{"id":"https://openalex.org/W2939710050","doi":"https://doi.org/10.21437/interspeech.2019-1873","title":"wav2vec: Unsupervised Pre-Training for Speech Recognition","display_name":"wav2vec: Unsupervised Pre-Training for Speech Recognition","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2939710050","doi":"https://doi.org/10.21437/interspeech.2019-1873","mag":"2939710050"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1873","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1873","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1904.05862","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102713154","display_name":"Steffen Schneider","orcid":"https://orcid.org/0000-0003-2327-6459"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Steffen Schneider","raw_affiliation_strings":["Technical University of Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"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"],"raw_orcid":null,"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"],"raw_orcid":null,"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta (Israel), Tel Aviv, Israel","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":76,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3465","last_page":"3469"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.7580877542495728},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7308038473129272},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.6485471725463867},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5946234464645386},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5779874324798584},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5463595390319824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5036126971244812},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.49831128120422363},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.4972265064716339},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4892852008342743},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.48271605372428894},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.47969672083854675},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4703312814235687},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.4488907754421234},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43981289863586426},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.41671645641326904},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.15895676612854004},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08477771282196045}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7580877542495728},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7308038473129272},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6485471725463867},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5946234464645386},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5779874324798584},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5463595390319824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5036126971244812},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.49831128120422363},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.4972265064716339},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4892852008342743},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.48271605372428894},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.47969672083854675},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4703312814235687},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4488907754421234},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43981289863586426},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.41671645641326904},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.15895676612854004},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08477771282196045},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2019-1873","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1873","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1904.05862","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.05862","pdf_url":"https://arxiv.org/pdf/1904.05862","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":"","raw_type":"text"},{"id":"mag:2939710050","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1904.05862","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.1904.05862","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1904.05862","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1904.05862","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.05862","pdf_url":"https://arxiv.org/pdf/1904.05862","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":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2939710050.pdf","grobid_xml":"https://content.openalex.org/works/W2939710050.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W343636949","https://openalex.org/W1494198834","https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2122028591","https://openalex.org/W2141440284","https://openalex.org/W2153579005","https://openalex.org/W2193413348","https://openalex.org/W2345968833","https://openalex.org/W2468716020","https://openalex.org/W2518108298","https://openalex.org/W2520160253","https://openalex.org/W2786459654","https://openalex.org/W2794209590","https://openalex.org/W2842511635","https://openalex.org/W2889282842","https://openalex.org/W2899377381","https://openalex.org/W2914120296","https://openalex.org/W2922709902","https://openalex.org/W2933138175","https://openalex.org/W2940180244","https://openalex.org/W2944828972","https://openalex.org/W2952230511","https://openalex.org/W2953190524","https://openalex.org/W2962896489","https://openalex.org/W2962901777","https://openalex.org/W2963303951","https://openalex.org/W2963970792","https://openalex.org/W2964121744","https://openalex.org/W2970119519","https://openalex.org/W2972894903","https://openalex.org/W3127686677"],"related_works":["https://openalex.org/W2973049979","https://openalex.org/W2842511635","https://openalex.org/W3036601975","https://openalex.org/W2626778328","https://openalex.org/W2988736778","https://openalex.org/W3015356564","https://openalex.org/W2963341956","https://openalex.org/W1494198834","https://openalex.org/W3207925072","https://openalex.org/W3160235762","https://openalex.org/W3133501470","https://openalex.org/W3125709657","https://openalex.org/W3145189018","https://openalex.org/W2056786202","https://openalex.org/W3026842484","https://openalex.org/W2103933358","https://openalex.org/W2397119088","https://openalex.org/W3130315320","https://openalex.org/W2044020303","https://openalex.org/W2124558353"],"abstract_inverted_index":{"We":[0,35],"explore":[1],"unsupervised":[2],"pre-training":[3],"for":[4],"speech":[5],"recognition":[6],"by":[7,64],"learning":[8],"representations":[9,26],"of":[10,19,57,73,105],"raw":[11],"audio.":[12],"wav2vec":[13],"is":[14,76],"trained":[15],"on":[16,53,83],"large":[17],"amounts":[18],"unlabeled":[20],"audio":[21],"data":[22,75],"and":[23],"the":[24,84,93,99],"resulting":[25],"are":[27],"then":[28],"used":[29],"to":[30,66],"improve":[31],"acoustic":[32],"model":[33],"training.":[34],"pre-train":[36],"a":[37,45,58,70],"simple":[38],"multi-layer":[39],"convolutional":[40],"neural":[41],"network":[42],"optimized":[43],"via":[44],"noise":[46],"contrastive":[47],"binary":[48],"classification":[49],"task.":[50],"Our":[51,78],"experiments":[52],"WSJ":[54],"reduce":[55],"WER":[56,82],"strong":[59],"character-based":[60,96],"log-mel":[61],"filterbank":[62],"baseline":[63],"up":[65],"36%":[67],"when":[68],"only":[69],"few":[71],"hours":[72],"transcribed":[74],"available.":[77],"approach":[79],"achieves":[80],"2.43%":[81],"nov92":[85],"test":[86],"set.":[87],"This":[88],"outperforms":[89],"Deep":[90],"Speech":[91],"2,":[92],"best":[94],"reported":[95],"system":[97],"in":[98],"literature":[100],"while":[101],"using":[102],"two":[103],"orders":[104],"magnitude":[106],"less":[107],"labeled":[108],"training":[109],"data.":[110]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":24},{"year":2020,"cited_by_count":11}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}