{"id":"https://openalex.org/W4385822870","doi":"https://doi.org/10.21437/interspeech.2023-1426","title":"Patch-Mix Contrastive Learning with Audio Spectrogram Transformer on Respiratory Sound Classification","display_name":"Patch-Mix Contrastive Learning with Audio Spectrogram Transformer on Respiratory Sound Classification","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822870","doi":"https://doi.org/10.21437/interspeech.2023-1426"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-1426","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/A5112425608","display_name":"Sangmin Bae","orcid":null},"institutions":[{"id":"https://openalex.org/I3130844761","display_name":"MODUL University Dubai","ror":"https://ror.org/04rrhkc58","country_code":"AE","type":"education","lineage":["https://openalex.org/I150545927","https://openalex.org/I3130844761"]},{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["AE","CA","KR"],"is_corresponding":false,"raw_author_name":"Sangmin Bae","raw_affiliation_strings":["MODULABS","KAIST AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MODULABS","institution_ids":["https://openalex.org/I3130844761"]},{"raw_affiliation_string":"KAIST AI","institution_ids":["https://openalex.org/I4210099236","https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085336408","display_name":"June-Woo Kim","orcid":"https://orcid.org/0000-0003-0111-300X"},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]},{"id":"https://openalex.org/I3130844761","display_name":"MODUL University Dubai","ror":"https://ror.org/04rrhkc58","country_code":"AE","type":"education","lineage":["https://openalex.org/I150545927","https://openalex.org/I3130844761"]}],"countries":["AE","KR"],"is_corresponding":false,"raw_author_name":"June-Woo Kim","raw_affiliation_strings":["MODULABS","Department of AI, Kyungpook National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MODULABS","institution_ids":["https://openalex.org/I3130844761"]},{"raw_affiliation_string":"Department of AI, Kyungpook National University","institution_ids":["https://openalex.org/I31419693"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109692699","display_name":"Won-Yang Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127432","display_name":"Start Making A Reader Today","ror":"https://ror.org/0345xq683","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210127432"]},{"id":"https://openalex.org/I3130844761","display_name":"MODUL University Dubai","ror":"https://ror.org/04rrhkc58","country_code":"AE","type":"education","lineage":["https://openalex.org/I150545927","https://openalex.org/I3130844761"]}],"countries":["AE","US"],"is_corresponding":false,"raw_author_name":"Won-Yang Cho","raw_affiliation_strings":["SmartSound","MODULABS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SmartSound","institution_ids":["https://openalex.org/I4210127432"]},{"raw_affiliation_string":"MODULABS","institution_ids":["https://openalex.org/I3130844761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109715198","display_name":"Hyerim Baek","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127432","display_name":"Start Making A Reader Today","ror":"https://ror.org/0345xq683","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210127432"]},{"id":"https://openalex.org/I3130844761","display_name":"MODUL University Dubai","ror":"https://ror.org/04rrhkc58","country_code":"AE","type":"education","lineage":["https://openalex.org/I150545927","https://openalex.org/I3130844761"]}],"countries":["AE","US"],"is_corresponding":false,"raw_author_name":"Hyerim Baek","raw_affiliation_strings":["MODULABS","SmartSound"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MODULABS","institution_ids":["https://openalex.org/I3130844761"]},{"raw_affiliation_string":"SmartSound","institution_ids":["https://openalex.org/I4210127432"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101206792","display_name":"Soyoun Son","orcid":null},"institutions":[{"id":"https://openalex.org/I3130844761","display_name":"MODUL University Dubai","ror":"https://ror.org/04rrhkc58","country_code":"AE","type":"education","lineage":["https://openalex.org/I150545927","https://openalex.org/I3130844761"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Soyoun Son","raw_affiliation_strings":["MODULABS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MODULABS","institution_ids":["https://openalex.org/I3130844761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088555849","display_name":"Byungjo Lee","orcid":"https://orcid.org/0000-0002-1404-8246"},"institutions":[{"id":"https://openalex.org/I3130844761","display_name":"MODUL University Dubai","ror":"https://ror.org/04rrhkc58","country_code":"AE","type":"education","lineage":["https://openalex.org/I150545927","https://openalex.org/I3130844761"]},{"id":"https://openalex.org/I205490536","display_name":"Dongguk University","ror":"https://ror.org/057q6n778","country_code":"KR","type":"education","lineage":["https://openalex.org/I205490536"]}],"countries":["AE","KR"],"is_corresponding":false,"raw_author_name":"Byungjo Lee","raw_affiliation_strings":["MODULABS","Dongguk University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MODULABS","institution_ids":["https://openalex.org/I3130844761"]},{"raw_affiliation_string":"Dongguk University","institution_ids":["https://openalex.org/I205490536"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023297568","display_name":"Chang-Wan Ha","orcid":"https://orcid.org/0000-0001-9504-9963"},"institutions":[{"id":"https://openalex.org/I3130844761","display_name":"MODUL University Dubai","ror":"https://ror.org/04rrhkc58","country_code":"AE","type":"education","lineage":["https://openalex.org/I150545927","https://openalex.org/I3130844761"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Changwan Ha","raw_affiliation_strings":["MODULABS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MODULABS","institution_ids":["https://openalex.org/I3130844761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059669800","display_name":"Kyongpil Tae","orcid":null},"institutions":[{"id":"https://openalex.org/I3130844761","display_name":"MODUL University Dubai","ror":"https://ror.org/04rrhkc58","country_code":"AE","type":"education","lineage":["https://openalex.org/I150545927","https://openalex.org/I3130844761"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Kyongpil Tae","raw_affiliation_strings":["MODULABS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MODULABS","institution_ids":["https://openalex.org/I3130844761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056038923","display_name":"Sungnyun Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]},{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["CA","KR"],"is_corresponding":false,"raw_author_name":"Sungnyun Kim","raw_affiliation_strings":["KAIST AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST AI","institution_ids":["https://openalex.org/I4210099236","https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091674853","display_name":"Se-Young Yun","orcid":"https://orcid.org/0000-0001-6675-5113"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]},{"id":"https://openalex.org/I3130844761","display_name":"MODUL University Dubai","ror":"https://ror.org/04rrhkc58","country_code":"AE","type":"education","lineage":["https://openalex.org/I150545927","https://openalex.org/I3130844761"]}],"countries":["AE","CA","KR"],"is_corresponding":true,"raw_author_name":"Se-Young Yun","raw_affiliation_strings":["MODULABS","KAIST AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MODULABS","institution_ids":["https://openalex.org/I3130844761"]},{"raw_affiliation_string":"KAIST AI","institution_ids":["https://openalex.org/I4210099236","https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5091674853"],"corresponding_institution_ids":["https://openalex.org/I157485424","https://openalex.org/I3130844761","https://openalex.org/I4210099236"],"apc_list":null,"apc_paid":null,"fwci":13.2257,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":{"value":0.99118813,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5436","last_page":"5440"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12419","display_name":"Phonocardiography and Auscultation Techniques","score":0.9886000156402588,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T12419","display_name":"Phonocardiography and Auscultation Techniques","score":0.9886000156402588,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9753000140190125,"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/spectrogram","display_name":"Spectrogram","score":0.8495326042175293},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6466715931892395},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.595537543296814},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5314471125602722},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4754875898361206},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3131171464920044},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19308245182037354},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1068967878818512}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8495326042175293},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6466715931892395},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.595537543296814},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5314471125602722},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4754875898361206},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3131171464920044},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19308245182037354},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1068967878818512},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-1426","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/W1513801117","https://openalex.org/W2016016168","https://openalex.org/W2108598243","https://openalex.org/W2152536757","https://openalex.org/W2170748564","https://openalex.org/W2593116425","https://openalex.org/W2765407302","https://openalex.org/W2770896033","https://openalex.org/W2936774411","https://openalex.org/W2992308087","https://openalex.org/W2992420332","https://openalex.org/W3005680577","https://openalex.org/W3022944588","https://openalex.org/W3035524453","https://openalex.org/W3093423309","https://openalex.org/W3095616795","https://openalex.org/W3095921152","https://openalex.org/W3097359093","https://openalex.org/W3130328637","https://openalex.org/W3135818473","https://openalex.org/W3136810184","https://openalex.org/W3196974791","https://openalex.org/W3199069548","https://openalex.org/W3204056572","https://openalex.org/W3206996142","https://openalex.org/W4205232882","https://openalex.org/W4205773069","https://openalex.org/W4224917537","https://openalex.org/W4225915947","https://openalex.org/W4295508308","https://openalex.org/W4297841511","https://openalex.org/W4297841853","https://openalex.org/W4306705160","https://openalex.org/W4307786629","https://openalex.org/W4313118352"],"related_works":["https://openalex.org/W2973062255","https://openalex.org/W2897924318","https://openalex.org/W2138997758","https://openalex.org/W2766960583","https://openalex.org/W2065296656","https://openalex.org/W3195104037","https://openalex.org/W4301857073","https://openalex.org/W3133517635","https://openalex.org/W2395582662","https://openalex.org/W2351056281"],"abstract_inverted_index":{"Respiratory":[0],"sound":[1,75],"contains":[2],"crucial":[3],"information":[4],"for":[5],"the":[6,13,50,60,73,108,112,120,124],"early":[7],"diagnosis":[8],"of":[9,52,131],"fatal":[10],"lung":[11,41],"diseases.Since":[12],"COVID-19":[14],"pandemic,":[15],"there":[16],"has":[17],"been":[18,37],"a":[19,81,99],"growing":[20],"interest":[21],"in":[22,111],"contact-free":[23],"medical":[24,53],"care":[25],"based":[26],"on":[27,63,119],"electronic":[28],"stethoscopes.To":[29],"this":[30,55],"end,":[31],"cutting-edge":[32],"deep":[33],"learning":[34],"models":[35],"have":[36],"developed":[38],"to":[39,49,72,106],"diagnose":[40],"diseases;":[42],"however,":[43],"it":[44],"is":[45],"still":[46],"challenging":[47],"due":[48],"scarcity":[51],"data.In":[54],"study,":[56],"we":[57,79],"demonstrate":[58],"that":[59],"pretrained":[61],"model":[62],"large-scale":[64],"visual":[65],"and":[66,101],"audio":[67],"datasets":[68],"can":[69],"be":[70],"generalized":[71],"respiratory":[74],"classification":[76],"task.In":[77],"addition,":[78],"introduce":[80],"straightforward":[82],"Patch-Mix":[83,103],"augmentation,":[84],"which":[85],"randomly":[86],"mixes":[87],"patches":[88],"between":[89],"different":[90],"samples,":[91],"with":[92],"Audio":[93],"Spectrogram":[94],"Transformer":[95],"(AST).We":[96],"further":[97],"propose":[98],"novel":[100],"effective":[102],"Contrastive":[104],"Learning":[105],"distinguish":[107],"mixed":[109],"representations":[110],"latent":[113],"space.Our":[114],"method":[115],"achieves":[116],"state-of-the-art":[117],"performance":[118],"ICBHI":[121],"dataset,":[122],"outperforming":[123],"prior":[125],"leading":[126],"score":[127],"by":[128],"an":[129],"improvement":[130],"4.08%.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":30},{"year":2024,"cited_by_count":19}],"updated_date":"2026-07-09T07:52:08.696243","created_date":"2025-10-10T00:00:00"}
