{"id":"https://openalex.org/W2936774411","doi":"https://doi.org/10.21437/interspeech.2019-2680","title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","display_name":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2936774411","doi":"https://doi.org/10.21437/interspeech.2019-2680","mag":"2936774411"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2680","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2680","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"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1904.08779","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100613715","display_name":"Daniel Park","orcid":"https://orcid.org/0000-0002-1919-0460"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel S. Park","raw_affiliation_strings":["Google Brain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102811560","display_name":"William Chan","orcid":"https://orcid.org/0000-0001-6205-255X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Chan","raw_affiliation_strings":["Google Brain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433382","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0001-6183-0612"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Google Brain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027763497","display_name":"Chung\u2010Cheng Chiu","orcid":"https://orcid.org/0000-0001-9729-4778"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chung-Cheng Chiu","raw_affiliation_strings":["Google Brain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026064427","display_name":"Barret Zoph","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Barret Zoph","raw_affiliation_strings":["Google Brain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065360819","display_name":"Ekin D. Cubuk","orcid":"https://orcid.org/0000-0003-0524-2837"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ekin D. Cubuk","raw_affiliation_strings":["Google Brain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088551093","display_name":"Quoc V. Le","orcid":"https://orcid.org/0000-0002-1087-2844"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Quoc V. Le","raw_affiliation_strings":["Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3561,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2613","last_page":"2617"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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/T11309","display_name":"Music and Audio Processing","score":0.9983000159263611,"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/speech-recognition","display_name":"Speech recognition","score":0.7645178437232971},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7506711483001709},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6470323801040649},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.6326805353164673},{"id":"https://openalex.org/keywords/spell","display_name":"Spell","score":0.5236018300056458},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5105810761451721},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48649805784225464},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45765718817710876},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4405686855316162},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.41960498690605164},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3625924587249756},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.26055461168289185},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11703541874885559},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08457052707672119}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7645178437232971},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7506711483001709},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6470323801040649},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.6326805353164673},{"id":"https://openalex.org/C2780957641","wikidata":"https://www.wikidata.org/wiki/Q1999796","display_name":"Spell","level":2,"score":0.5236018300056458},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5105810761451721},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48649805784225464},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45765718817710876},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4405686855316162},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.41960498690605164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3625924587249756},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.26055461168289185},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11703541874885559},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08457052707672119},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2019-2680","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2680","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:1904.08779","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.08779","pdf_url":"https://arxiv.org/pdf/1904.08779","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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1904.08779","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.08779","pdf_url":"https://arxiv.org/pdf/1904.08779","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":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W97072897","https://openalex.org/W1485222997","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1915251500","https://openalex.org/W1922655562","https://openalex.org/W1989674786","https://openalex.org/W2099621636","https://openalex.org/W2102113734","https://openalex.org/W2108677974","https://openalex.org/W2112739286","https://openalex.org/W2121879602","https://openalex.org/W2131342762","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2166637769","https://openalex.org/W2183341477","https://openalex.org/W2184045248","https://openalex.org/W2184343439","https://openalex.org/W2327501763","https://openalex.org/W2397147568","https://openalex.org/W2407080277","https://openalex.org/W2514741789","https://openalex.org/W2520160253","https://openalex.org/W2521999726","https://openalex.org/W2577366047","https://openalex.org/W2597757402","https://openalex.org/W2608712415","https://openalex.org/W2617258110","https://openalex.org/W2746314669","https://openalex.org/W2759921250","https://openalex.org/W2781384251","https://openalex.org/W2782451907","https://openalex.org/W2799800213","https://openalex.org/W2804047946","https://openalex.org/W2887528618","https://openalex.org/W2888493875","https://openalex.org/W2889163603","https://openalex.org/W2889282842","https://openalex.org/W2898181186","https://openalex.org/W2904818793","https://openalex.org/W2905263927","https://openalex.org/W2912492482","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2963070863","https://openalex.org/W2963303028","https://openalex.org/W2963727906","https://openalex.org/W2963742216","https://openalex.org/W2973215447","https://openalex.org/W4289440825","https://openalex.org/W4295727797","https://openalex.org/W4297818305"],"related_works":["https://openalex.org/W2126322296","https://openalex.org/W2163537793","https://openalex.org/W2916997151","https://openalex.org/W2781555308","https://openalex.org/W3021690593","https://openalex.org/W2125343999","https://openalex.org/W4200200210","https://openalex.org/W2161188302","https://openalex.org/W2888189389","https://openalex.org/W2125971872"],"abstract_inverted_index":{"We":[0,46,60],"present":[1],"SpecAugment,":[2],"a":[3,20,88,98,130],"simple":[4],"data":[5],"augmentation":[6,28],"method":[7],"for":[8,55],"speech":[9,57],"recognition.":[10],"SpecAugment":[11,48],"is":[12],"applied":[13],"directly":[14],"to":[15,103,140],"the":[16,33,65,85,104,118,122,127,141],"feature":[17],"inputs":[18],"of":[19,31,37,43,87,109,121,129],"neural":[21],"network":[22],"(i.e.,":[23],"filter":[24],"bank":[25],"coefficients).":[26],"The":[27],"policy":[29],"consists":[30],"warping":[32],"features,":[34],"masking":[35,41],"blocks":[36,42],"frequency":[38],"channels,":[39],"and":[40,52,68,91,133],"time":[44],"steps.":[45],"apply":[47],"on":[49,64,82,117],"Listen,":[50],"Attend":[51],"Spell":[53],"networks":[54],"end-to-end":[56],"recognition":[58],"tasks.":[59],"achieve":[61,79,115],"state-of-the-art":[62,106,143],"performance":[63],"LibriSpeech":[66],"960h":[67],"Swichboard":[69],"300h":[70],"tasks,":[71],"outperforming":[72],"all":[73],"prior":[74],"work.":[75],"On":[76],"LibriSpeech,":[77],"we":[78,114],"6.8%":[80],"WER":[81,93],"test-other":[83],"without":[84,126],"use":[86,128],"language":[89,99,131],"model,":[90,132],"5.8%":[92],"with":[94,97,135],"shallow":[95,136],"fusion":[96],"model.":[100],"This":[101],"compares":[102,139],"previous":[105,142],"hybrid":[107,144],"system":[108,145],"7.5%":[110],"WER.":[111,148],"For":[112],"Switchboard,":[113],"7.2%/14.6%":[116],"Switchboard/CallHome":[119],"portion":[120],"Hub5'00":[123],"test":[124],"set":[125],"6.8%/14.1%":[134],"fusion,":[137],"which":[138],"at":[146],"8.3%/17.3%":[147]},"counts_by_year":[{"year":2026,"cited_by_count":135},{"year":2025,"cited_by_count":398},{"year":2024,"cited_by_count":433},{"year":2023,"cited_by_count":645},{"year":2022,"cited_by_count":601},{"year":2021,"cited_by_count":802},{"year":2020,"cited_by_count":457},{"year":2019,"cited_by_count":86},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2019-04-25T00:00:00"}