{"id":"https://openalex.org/W3015356564","doi":"https://doi.org/10.1109/icassp40776.2020.9054224","title":"Effectiveness of Self-Supervised Pre-Training for ASR","display_name":"Effectiveness of Self-Supervised Pre-Training for ASR","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015356564","doi":"https://doi.org/10.1109/icassp40776.2020.9054224","mag":"3015356564"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054224","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054224","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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":true,"raw_author_name":"Alexei Baevski","raw_affiliation_strings":["Facebook AI Research"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103742478","display_name":"Abdelrahman Mohamed","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":"Abdelrahman Mohamed","raw_affiliation_strings":["Facebook AI Research"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5031979802"],"corresponding_institution_ids":["https://openalex.org/I2252078561"],"apc_list":null,"apc_paid":null,"fwci":9.3785,"has_fulltext":false,"cited_by_count":99,"citation_normalized_percentile":{"value":0.98382294,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7694","last_page":"7698"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9994999766349792,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9984999895095825,"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":0.7773282527923584},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6874544024467468},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6137593388557434},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5707540512084961},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.5544864535331726},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.5465089082717896},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5404589772224426},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5377901196479797},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4752331078052521},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.4564949572086334},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3677269518375397},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36472076177597046},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.28223928809165955}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7773282527923584},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6874544024467468},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6137593388557434},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5707540512084961},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5544864535331726},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.5465089082717896},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5404589772224426},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5377901196479797},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4752331078052521},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4564949572086334},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3677269518375397},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36472076177597046},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28223928809165955},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"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":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054224","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054224","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W30845872","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W2025482506","https://openalex.org/W2055408826","https://openalex.org/W2059652594","https://openalex.org/W2114347655","https://openalex.org/W2124558353","https://openalex.org/W2296681920","https://openalex.org/W2586148577","https://openalex.org/W2667408400","https://openalex.org/W2752796333","https://openalex.org/W2842511635","https://openalex.org/W2896457183","https://openalex.org/W2932675979","https://openalex.org/W2933138175","https://openalex.org/W2936774411","https://openalex.org/W2940322076","https://openalex.org/W2941814890","https://openalex.org/W2944255943","https://openalex.org/W2948012107","https://openalex.org/W2953190524","https://openalex.org/W2962907457","https://openalex.org/W2963341956","https://openalex.org/W2963382687","https://openalex.org/W2963425185","https://openalex.org/W2963571336","https://openalex.org/W2963799213","https://openalex.org/W2963807318","https://openalex.org/W2964001192","https://openalex.org/W2964110616","https://openalex.org/W2964115348","https://openalex.org/W2965373594","https://openalex.org/W2970119519","https://openalex.org/W2971155163","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2979476256","https://openalex.org/W2981857663","https://openalex.org/W2995181338","https://openalex.org/W2996383576","https://openalex.org/W2998649947","https://openalex.org/W3015522062","https://openalex.org/W3103005696","https://openalex.org/W4297808394","https://openalex.org/W6631362777","https://openalex.org/W6697456849","https://openalex.org/W6755207826","https://openalex.org/W6760911985","https://openalex.org/W6761176036","https://openalex.org/W6761563299","https://openalex.org/W6763416564","https://openalex.org/W6766673545","https://openalex.org/W6769196770","https://openalex.org/W6769557084","https://openalex.org/W6771812881","https://openalex.org/W6772641181","https://openalex.org/W6775452034"],"related_works":["https://openalex.org/W2130553454","https://openalex.org/W3022007134","https://openalex.org/W4317548404","https://openalex.org/W2087783760","https://openalex.org/W1509924131","https://openalex.org/W4287241967","https://openalex.org/W3144173820","https://openalex.org/W209733029","https://openalex.org/W3163689946","https://openalex.org/W4287890939"],"abstract_inverted_index":{"We":[0,18,80],"compare":[1,94],"self-supervised":[2],"representation":[3],"learning":[4,42,86],"algorithms":[5],"which":[6],"either":[7],"explicitly":[8],"quantize":[9],"the":[10,20,33,57,74,89,122],"audio":[11,91,98],"data":[12,34,92,112,133],"or":[13],"learn":[14],"representations":[15,45,75],"without":[16],"quantization.":[17],"find":[19],"former":[21],"to":[22,40,51,99],"be":[23],"more":[24],"accurate":[25],"since":[26],"it":[27],"builds":[28],"a":[29,65,77,83,103,114,138,172],"good":[30,120],"vocabulary":[31,116],"of":[32,43,72,109,131,149,175],"through":[35],"vq-wav2vec":[36,115],"[1]":[37],"self-supervision":[38,164],"approach":[39],"enable":[41,166],"effective":[44],"in":[46],"subsequent":[47],"BERT":[48,59,104],"training.":[49],"Different":[50],"previous":[52],"work,":[53],"we":[54],"directly":[55,87],"fine-tune":[56],"pre-trained":[58],"models":[60],"on":[61,96,106,128,134,142,155,159,171],"transcribed":[62,176],"speech":[63,167],"using":[64,145],"Connectionist":[66],"Temporal":[67],"Classification":[68],"(CTC)":[69],"loss":[70],"instead":[71],"feeding":[73],"into":[76],"task-specific":[78],"model.":[79],"also":[81],"propose":[82],"BERT-style":[84],"model":[85,105],"from":[88],"continuous":[90],"and":[93,157],"pre-training":[95],"raw":[97],"spectral":[100],"features.":[101],"Fine-tuning":[102],"10":[107,147],"hour":[108],"labeled":[110,132,150],"Librispeech":[111],"with":[113],"is":[117,153],"almost":[118],"as":[119,121],"best":[123],"known":[124],"reported":[125],"system":[126],"trained":[127,170],"100":[129],"hours":[130],"test-clean,":[135],"while":[136],"achieving":[137],"25%":[139],"WER":[140,152],"reduction":[141],"test-other.":[143],"When":[144],"only":[146],"minutes":[148],"data,":[151],"25.2":[154],"test-other":[156],"16.3":[158],"test-clean.":[160],"This":[161],"demonstrates":[162],"that":[163],"can":[165],"recognition":[168],"systems":[169],"near-zero":[173],"amount":[174],"data.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":23},{"year":2020,"cited_by_count":3}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}