{"id":"https://openalex.org/W4414897299","doi":"https://doi.org/10.1145/3715071.3750404","title":"CoughViT: A Self-Supervised Vision Transformer for Cough Audio Representation Learning","display_name":"CoughViT: A Self-Supervised Vision Transformer for Cough Audio Representation Learning","publication_year":2025,"publication_date":"2025-10-07","ids":{"openalex":"https://openalex.org/W4414897299","doi":"https://doi.org/10.1145/3715071.3750404"},"language":"en","primary_location":{"id":"doi:10.1145/3715071.3750404","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3715071.3750404","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3715071.3750404","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM International Symposium on Wearable Computers","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3715071.3750404","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043611464","display_name":"Justin C. Luong","orcid":"https://orcid.org/0000-0003-2118-4788"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Justin Luong","raw_affiliation_strings":["University of New South Wales, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000564739","display_name":"Hao Xue","orcid":"https://orcid.org/0000-0003-1700-9215"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hao Xue","raw_affiliation_strings":["University of New South Wales, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0003-1700-9215","affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090893421","display_name":"Flora D. Salim","orcid":"https://orcid.org/0000-0002-1237-1664"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Flora D. Salim","raw_affiliation_strings":["School of Computer Science and Engineering, University of New South Wales, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-1237-1664","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of New South Wales, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I31746571"],"apc_list":null,"apc_paid":null,"fwci":8.0725,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.96009577,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"45","last_page":"52"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12418","display_name":"Respiratory and Cough-Related Research","score":0.9987000226974487,"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/T12418","display_name":"Respiratory and Cough-Related Research","score":0.9987000226974487,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9926000237464905,"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/T10860","display_name":"Speech and Audio Processing","score":0.9824000000953674,"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/feature-learning","display_name":"Feature learning","score":0.508400022983551},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.4634000062942505},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.3970000147819519},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.3896999955177307},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3594000041484833},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3549000024795532},{"id":"https://openalex.org/keywords/respiratory-sounds","display_name":"Respiratory sounds","score":0.34850001335144043}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6621000170707703},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.508400022983551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48840001225471497},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4634000062942505},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45719999074935913},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.423799991607666},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3970000147819519},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3896999955177307},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3594000041484833},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C2777402568","wikidata":"https://www.wikidata.org/wiki/Q779038","display_name":"Respiratory sounds","level":3,"score":0.34850001335144043},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2842000126838684},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.27250000834465027},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2644999921321869},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C163985040","wikidata":"https://www.wikidata.org/wiki/Q1172399","display_name":"Data acquisition","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3715071.3750404","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3715071.3750404","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3715071.3750404","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM International Symposium on Wearable Computers","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3715071.3750404","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3715071.3750404","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3715071.3750404","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM International Symposium on Wearable Computers","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2935801862","display_name":"ARC Centre of Excellence for Automated Decision-Making and Society","funder_award_id":"CE200100005","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"},{"id":"https://openalex.org/G6648413181","display_name":"Collaborative Research: NSF-CSIRO: HCC: Small: Understanding Bias in AI Models for the Prediction of Infectious Disease Spread","funder_award_id":"2302970","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7969191702","display_name":"Collaborative Research: NSF-CSIRO: HCC: Small: Understanding Bias in AI Models for the Prediction of Infectious Disease Spread","funder_award_id":"2302969","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320312169","display_name":"National Computational Infrastructure","ror":"https://ror.org/04yx6dh41"},{"id":"https://openalex.org/F4320320386","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414897299.pdf","grobid_xml":"https://content.openalex.org/works/W4414897299.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W829541538","https://openalex.org/W1494198834","https://openalex.org/W1513801117","https://openalex.org/W1924943994","https://openalex.org/W2009481975","https://openalex.org/W2119036316","https://openalex.org/W2593116425","https://openalex.org/W2931364255","https://openalex.org/W2948751094","https://openalex.org/W2968272386","https://openalex.org/W2979298088","https://openalex.org/W2982127621","https://openalex.org/W2982223350","https://openalex.org/W3016719260","https://openalex.org/W3046375318","https://openalex.org/W3088067841","https://openalex.org/W3089168043","https://openalex.org/W3109783949","https://openalex.org/W3138516171","https://openalex.org/W3163384138","https://openalex.org/W3175291108","https://openalex.org/W3175510762","https://openalex.org/W3185939438","https://openalex.org/W3185940864","https://openalex.org/W3198126430","https://openalex.org/W3205790296","https://openalex.org/W3206996142","https://openalex.org/W4210729464","https://openalex.org/W4221099308","https://openalex.org/W4225288540","https://openalex.org/W4285483774","https://openalex.org/W4297841558","https://openalex.org/W4313156423","https://openalex.org/W4316923454","https://openalex.org/W4385647277","https://openalex.org/W4389542817"],"related_works":[],"abstract_inverted_index":{"Physicians":[0],"routinely":[1],"assess":[2],"respiratory":[3,26,32],"sounds":[4],"during":[5],"the":[6,12],"diagnostic":[7,22,66,89],"process,":[8],"providing":[9],"insight":[10],"into":[11],"condition":[13],"of":[14],"a":[15,38,77,107,111],"patient's":[16],"airways.":[17],"In":[18,71],"recent":[19],"years,":[20],"AI-based":[21],"systems":[23,36],"operating":[24],"on":[25,123,147],"sounds,":[27],"have":[28],"demonstrated":[29],"success":[30],"in":[31,41,91,110,144],"disease":[33],"detection.":[34],"These":[35],"represent":[37],"crucial":[39],"advancement":[40],"early":[42],"and":[43,54,68],"accessible":[44],"diagnosis":[45],"which":[46],"is":[47],"essential":[48],"for":[49,61,81],"timely":[50],"treatment.":[51],"However,":[52],"label":[53,98],"data":[55,103],"scarcity":[56],"remain":[57],"key":[58],"challenges,":[59],"especially":[60],"conditions":[62],"beyond":[63],"COVID-19,":[64],"limiting":[65],"performance":[67,90,146],"reliable":[69],"evaluation.":[70],"this":[72],"paper,":[73],"we":[74,100],"propose":[75],"CoughViT,":[76],"novel":[78],"pre-training":[79,121],"framework":[80],"learning":[82,113],"general-purpose":[83],"cough":[84,127],"sound":[85],"representations,":[86],"to":[87,105],"enhance":[88],"tasks":[92],"with":[93],"limited":[94],"data.":[95],"To":[96],"address":[97],"scarcity,":[99],"employ":[101],"masked":[102],"modelling":[104],"train":[106],"feature":[108],"encoder":[109],"self-supervised":[112],"manner.":[114],"We":[115],"evaluate":[116],"our":[117,134],"approach":[118],"against":[119],"other":[120],"strategies":[122],"three":[124],"diagnostically":[125],"important":[126],"classification":[128],"tasks.":[129,149],"Experimental":[130],"results":[131],"show":[132],"that":[133],"representations":[135,143],"match":[136],"or":[137],"exceed":[138],"current":[139],"state-of-the-art":[140],"supervised":[141],"audio":[142],"enhancing":[145],"downstream":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}