{"id":"https://openalex.org/W3144173820","doi":"https://doi.org/10.21437/interspeech.2021-236","title":"Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training","display_name":"Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3144173820","doi":"https://doi.org/10.21437/interspeech.2021-236","mag":"3144173820"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-236","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-236","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.01027","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051950818","display_name":"Wei-Ning Hsu","orcid":"https://orcid.org/0000-0001-5546-5217"},"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":"Wei-Ning Hsu","raw_affiliation_strings":["Meta (Israel), Tel Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"Meta (Israel), Tel Aviv, Israel","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047764126","display_name":"Anuroop Sriram","orcid":"https://orcid.org/0000-0001-6295-7535"},"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":"Anuroop Sriram","raw_affiliation_strings":["Meta (Israel), Tel Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"Meta (Israel), Tel Aviv, Israel","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":["Meta (Israel), Tel Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"Meta (Israel), Tel Aviv, Israel","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":["Meta (Israel), Tel Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"Meta (Israel), Tel Aviv, Israel","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","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":false,"raw_author_name":"Qiantong Xu","raw_affiliation_strings":["Meta (Israel), Tel Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"Meta (Israel), Tel Aviv, Israel","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028944337","display_name":"Vineel Pratap","orcid":"https://orcid.org/0000-0003-3333-910X"},"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":"Vineel Pratap","raw_affiliation_strings":["Meta (Israel), Tel Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"Meta (Israel), Tel Aviv, Israel","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027275703","display_name":"Jacob Kahn","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":"Jacob Kahn","raw_affiliation_strings":["Meta (Israel), Tel Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"Meta (Israel), Tel Aviv, Israel","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084509956","display_name":"Ann Lee","orcid":"https://orcid.org/0000-0003-4300-9032"},"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":"Ann Lee","raw_affiliation_strings":["Meta (Israel), Tel Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"Meta (Israel), Tel Aviv, Israel","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":["Meta (Israel), Tel Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"Meta (Israel), Tel Aviv, Israel","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":["Meta (Israel), Tel Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"Meta (Israel), Tel Aviv, Israel","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":["Meta (Israel), Tel Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"Meta (Israel), Tel Aviv, Israel","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5051950818"],"corresponding_institution_ids":["https://openalex.org/I2252078561"],"apc_list":null,"apc_paid":null,"fwci":2.5197,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.90901923,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"721","last_page":"725"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9972000122070312,"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/T10028","display_name":"Topic Modeling","score":0.9950000047683716,"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/domain","display_name":"Domain (mathematical analysis)","score":0.7781035900115967},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7732915878295898},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.7632158994674683},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6714022159576416},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.6379202604293823},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.6041635870933533},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5840557217597961},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5815184712409973},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5435582995414734},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4755023419857025},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44563060998916626},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38633492588996887},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3208792805671692},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10302028059959412}],"concepts":[{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.7781035900115967},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7732915878295898},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.7632158994674683},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6714022159576416},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.6379202604293823},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.6041635870933533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5840557217597961},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5815184712409973},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5435582995414734},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4755023419857025},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44563060998916626},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38633492588996887},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3208792805671692},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10302028059959412},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2021-236","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-236","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"},{"id":"pmh:oai:arXiv.org:2104.01027","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.01027","pdf_url":"https://arxiv.org/pdf/2104.01027","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3144173820","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2104.01027.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2104.01027","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.01027","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.01027","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.01027","pdf_url":"https://arxiv.org/pdf/2104.01027","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3144173820.pdf","grobid_xml":"https://content.openalex.org/works/W3144173820.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1571339265","https://openalex.org/W1992272902","https://openalex.org/W2062164080","https://openalex.org/W2124509324","https://openalex.org/W2127141656","https://openalex.org/W2134800885","https://openalex.org/W2547875792","https://openalex.org/W2617258110","https://openalex.org/W2758785877","https://openalex.org/W2842511635","https://openalex.org/W2896457183","https://openalex.org/W2953190524","https://openalex.org/W2962946733","https://openalex.org/W2963403868","https://openalex.org/W2964245029","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2973157397","https://openalex.org/W2988736778","https://openalex.org/W2995181338","https://openalex.org/W2995929068","https://openalex.org/W2996159613","https://openalex.org/W2996383576","https://openalex.org/W3005511757","https://openalex.org/W3015349902","https://openalex.org/W3015726069","https://openalex.org/W3025165719","https://openalex.org/W3037057938","https://openalex.org/W3093502935","https://openalex.org/W3099782249","https://openalex.org/W3101648800","https://openalex.org/W3102342027","https://openalex.org/W3119308075","https://openalex.org/W3163464943"],"related_works":["https://openalex.org/W3198771897","https://openalex.org/W3099782249","https://openalex.org/W1494198834","https://openalex.org/W2995181338","https://openalex.org/W2963341956","https://openalex.org/W2842511635","https://openalex.org/W3093579165","https://openalex.org/W3037057938","https://openalex.org/W2996383576","https://openalex.org/W2973049979","https://openalex.org/W2963403868","https://openalex.org/W2000987725","https://openalex.org/W3011351697","https://openalex.org/W3176720610","https://openalex.org/W3149645030","https://openalex.org/W3159671172","https://openalex.org/W1522753273","https://openalex.org/W3165666670","https://openalex.org/W2982223350","https://openalex.org/W2127141656"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1],"of":[2,32,48,59,93],"speech":[3],"representations":[4],"has":[5,123],"been":[6],"a":[7,18,91,96],"very":[8],"active":[9],"research":[10],"area":[11],"but":[12],"most":[13],"work":[14],"is":[15,129],"focused":[16],"on":[17,104,114,146,152],"single":[19],"domain":[20,47,58,81,136],"such":[21],"as":[22],"read":[23],"audio":[24],"books":[25],"for":[26,52,63],"which":[27,65],"there":[28],"exist":[29],"large":[30,87],"quantities":[31],"labeled":[33,61,118,139],"and":[34,116,159],"unlabeled":[35,50,105,134],"data.":[36,140],"In":[37],"this":[38],"paper,":[39],"we":[40,100,142],"explore":[41],"more":[42],"general":[43],"setups":[44],"where":[45],"the":[46,49,57,60,71,109],"data":[51,54,62,73,82,107,119,137],"pre-training":[53,84,103,145],"differs":[55],"from":[56,70],"fine-tuning,":[64],"in":[66],"turn":[67],"may":[68],"differ":[69],"test":[72],"domain.":[74],"Our":[75],"experiments":[76],"show":[77,101],"that":[78,102,144],"using":[79],"target":[80,135],"during":[83,156],"leads":[85],"to":[86,132],"performance":[88,151],"improvements":[89],"across":[90],"variety":[92],"setups.":[94],"On":[95],"large-scale":[97],"competitive":[98],"setup,":[99],"in-domain":[106,115],"reduces":[108],"gap":[110],"between":[111],"models":[112,160],"trained":[113],"out-of-domain":[117],"by":[120],"66%-73%.":[121],"This":[122],"obvious":[124],"practical":[125],"implications":[126],"since":[127],"it":[128],"much":[130],"easier":[131],"obtain":[133],"than":[138],"Moreover,":[141],"find":[143],"multiple":[147],"domains":[148,153],"improves":[149],"generalization":[150],"not":[154],"seen":[155],"training.":[157],"Code":[158],"will":[161],"be":[162],"made":[163],"available":[164],"at":[165],"https://github.com/pytorch/fairseq.":[166]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":7}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
