{"id":"https://openalex.org/W4375869071","doi":"https://doi.org/10.1109/icassp49357.2023.10095001","title":"Randmasking Augment: A Simple and Randomized Data Augmentation For Acoustic Scene Classification","display_name":"Randmasking Augment: A Simple and Randomized Data Augmentation For Acoustic Scene Classification","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869071","doi":"https://doi.org/10.1109/icassp49357.2023.10095001"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095001","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095001","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5101201258","display_name":"Jubum Han","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jubum Han","raw_affiliation_strings":["Samsung Research,Korea","Samsung Research, Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research,Korea","institution_ids":["https://openalex.org/I2250650973"]},{"raw_affiliation_string":"Samsung Research, Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083485295","display_name":"Mateusz Matuszewski","orcid":"https://orcid.org/0000-0003-2821-1750"},"institutions":[{"id":"https://openalex.org/I4210128738","display_name":"Samsung (Poland)","ror":"https://ror.org/0381acm07","country_code":"PL","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210128738"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Mateusz Matuszewski","raw_affiliation_strings":["Samsung R&D Institute Poland,Poland"],"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute Poland,Poland","institution_ids":["https://openalex.org/I4210128738"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092339702","display_name":"Olaf Sikorski","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128738","display_name":"Samsung (Poland)","ror":"https://ror.org/0381acm07","country_code":"PL","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210128738"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Olaf Sikorski","raw_affiliation_strings":["Samsung R&D Institute Poland,Poland"],"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute Poland,Poland","institution_ids":["https://openalex.org/I4210128738"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082652105","display_name":"Hosang Sung","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hosang Sung","raw_affiliation_strings":["Samsung Research,Korea","Samsung Research, Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research,Korea","institution_ids":["https://openalex.org/I2250650973"]},{"raw_affiliation_string":"Samsung Research, Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051855901","display_name":"Hoonyoung Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hoonyoung Cho","raw_affiliation_strings":["Samsung Research,Korea","Samsung Research, Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research,Korea","institution_ids":["https://openalex.org/I2250650973"]},{"raw_affiliation_string":"Samsung Research, Korea","institution_ids":["https://openalex.org/I2250650973"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101201258"],"corresponding_institution_ids":["https://openalex.org/I2250650973"],"apc_list":null,"apc_paid":null,"fwci":0.8133,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7022595,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9973999857902527,"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/spectrogram","display_name":"Spectrogram","score":0.8421545028686523},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7430702447891235},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.7253316044807434},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5688043832778931},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5370489954948425},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.524591863155365},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5219770669937134},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5079367756843567},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5034565329551697},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41027557849884033}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8421545028686523},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7430702447891235},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.7253316044807434},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5688043832778931},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5370489954948425},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.524591863155365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5219770669937134},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5079367756843567},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5034565329551697},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41027557849884033},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"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/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095001","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095001","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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":34,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2154778040","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2765407302","https://openalex.org/W2773284573","https://openalex.org/W2936774411","https://openalex.org/W2937299048","https://openalex.org/W2955425717","https://openalex.org/W2963855133","https://openalex.org/W2982083293","https://openalex.org/W2982346427","https://openalex.org/W2982415754","https://openalex.org/W2992308087","https://openalex.org/W2998508940","https://openalex.org/W3015530480","https://openalex.org/W3035682985","https://openalex.org/W3097327166","https://openalex.org/W3178592608","https://openalex.org/W3196782138","https://openalex.org/W3197827948","https://openalex.org/W3198860978","https://openalex.org/W3203468141","https://openalex.org/W3212656946","https://openalex.org/W4225270894","https://openalex.org/W4295723153","https://openalex.org/W4298091485","https://openalex.org/W6631190155","https://openalex.org/W6745136726","https://openalex.org/W6752516136","https://openalex.org/W6762718338","https://openalex.org/W6779341498","https://openalex.org/W6803691255","https://openalex.org/W6810938606"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W2942893872"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3],"describe":[4],"RandMasking":[5,79],"Augment":[6,80],"as":[7],"an":[8],"effective":[9],"data":[10],"augmentation":[11,27,67,105,124,128],"method":[12],"for":[13],"acoustic":[14,51],"scene":[15],"classification":[16],"research.":[17],"We":[18,101],"concentrate":[19],"on":[20,93,106],"both":[21],"time":[22,38,63],"and":[23,31,39,62,89,112,118],"frequency":[24,40,61,94],"domains":[25],"masking":[26,48,99],"introduced":[28],"in":[29,76,96],"SpecAugment,":[30],"apply":[32],"various":[33,56,133],"transformations":[34],"that":[35],"can":[36,68,81],"maintain":[37],"information":[41],"of":[42,60,72],"the":[43,47,65,73,97,103,107,113],"original":[44],"spectrogram":[45],"to":[46],"region.":[49,100],"Because":[50],"feature":[52],"is":[53,120],"transformed":[54],"into":[55],"forms":[57],"without":[58],"distortion":[59],"information,":[64],"proposed":[66,127],"capture":[69],"unique":[70],"characteristics":[71],"input":[74],"audio":[75,87],"detail.":[77],"Moreover,":[78],"be":[82],"extended":[83],"by":[84],"mixing":[85],"other":[86,123],"samples":[88],"applying":[90],"different":[91],"weights":[92],"bands":[95],"randomized":[98],"evaluate":[102],"suggested":[104],"DCASE":[108,114],"2018":[109],"Task1A":[110,116],"dataset":[111],"2019":[115],"dataset,":[117],"it":[119],"compared":[121],"with":[122,132],"methods.":[125],"The":[126],"shows":[129],"outstanding":[130],"performances":[131],"popular":[134],"convolutional":[135],"neural":[136],"networks.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}