{"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":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"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":"INTERSPEECH 2023","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2305.14032","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112425608","display_name":"Sangmin Bae","orcid":null,"observed_orcids":[]},"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"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sangmin Bae","raw_affiliation_strings":["KAIST AI","MODULABS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST AI","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"MODULABS","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085336408","display_name":"June-Woo Kim","orcid":"https://orcid.org/0000-0003-0111-300X","observed_orcids":["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"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"June-Woo Kim","raw_affiliation_strings":["Department of AI, Kyungpook National University","MODULABS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of AI, Kyungpook National University","institution_ids":["https://openalex.org/I31419693"]},{"raw_affiliation_string":"MODULABS","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109692699","display_name":"Won-Yang Cho","orcid":"https://orcid.org/0000-0001-9225-4013","observed_orcids":["https://orcid.org/0000-0001-9225-4013"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Won-Yang Cho","raw_affiliation_strings":["MODULABS","SmartSound"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MODULABS","institution_ids":[]},{"raw_affiliation_string":"SmartSound","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109715198","display_name":"Hyerim Baek","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyerim Baek","raw_affiliation_strings":["MODULABS","SmartSound"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MODULABS","institution_ids":[]},{"raw_affiliation_string":"SmartSound","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101206792","display_name":"Soyoun Son","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Soyoun Son","raw_affiliation_strings":["MODULABS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MODULABS","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088555849","display_name":"Byungjo Lee","orcid":"https://orcid.org/0000-0002-1404-8246","observed_orcids":["https://orcid.org/0000-0002-1404-8246"]},"institutions":[{"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":["KR"],"is_corresponding":false,"raw_author_name":"Byungjo Lee","raw_affiliation_strings":["Dongguk University","MODULABS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dongguk University","institution_ids":["https://openalex.org/I205490536"]},{"raw_affiliation_string":"MODULABS","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Changwan Ha","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changwan Ha","raw_affiliation_strings":["MODULABS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MODULABS","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059669800","display_name":"Kyongpil Tae","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kyongpil Tae","raw_affiliation_strings":["MODULABS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MODULABS","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056038923","display_name":"Sungnyun Kim","orcid":null,"observed_orcids":[]},"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"]}],"countries":["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/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091674853","display_name":"Se-Young Yun","orcid":"https://orcid.org/0000-0001-6675-5113","observed_orcids":["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"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Se-Young Yun","raw_affiliation_strings":["KAIST AI","MODULABS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST AI","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"MODULABS","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5091674853"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":92.1863,"has_fulltext":true,"cited_by_count":68,"citation_normalized_percentile":{"value":0.99967877,"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":0.9994999766349792,"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":0.9994999766349792,"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":0.0003000000142492354,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/respiratory-sound-classification","display_name":"respiratory sound classification","score":0.9929999709129333},{"id":"https://openalex.org/keywords/contrastive-learning","display_name":"contrastive learning","score":0.984000027179718},{"id":"https://openalex.org/keywords/audio-spectrogram-transformer","display_name":"Audio Spectrogram Transformer","score":0.8960000276565552},{"id":"https://openalex.org/keywords/lung-disease-diagnosis","display_name":"lung disease diagnosis","score":0.6389999985694885},{"id":"https://openalex.org/keywords/electronic-stethoscope","display_name":"electronic stethoscope","score":0.8320000171661377},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.47600001096725464},{"id":"https://openalex.org/keywords/data-scarcity","display_name":"data scarcity","score":0.37400001287460327}],"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":3,"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":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"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":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2305.14032","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.14032","pdf_url":"https://arxiv.org/pdf/2305.14032","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2305.14032","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2305.14032","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2305.14032","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.14032","pdf_url":"https://arxiv.org/pdf/2305.14032","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3","score":0.6240000128746033}],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1346884545","display_name":null,"funder_award_id":"IITP-2023-2020-0-01808","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G1769687045","display_name":null,"funder_award_id":"2019-0-00075","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G2148870006","display_name":null,"funder_award_id":"2019-0-00075","funder_id":"https://openalex.org/F4320324161","funder_display_name":"Korea Advanced Institute of Science and Technology"},{"id":"https://openalex.org/G4021044050","display_name":null,"funder_award_id":"2022-0-00641","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G4700831490","display_name":null,"funder_award_id":"2022-","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G5204723964","display_name":null,"funder_award_id":"2022-0-00641","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G5415505637","display_name":null,"funder_award_id":"2019-0-00075","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G6776584021","display_name":null,"funder_award_id":"2019-0-00075","funder_id":"https://openalex.org/F4320324891","funder_display_name":"Iran Telecommunication Research Center"},{"id":"https://openalex.org/G7555590354","display_name":null,"funder_award_id":"2020-0-01808","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320324161","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63"},{"id":"https://openalex.org/F4320324891","display_name":"Iran Telecommunication Research Center","ror":"https://ror.org/01a3g2z22"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385822870.pdf","grobid_xml":"https://content.openalex.org/works/W4385822870.grobid-xml"},"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/W3032968349","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/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":[1,78],"contains":[2],"crucial":[3],"information":[4],"for":[5],"the":[6,14,52,63,76,113,117,126,130],"early":[7],"diagnosis":[8],"of":[9,54,137],"fatal":[10],"lung":[11,43],"diseases.":[12],"Since":[13],"COVID-19":[15],"pandemic,":[16],"there":[17],"has":[18],"been":[19,39],"a":[20,85,104],"growing":[21],"interest":[22],"in":[23,116],"contact-free":[24],"medical":[25,55],"care":[26],"based":[27],"on":[28,66,125],"electronic":[29],"stethoscopes.":[30],"To":[31],"this":[32,58],"end,":[33],"cutting-edge":[34],"deep":[35],"learning":[36],"models":[37],"have":[38],"developed":[40],"to":[41,51,75,111],"diagnose":[42],"diseases;":[44],"however,":[45],"it":[46],"is":[47],"still":[48],"challenging":[49],"due":[50],"scarcity":[53],"data.":[56],"In":[57,81],"study,":[59],"we":[60,83],"demonstrate":[61],"that":[62],"pretrained":[64],"model":[65],"large-scale":[67],"visual":[68],"and":[69,106],"audio":[70],"datasets":[71],"can":[72],"be":[73],"generalized":[74],"respiratory":[77],"classification":[79],"task.":[80],"addition,":[82],"introduce":[84],"straightforward":[86],"Patch-Mix":[87,108],"augmentation,":[88],"which":[89],"randomly":[90],"mixes":[91],"patches":[92],"between":[93],"different":[94],"samples,":[95],"with":[96],"Audio":[97],"Spectrogram":[98],"Transformer":[99],"(AST).":[100],"We":[101],"further":[102],"propose":[103],"novel":[105],"effective":[107],"Contrastive":[109],"Learning":[110],"distinguish":[112],"mixed":[114],"representations":[115],"latent":[118],"space.":[119],"Our":[120],"method":[121],"achieves":[122],"state-of-the-art":[123],"performance":[124],"ICBHI":[127],"dataset,":[128],"outperforming":[129],"prior":[131],"leading":[132],"score":[133],"by":[134],"an":[135],"improvement":[136],"4.08%.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":16},{"year":2025,"cited_by_count":32},{"year":2024,"cited_by_count":20}],"updated_date":"2026-10-07T09:51:55.459714","created_date":"2025-10-10T00:00:00"}
