{"id":"https://openalex.org/W4405488784","doi":"https://doi.org/10.1109/embc53108.2024.10782479","title":"Exploring Pre-trained General-purpose Audio Representations for Heart Murmur Detection","display_name":"Exploring Pre-trained General-purpose Audio Representations for Heart Murmur Detection","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4405488784","doi":"https://doi.org/10.1109/embc53108.2024.10782479","pmid":"https://pubmed.ncbi.nlm.nih.gov/40039556"},"language":"en","primary_location":{"id":"doi:10.1109/embc53108.2024.10782479","is_oa":false,"landing_page_url":"https://doi.org/10.1109/embc53108.2024.10782479","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","pubmed"],"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/A5091219538","display_name":"Daisuke Niizumi","orcid":"https://orcid.org/0000-0002-5063-0508"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daisuke Niizumi","raw_affiliation_strings":["Nippon Telegraph and Telephone Corporation,Communication Science Laboratories,Atsugi,Japan,243-0198"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nippon Telegraph and Telephone Corporation,Communication Science Laboratories,Atsugi,Japan,243-0198","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103978078","display_name":"Daiki Takeuchi","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daiki Takeuchi","raw_affiliation_strings":["Nippon Telegraph and Telephone Corporation,Communication Science Laboratories,Atsugi,Japan,243-0198"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nippon Telegraph and Telephone Corporation,Communication Science Laboratories,Atsugi,Japan,243-0198","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062509967","display_name":"Yasunori Ohishi","orcid":"https://orcid.org/0000-0002-7856-248X"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasunori Ohishi","raw_affiliation_strings":["Nippon Telegraph and Telephone Corporation,Communication Science Laboratories,Atsugi,Japan,243-0198"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nippon Telegraph and Telephone Corporation,Communication Science Laboratories,Atsugi,Japan,243-0198","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054467679","display_name":"Noboru Harada","orcid":"https://orcid.org/0000-0002-1759-4533"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Noboru Harada","raw_affiliation_strings":["Nippon Telegraph and Telephone Corporation,Communication Science Laboratories,Atsugi,Japan,243-0198"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nippon Telegraph and Telephone Corporation,Communication Science Laboratories,Atsugi,Japan,243-0198","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061465935","display_name":"Kunio Kashino","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kunio Kashino","raw_affiliation_strings":["Nippon Telegraph and Telephone Corporation,Communication Science Laboratories,Atsugi,Japan,243-0198"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nippon Telegraph and Telephone Corporation,Communication Science Laboratories,Atsugi,Japan,243-0198","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":3.0512,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.93286471,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"2024","issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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/T12419","display_name":"Phonocardiography and Auscultation Techniques","score":0.9984999895095825,"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/T10860","display_name":"Speech and Audio Processing","score":0.9979000091552734,"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/computer-science","display_name":"Computer science","score":0.629447877407074},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4816419184207916},{"id":"https://openalex.org/keywords/heart-murmur","display_name":"Heart murmur","score":0.4122958183288574},{"id":"https://openalex.org/keywords/cardiology","display_name":"Cardiology","score":0.12189921736717224},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.0936788022518158}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.629447877407074},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4816419184207916},{"id":"https://openalex.org/C2780379053","wikidata":"https://www.wikidata.org/wiki/Q1060911","display_name":"Heart murmur","level":2,"score":0.4122958183288574},{"id":"https://openalex.org/C164705383","wikidata":"https://www.wikidata.org/wiki/Q10379","display_name":"Cardiology","level":1,"score":0.12189921736717224},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0936788022518158}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006326","descriptor_name":"Heart Auscultation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D006326","descriptor_name":"Heart Auscultation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D006326","descriptor_name":"Heart Auscultation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D006337","descriptor_name":"Heart Murmurs","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":true},{"descriptor_ui":"D006337","descriptor_name":"Heart Murmurs","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":true},{"descriptor_ui":"D006337","descriptor_name":"Heart Murmurs","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":true},{"descriptor_ui":"D006337","descriptor_name":"Heart Murmurs","qualifier_ui":"Q000503","qualifier_name":"physiopathology","is_major_topic":true},{"descriptor_ui":"D006347","descriptor_name":"Heart Sounds","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006347","descriptor_name":"Heart Sounds","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006347","descriptor_name":"Heart Sounds","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012815","descriptor_name":"Signal Processing, Computer-Assisted","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012815","descriptor_name":"Signal Processing, Computer-Assisted","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012815","descriptor_name":"Signal Processing, Computer-Assisted","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/embc53108.2024.10782479","is_oa":false,"landing_page_url":"https://doi.org/10.1109/embc53108.2024.10782479","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)","raw_type":"proceedings-article"},{"id":"pmid:40039556","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40039556","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1501669607","https://openalex.org/W2593116425","https://openalex.org/W2936774411","https://openalex.org/W3082319384","https://openalex.org/W3094550259","https://openalex.org/W3162391496","https://openalex.org/W3191193899","https://openalex.org/W3196974791","https://openalex.org/W3201143670","https://openalex.org/W4205561942","https://openalex.org/W4213019189","https://openalex.org/W4310873011","https://openalex.org/W4323027401","https://openalex.org/W4323027434","https://openalex.org/W4372341324","https://openalex.org/W4386615065","https://openalex.org/W4386838249","https://openalex.org/W4388118620","https://openalex.org/W4400526340","https://openalex.org/W6780218876","https://openalex.org/W6856586576","https://openalex.org/W6910936539"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"To":[0],"reduce":[1],"the":[2,24,32,35,48,66,85,93,105,134,146],"need":[3],"for":[4,26,29,53,76,148],"skilled":[5],"clinicians":[6],"in":[7,79,140],"heart":[8,36,80,88,142],"sound":[9,37,89],"interpretation,":[10],"recent":[11,94],"studies":[12],"on":[13,73,84],"automating":[14],"cardiac":[15],"auscultation":[16],"have":[17],"explored":[18],"deep":[19,30],"learning":[20,78,96],"approaches.":[21],"However,":[22],"despite":[23],"demands":[25],"large":[27],"data":[28],"learning,":[31],"size":[33],"of":[34,68,107,111,118,136],"datasets":[38,75],"is":[39,45],"limited,":[40],"and":[41,113,144],"no":[42],"pre-trained":[43,51,72],"model":[44],"available.":[46],"On":[47],"contrary,":[49],"many":[50],"models":[52],"general":[54],"audio":[55,61,70,138],"tasks":[56],"are":[57],"available":[58],"as":[59],"general-purpose":[60,69,137],"representations.":[62],"This":[63],"study":[64],"explores":[65],"potential":[67],"representations":[71],"large-scale":[74],"transfer":[77],"murmur":[81],"detection.":[82],"Experiments":[83,120],"CirCor":[86],"DigiScope":[87],"dataset":[90],"show":[91],"that":[92],"self-supervised":[95],"Masked":[97],"Modeling":[98],"Duo":[99],"(M2D)":[100],"outperforms":[101],"previous":[102],"methods":[103],"with":[104,128],"results":[106,132],"a":[108],"weighted":[109],"accuracy":[110],"0.832":[112],"an":[114],"unweighted":[115],"average":[116],"recall":[117],"0.713.":[119],"further":[121,149],"confirm":[122],"improved":[123],"performance":[124],"by":[125],"ensembling":[126],"M2D":[127],"other":[129],"models.":[130],"These":[131],"demonstrate":[133],"effectiveness":[135],"representation":[139],"processing":[141],"sounds":[143],"open":[145],"way":[147],"applications1.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6}],"updated_date":"2026-08-31T07:19:18.363097","created_date":"2025-10-10T00:00:00"}
