{"id":"https://openalex.org/W3015995734","doi":"https://doi.org/10.1109/icassp40776.2020.9053205","title":"Specaugment on Large Scale Datasets","display_name":"Specaugment on Large Scale Datasets","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015995734","doi":"https://doi.org/10.1109/icassp40776.2020.9053205","mag":"3015995734"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053205","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053205","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":"conference-paper","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/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 Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433648","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0002-9505-1833"},"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 Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","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 Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018757219","display_name":"Youzheng Chen","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":"Youzheng Chen","raw_affiliation_strings":["Google Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004328744","display_name":"Bo Li","orcid":"https://orcid.org/0000-0002-4632-2721"},"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":"Bo Li","raw_affiliation_strings":["Google Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","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 Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","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 Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010253402","display_name":"Yonghui Wu","orcid":"https://orcid.org/0000-0002-6780-6135"},"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":"Yonghui Wu","raw_affiliation_strings":["Google Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","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":148,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6879","last_page":"6883"},"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":0.9966999888420105,"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":0.9952999949455261,"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":0.7788156270980835},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7007620334625244},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6884166598320007},{"id":"https://openalex.org/keywords/spell","display_name":"Spell","score":0.6070622801780701},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.587992787361145},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.49904298782348633},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.46336787939071655},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.44146230816841125},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.43400442600250244},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4207974076271057},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.4128209352493286},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3579249083995819},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32659900188446045},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10260939598083496}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7788156270980835},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7007620334625244},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6884166598320007},{"id":"https://openalex.org/C2780957641","wikidata":"https://www.wikidata.org/wiki/Q1999796","display_name":"Spell","level":2,"score":0.6070622801780701},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.587992787361145},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.49904298782348633},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.46336787939071655},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.44146230816841125},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.43400442600250244},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4207974076271057},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4128209352493286},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3579249083995819},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32659900188446045},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10260939598083496},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053205","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053205","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1485222997","https://openalex.org/W1494198834","https://openalex.org/W1915251500","https://openalex.org/W1922655562","https://openalex.org/W1989674786","https://openalex.org/W2099621636","https://openalex.org/W2121879602","https://openalex.org/W2184343439","https://openalex.org/W2327501763","https://openalex.org/W2397147568","https://openalex.org/W2398826216","https://openalex.org/W2407080277","https://openalex.org/W2577366047","https://openalex.org/W2617258110","https://openalex.org/W2622203030","https://openalex.org/W2759921250","https://openalex.org/W2887528618","https://openalex.org/W2888493875","https://openalex.org/W2936774411","https://openalex.org/W2944255943","https://openalex.org/W2962760690","https://openalex.org/W2962824709","https://openalex.org/W2963122170","https://openalex.org/W2963590452","https://openalex.org/W2972816482","https://openalex.org/W2972818416","https://openalex.org/W2972991469","https://openalex.org/W2977728428","https://openalex.org/W3006827623","https://openalex.org/W3103005696","https://openalex.org/W6675409298","https://openalex.org/W6686369942","https://openalex.org/W6712560600","https://openalex.org/W6713762819","https://openalex.org/W6738686518","https://openalex.org/W6753435171"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4287256643","https://openalex.org/W2011227383","https://openalex.org/W4375868962","https://openalex.org/W2088854863","https://openalex.org/W2745258745","https://openalex.org/W1976719989","https://openalex.org/W2942893872","https://openalex.org/W2065606036","https://openalex.org/W3179495260"],"abstract_inverted_index":{"Recently,":[0],"SpecAugment,":[1],"an":[2],"augmentation":[3],"scheme":[4],"for":[5],"automatic":[6],"speech":[7],"recognition":[8],"that":[9,91],"acts":[10],"directly":[11],"on":[12,31,41,100,132,137,142],"the":[13,26,52,81,93,101,104,123,126],"spectrogram":[14],"of":[15,28,89,103,125],"input":[16],"utterances,":[17],"has":[18],"shown":[19],"to":[20,51,120,134],"be":[21],"highly":[22],"effective":[23],"in":[24],"enhancing":[25],"performance":[27,124],"end-to-end":[29],"networks":[30],"public":[32],"datasets.":[33],"In":[34],"this":[35],"paper,":[36],"we":[37,117],"demonstrate":[38],"its":[39,49],"effectiveness":[40],"tasks":[42],"with":[43,73],"large":[44,110],"scale":[45,111],"datasets":[46],"by":[47,67],"investigating":[48],"application":[50],"Google":[53],"Multidomain":[54],"Dataset":[55],"(Narayanan":[56],"et":[57],"al.,":[58],"2018).":[59],"We":[60,84],"achieve":[61],"improvement":[62],"across":[63],"all":[64],"test":[65],"domains":[66],"mixing":[68],"raw":[69],"training":[70,77,80],"data":[71,78],"augmented":[72],"SpecAugment":[74,90],"and":[75,129,139],"noise-perturbed":[76],"when":[79],"acoustic":[82],"model.":[83],"also":[85],"introduce":[86],"a":[87],"modification":[88],"adapts":[92],"time":[94],"mask":[95],"size":[96],"and/or":[97],"multiplicity":[98],"depending":[99],"length":[102],"utterance,":[105],"which":[106],"can":[107],"potentially":[108],"benefit":[109],"tasks.":[112],"By":[113],"using":[114],"adaptive":[115],"masking,":[116],"are":[118],"able":[119],"further":[121],"improve":[122],"Listen,":[127],"Attend":[128],"Spell":[130],"model":[131],"LibriSpeech":[133],"2.2%":[135],"WER":[136,141],"test-clean":[138],"5.2%":[140],"test-other.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":23},{"year":2023,"cited_by_count":21},{"year":2022,"cited_by_count":26},{"year":2021,"cited_by_count":36},{"year":2020,"cited_by_count":24}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}