{"id":"https://openalex.org/W4389474444","doi":"https://doi.org/10.1109/mmsp59012.2023.10337717","title":"An Inception-Residual-Based Architecture with Multi-Objective Loss for Detecting Respiratory Anomalies","display_name":"An Inception-Residual-Based Architecture with Multi-Objective Loss for Detecting Respiratory Anomalies","publication_year":2023,"publication_date":"2023-09-27","ids":{"openalex":"https://openalex.org/W4389474444","doi":"https://doi.org/10.1109/mmsp59012.2023.10337717"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp59012.2023.10337717","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp59012.2023.10337717","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 25th International Workshop on Multimedia Signal Processing (MMSP)","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/A5102968151","display_name":"Dat Ngo","orcid":"https://orcid.org/0000-0003-4374-5056"},"institutions":[{"id":"https://openalex.org/I110002522","display_name":"University of Essex","ror":"https://ror.org/02nkf1q06","country_code":"GB","type":"education","lineage":["https://openalex.org/I110002522"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Dat Ngo","raw_affiliation_strings":["School of Computer Science and Electronic Engineering, University of Essex,UK","School of Computer Science and Electronic Engineering, University of Essex, UK"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Electronic Engineering, University of Essex,UK","institution_ids":["https://openalex.org/I110002522"]},{"raw_affiliation_string":"School of Computer Science and Electronic Engineering, University of Essex, UK","institution_ids":["https://openalex.org/I110002522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075250567","display_name":"Lam Pham","orcid":"https://orcid.org/0000-0001-8155-7553"},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Lam Pham","raw_affiliation_strings":["Austrian Institute of Technology,Center for Digital Safety & Security,Austria"],"affiliations":[{"raw_affiliation_string":"Austrian Institute of Technology,Center for Digital Safety & Security,Austria","institution_ids":["https://openalex.org/I132118926"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027304029","display_name":"Huy P. Phan","orcid":"https://orcid.org/0000-0002-3066-4647"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huy Phan","raw_affiliation_strings":["Amazon Alexa,Cambridge,MA,US","Amazon Alexa, Cambridge, MA, US"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa,Cambridge,MA,US","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa, Cambridge, MA, US","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101612317","display_name":"Minh Tr\u1ea7n","orcid":"https://orcid.org/0000-0003-4637-6081"},"institutions":[{"id":"https://openalex.org/I2801809904","display_name":"Nuffield Orthopaedic Centre","ror":"https://ror.org/0036ate90","country_code":"GB","type":"healthcare","lineage":["https://openalex.org/I2801809904","https://openalex.org/I4210147381"]},{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Minh Tran","raw_affiliation_strings":["University of Oxford,Nuffield Department of Clinical Neurosciences,UK","Nuffield Department of Clinical Neurosciences, University of Oxford, UK"],"affiliations":[{"raw_affiliation_string":"University of Oxford,Nuffield Department of Clinical Neurosciences,UK","institution_ids":["https://openalex.org/I2801809904","https://openalex.org/I40120149"]},{"raw_affiliation_string":"Nuffield Department of Clinical Neurosciences, University of Oxford, UK","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086705584","display_name":"Delaram Jarchi","orcid":"https://orcid.org/0000-0001-6699-8721"},"institutions":[{"id":"https://openalex.org/I110002522","display_name":"University of Essex","ror":"https://ror.org/02nkf1q06","country_code":"GB","type":"education","lineage":["https://openalex.org/I110002522"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Delaram Jarchi","raw_affiliation_strings":["School of Computer Science and Electronic Engineering, University of Essex,UK","School of Computer Science and Electronic Engineering, University of Essex, UK"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Electronic Engineering, University of Essex,UK","institution_ids":["https://openalex.org/I110002522"]},{"raw_affiliation_string":"School of Computer Science and Electronic Engineering, University of Essex, UK","institution_ids":["https://openalex.org/I110002522"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057663485","display_name":"\u015eefki Kolozali","orcid":"https://orcid.org/0000-0001-9920-1299"},"institutions":[{"id":"https://openalex.org/I110002522","display_name":"University of Essex","ror":"https://ror.org/02nkf1q06","country_code":"GB","type":"education","lineage":["https://openalex.org/I110002522"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"\u015eefki Kolozali","raw_affiliation_strings":["School of Computer Science and Electronic Engineering, University of Essex,UK","School of Computer Science and Electronic Engineering, University of Essex, UK"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Electronic Engineering, University of Essex,UK","institution_ids":["https://openalex.org/I110002522"]},{"raw_affiliation_string":"School of Computer Science and Electronic Engineering, University of Essex, UK","institution_ids":["https://openalex.org/I110002522"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102968151"],"corresponding_institution_ids":["https://openalex.org/I110002522"],"apc_list":null,"apc_paid":null,"fwci":2.1332,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.88622513,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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/T12418","display_name":"Respiratory and Cough-Related Research","score":0.9966999888420105,"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":0.9921000003814697,"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":0.855765700340271},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7168489098548889},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6181026101112366},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6105675101280212},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6015320420265198},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5876502990722656},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.549800455570221},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.5415738821029663},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5254660844802856},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48726168274879456},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.48152026534080505},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11483106017112732},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11219960451126099},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10893523693084717}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.855765700340271},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7168489098548889},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6181026101112366},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6105675101280212},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6015320420265198},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5876502990722656},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.549800455570221},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.5415738821029663},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5254660844802856},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48726168274879456},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.48152026534080505},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11483106017112732},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11219960451126099},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10893523693084717},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp59012.2023.10337717","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp59012.2023.10337717","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 25th International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2019560659","https://openalex.org/W2097117768","https://openalex.org/W2157364932","https://openalex.org/W2768188490","https://openalex.org/W2781186372","https://openalex.org/W2899493363","https://openalex.org/W2936774411","https://openalex.org/W2964439653","https://openalex.org/W3003965947","https://openalex.org/W3135818473","https://openalex.org/W3152792492","https://openalex.org/W3161473931","https://openalex.org/W3188566655","https://openalex.org/W4200420926","https://openalex.org/W4221140096","https://openalex.org/W4225915947","https://openalex.org/W4283726207","https://openalex.org/W4294891479","https://openalex.org/W4309242623","https://openalex.org/W4309263216","https://openalex.org/W4309270060","https://openalex.org/W4312886255","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6745930336","https://openalex.org/W6810295955","https://openalex.org/W6839321029"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2373577936","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W2337753992","https://openalex.org/W4283754361"],"abstract_inverted_index":{"This":[0,29],"paper":[1],"presents":[2],"a":[3,39,72,84],"deep":[4],"learning":[5],"system":[6,17,53,147],"applied":[7],"for":[8],"detecting":[9],"anomalies":[10],"from":[11,79],"respiratory":[12,35,67],"sound":[13,36],"recordings.":[14],"Initially,":[15],"our":[16,51,145],"begins":[18],"with":[19,59,186],"audio":[20],"feature":[21],"extraction":[22],"using":[23],"Gammatone":[24],"and":[25,45,62,142,155,164,183,192],"Continuous":[26],"Wavelet":[27],"transformation.":[28],"step":[30],"aims":[31],"to":[32,65,91,169],"transform":[33],"the":[34,89,94,101,106,112,125,132,139,170,177,187],"input":[37],"into":[38],"two-dimensional":[40],"spectrogram":[41,99],"where":[42],"both":[43],"spectral":[44],"temporal":[46],"features":[47],"are":[48],"presented.":[49],"Then,":[50],"proposed":[52,123,146],"integrates":[54],"Inception-residual-based":[55],"backbone":[56],"models":[57],"combined":[58],"multi-head":[60],"attention":[61],"multi-objective":[63],"loss":[64],"classify":[66],"anomalies.":[68],"Instead":[69],"of":[70,96,115,151,190],"applying":[71],"simple":[73],"concatenation":[74],"approach":[75],"by":[76,124,135],"combining":[77],"results":[78],"various":[80],"spectrograms,":[81],"we":[82,108,175],"propose":[83],"linear":[85],"combination,":[86],"which":[87],"has":[88],"ability":[90],"regulate":[92],"equally":[93],"contribution":[95],"each":[97],"individual":[98],"throughout":[100],"training":[102],"process.":[103],"To":[104],"evaluate":[105],"performance,":[107],"conducted":[109],"experiments":[110],"over":[111],"benchmark":[113],"dataset":[114],"SPRSound":[116],"(The":[117],"Open-Source":[118],"SJTU":[119],"Paediatric":[120],"Respiratory":[121],"Sound)":[122],"IEEE":[126],"BioCAS":[127],"2022":[128],"challenge.":[129],"As":[130],"regards":[131],"Score":[133,189],"computed":[134],"an":[136],"average":[137,140],"between":[138],"score":[141],"harmonic":[143],"score,":[144],"gained":[148],"significant":[149],"improvements":[150],"9.7%,":[152],"15.8%,":[153],"17.8%,":[154],"16.1%":[156],"in":[157,180],"Task":[158,160,162,165,181,184],"1\u20131,":[159],"1\u20132,":[161],"2\u20131,":[163],"2\u20132,":[166],"respectively,":[167],"compared":[168],"challenge":[171],"baseline":[172],"system.":[173],"Notably,":[174],"achieved":[176],"Top-1":[178],"performance":[179],"2\u20131":[182],"2\u20132":[185],"highest":[188],"74.5%":[191],"53.9%,":[193],"respectively.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}