openalex.org/W2728761353","https://openalex.org/W2883671469","https://openalex.org/W2338806053","https://openalex.org/W3007142233","https://openalex.org/W3037186962","https://openalex.org/W4385571610","https://openalex.org/W39235475","https://openalex.org/W1540615732"],"abstract_inverted_index":{"End-to-end":[0],"speech-to-text":[1],"translation":[2,46,78,97],"can":[3,19,42,55,64,93],"provide":[4],"a":[5,82,106],"simpler":[6],"and":[7,23,61,99],"smaller":[8],"system":[9],"but":[10],"is":[11],"facing":[12],"the":[13,44,96],"challenge":[14],"of":[15,108],"data":[16,22],"scarcity.Pre-training":[17],"methods":[18,71],"leverage":[20],"unlabeled":[21],"have":[24],"been":[25],"shown":[26],"to":[27,58,103,105],"be":[28,65],"effective":[29],"on":[30],"data-scarce":[31],"settings.In":[32],"this":[33],"work,":[34],"we":[35],"explore":[36],"whether":[37,53,62],"self-supervised":[38],"pre-trained":[39,83,91],"speech":[40,45,77,85],"representations":[41],"benefit":[43],"task":[47],"in":[48],"both":[49],"highand":[50],"low-resource":[51,75],"settings,":[52],"they":[54,63],"transfer":[56,101],"well":[57],"other":[59,69],"languages,":[60],"effectively":[66],"combined":[67],"with":[68,112],"common":[70],"that":[72,89],"help":[73],"improve":[74,95],"end-to-end":[76],"such":[79],"as":[80],"using":[81],"highresource":[84],"recognition":[86],"system.We":[87],"demonstrate":[88],"selfsupervised":[90],"features":[92],"consistently":[94],"performance,":[98],"cross-lingual":[100],"allows":[102],"extend":[104],"variety":[107],"languages":[109],"without":[110],"or":[111],"little":[113],"tuning.":[114]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":5}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
