{"id":"https://openalex.org/W3161714660","doi":"https://doi.org/10.1109/icassp39728.2021.9414316","title":"Enhancing Audio Augmentation Methods with Consistency Learning","display_name":"Enhancing Audio Augmentation Methods with Consistency Learning","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161714660","doi":"https://doi.org/10.1109/icassp39728.2021.9414316","mag":"3161714660"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414316","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5056441203","display_name":"Turab Iqbal","orcid":"https://orcid.org/0000-0003-3393-2544"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Turab Iqbal","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing,UK","Centre for Vision, Speech and Signal Processing, University of Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing,UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014282181","display_name":"Karim Helwani","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karim Helwani","raw_affiliation_strings":["Amazon Web Services, Inc,Palo Alto,CA,USA","Amazon Web Services, Inc, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services, Inc,Palo Alto,CA,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Web Services, Inc, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112751528","display_name":"Arvindh Krishnaswamy","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arvindh Krishnaswamy","raw_affiliation_strings":["Amazon Web Services, Inc,Palo Alto,CA,USA","Amazon Web Services, Inc, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services, Inc,Palo Alto,CA,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Web Services, Inc, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing,UK","Centre for Vision, Speech and Signal Processing, University of Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing,UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7252,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.68014909,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"646","last_page":"650"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980000257492065,"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/computer-science","display_name":"Computer science","score":0.7897974252700806},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6398580074310303},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5411350727081299},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5383867025375366},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5191035270690918},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5172789096832275},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.4948047995567322},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.47457173466682434},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43724122643470764},{"id":"https://openalex.org/keywords/weak-consistency","display_name":"Weak consistency","score":0.414399117231369},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33265459537506104},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.20590367913246155},{"id":"https://openalex.org/keywords/strong-consistency","display_name":"Strong consistency","score":0.20169666409492493},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10022130608558655},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0748065710067749}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7897974252700806},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6398580074310303},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5411350727081299},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5383867025375366},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5191035270690918},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5172789096832275},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.4948047995567322},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.47457173466682434},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43724122643470764},{"id":"https://openalex.org/C122377713","wikidata":"https://www.wikidata.org/wiki/Q4422799","display_name":"Weak consistency","level":4,"score":0.414399117231369},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33265459537506104},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.20590367913246155},{"id":"https://openalex.org/C31388003","wikidata":"https://www.wikidata.org/wiki/Q7624548","display_name":"Strong consistency","level":3,"score":0.20169666409492493},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10022130608558655},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0748065710067749},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414316","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W2052666245","https://openalex.org/W2096733369","https://openalex.org/W2163922914","https://openalex.org/W2342045095","https://openalex.org/W2509065397","https://openalex.org/W2767754137","https://openalex.org/W2908510526","https://openalex.org/W2917294828","https://openalex.org/W2936774411","https://openalex.org/W2949117887","https://openalex.org/W2962369866","https://openalex.org/W2964159205","https://openalex.org/W2973049979","https://openalex.org/W2994088087","https://openalex.org/W2994931756","https://openalex.org/W3005680577","https://openalex.org/W3021472582","https://openalex.org/W3034978746","https://openalex.org/W3047666748","https://openalex.org/W3094550259","https://openalex.org/W3097034112","https://openalex.org/W3097679055","https://openalex.org/W3098357269","https://openalex.org/W3099206234","https://openalex.org/W3106031848","https://openalex.org/W3127902700","https://openalex.org/W6637373629","https://openalex.org/W6638667902","https://openalex.org/W6757817989","https://openalex.org/W6765939562","https://openalex.org/W6770979763","https://openalex.org/W6774314701","https://openalex.org/W6776411772"],"related_works":["https://openalex.org/W3010022189","https://openalex.org/W2805810362","https://openalex.org/W4301894417","https://openalex.org/W2971748376","https://openalex.org/W2098650100","https://openalex.org/W2560551601","https://openalex.org/W2389185733","https://openalex.org/W2123855908","https://openalex.org/W2166510438","https://openalex.org/W4290062159"],"abstract_inverted_index":{"Data":[0],"augmentation":[1,133],"is":[2,12,26,44],"an":[3],"inexpensive":[4],"way":[5],"to":[6,39],"increase":[7],"training":[8,62],"data":[9,35],"diversity,":[10],"and":[11,70,107],"commonly":[13],"achieved":[14],"via":[15],"transformations":[16],"of":[17,33,61,82,97,120],"existing":[18,132],"data.":[19],"For":[20],"tasks":[21,121],"such":[22,40,51,110,122],"as":[23,52,123],"classification,":[24],"there":[25],"a":[27],"good":[28],"case":[29],"for":[30],"learning":[31,138],"representations":[32],"the":[34,53,59,80,88,104,113,118],"that":[36,64,94,108],"are":[37,99],"invariant":[38],"transformations,":[41],"yet":[42],"this":[43,67],"not":[45,100],"explicitly":[46,65],"enforced":[47],"by":[48,103,139],"classification":[49,77],"losses":[50],"cross-entropy":[54,105],"loss.":[55],"This":[56],"paper":[57],"investigates":[58],"use":[60],"objectives":[63],"impose":[66],"consistency":[68,98],"constraint,":[69],"how":[71,131],"it":[72],"can":[73,116,135],"impact":[74],"downstream":[75],"audio":[76,124],"tasks.":[78],"In":[79],"context":[81],"deep":[83],"convolutional":[84],"neural":[85],"networks":[86],"in":[87],"supervised":[89],"setting,":[90],"we":[91,129],"show":[92],"empirically":[93],"certain":[95],"measures":[96,111],"implicitly":[101],"captured":[102],"loss,":[106],"incorporating":[109],"into":[112],"loss":[114],"function":[115],"improve":[117,137],"performance":[119],"tagging.":[125],"Put":[126],"another":[127],"way,":[128],"demonstrate":[130],"methods":[134],"further":[136],"enforcing":[140],"consistency.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}