{"id":"https://openalex.org/W4319862247","doi":"https://doi.org/10.1109/slt54892.2023.10022748","title":"G-Augment: Searching for the Meta-Structure of Data Augmentation Policies for ASR","display_name":"G-Augment: Searching for the Meta-Structure of Data Augmentation Policies for ASR","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862247","doi":"https://doi.org/10.1109/slt54892.2023.10022748"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022748","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022748","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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/A5025935520","display_name":"Gary Wang","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":"Gary Wang","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/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 Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102902866","display_name":"Andrew Rosenberg","orcid":"https://orcid.org/0000-0003-1780-4390"},"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":"Andrew Rosenberg","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/A5038305187","display_name":"Shuyang Cheng","orcid":"https://orcid.org/0000-0001-5311-7235"},"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":"Shuyang Cheng","raw_affiliation_strings":["Google Inc","Pony.ai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Pony.ai","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103273436","display_name":"Ron J. Weiss","orcid":"https://orcid.org/0000-0003-2010-4053"},"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":"Ron J. Weiss","raw_affiliation_strings":["Google Inc","Meta Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Meta Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","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":"Bhuvana Ramabhadran","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/A5103874391","display_name":"Pedro J. Moreno","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":"Pedro J. Moreno","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/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"]}]}],"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":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9994000196456909,"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/T10028","display_name":"Topic Modeling","score":0.9988999962806702,"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/augment","display_name":"Augment","score":0.9793349504470825},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7640022039413452},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7479588985443115},{"id":"https://openalex.org/keywords/directed-acyclic-graph","display_name":"Directed acyclic graph","score":0.5966736674308777},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.47151103615760803},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4571840465068817},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42715656757354736},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2943336069583893},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26943260431289673},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13521432876586914}],"concepts":[{"id":"https://openalex.org/C2779070825","wikidata":"https://www.wikidata.org/wiki/Q760434","display_name":"Augment","level":2,"score":0.9793349504470825},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7640022039413452},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7479588985443115},{"id":"https://openalex.org/C74197172","wikidata":"https://www.wikidata.org/wiki/Q1195339","display_name":"Directed acyclic graph","level":2,"score":0.5966736674308777},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.47151103615760803},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4571840465068817},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42715656757354736},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2943336069583893},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26943260431289673},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13521432876586914},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10022748","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022748","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W84880661","https://openalex.org/W157468466","https://openalex.org/W1494198834","https://openalex.org/W1639032689","https://openalex.org/W1659842140","https://openalex.org/W1828163288","https://openalex.org/W1979651826","https://openalex.org/W2020399841","https://openalex.org/W2040492000","https://openalex.org/W2111935653","https://openalex.org/W2112796928","https://openalex.org/W2125336414","https://openalex.org/W2136439176","https://openalex.org/W2156163116","https://openalex.org/W2184343439","https://openalex.org/W2250357346","https://openalex.org/W2291975472","https://openalex.org/W2335728318","https://openalex.org/W2407080277","https://openalex.org/W2604262106","https://openalex.org/W2617258110","https://openalex.org/W2696967604","https://openalex.org/W2732547613","https://openalex.org/W2746314669","https://openalex.org/W2751134959","https://openalex.org/W2799473636","https://openalex.org/W2936774411","https://openalex.org/W2952217990","https://openalex.org/W2954996726","https://openalex.org/W2964081807","https://openalex.org/W2965658867","https://openalex.org/W2975761646","https://openalex.org/W2995181338","https://openalex.org/W3015995734","https://openalex.org/W3020336359","https://openalex.org/W3023540311","https://openalex.org/W3026041220","https://openalex.org/W3030437843","https://openalex.org/W3035160371","https://openalex.org/W3036601975","https://openalex.org/W3095687973","https://openalex.org/W3097777922","https://openalex.org/W3101648800","https://openalex.org/W3103351485","https://openalex.org/W3106753828","https://openalex.org/W3118608800","https://openalex.org/W3139918052","https://openalex.org/W3160259745","https://openalex.org/W3204696009","https://openalex.org/W4226207853","https://openalex.org/W4295727797","https://openalex.org/W4394662461","https://openalex.org/W6606439196","https://openalex.org/W6638749077","https://openalex.org/W6675409298","https://openalex.org/W6691509046","https://openalex.org/W6743428213","https://openalex.org/W6743928203","https://openalex.org/W6751795773","https://openalex.org/W6762334975","https://openalex.org/W6762619590","https://openalex.org/W6768297763","https://openalex.org/W6771467084","https://openalex.org/W6775002999","https://openalex.org/W6775537894","https://openalex.org/W6780218876","https://openalex.org/W6791904447","https://openalex.org/W6810921645","https://openalex.org/W6863618527"],"related_works":["https://openalex.org/W2584455473","https://openalex.org/W4303857474","https://openalex.org/W4239295757","https://openalex.org/W1989218596","https://openalex.org/W2355215981","https://openalex.org/W831794578","https://openalex.org/W2370652759","https://openalex.org/W1480922982","https://openalex.org/W4307074309","https://openalex.org/W4319862247"],"abstract_inverted_index":{"Data":[0],"augmentation":[1,34,37,56,71],"is":[2,106],"a":[3,51,111],"ubiquitous":[4],"technique":[5,52],"used":[6],"to":[7,10,39,43,53,68,88,109,136,143],"provide":[8],"robustness":[9],"automatic":[11],"speech":[12],"recognition":[13],"(ASR)":[14],"training.":[15],"However,":[16],"even":[17],"as":[18,58],"so":[19],"much":[20],"of":[21],"the":[22,32,55,70,78,117],"ASR":[23,114],"training":[24,138],"process":[25],"has":[26],"become":[27],"automated":[28],"and":[29,41,63,103,139],"more":[30],"\u201cend-to-end,\u201d":[31],"data":[33],"policy":[35,72],"(what":[36],"functions":[38],"use,":[40],"how":[42],"apply":[44],"them)":[45],"remains":[46],"hand-crafted.":[47],"We":[48,74,123],"present":[49],"G(raph)-Augment,":[50],"define":[54],"space":[57,67],"directed":[59],"acyclic":[60],"graphs":[61],"(DAGs)":[62],"search":[64,97],"over":[65],"this":[66],"optimize":[69],"itself.":[73],"show":[75,130],"that":[76,126],"given":[77],"same":[79],"computational":[80],"budget,":[81],"policies":[82,93,129],"produced":[83],"by":[84,95],"G-Augment":[85,105],"are":[86],"able":[87,108],"perform":[89],"better":[90,131],"than":[91],"SpecAugment":[92,145],"obtained":[94],"random":[96],"on":[98,101,116],"fine-tuning":[99],"tasks":[100],"CHiME-6":[102,118],"AMI.":[104],"also":[107],"establish":[110],"new":[112],"state-of-the-art":[113],"performance":[115],"evaluation":[119],"set":[120],"(30.7%":[121],"WER).":[122],"further":[124],"demonstrate":[125],"G-":[127],"Augment":[128],"transfer":[132],"properties":[133],"across":[134],"warm-start":[135],"cold-start":[137],"model":[140],"size":[141],"compared":[142],"random-searched":[144],"policies.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}