{"id":"https://openalex.org/W4221163652","doi":"https://doi.org/10.1109/icassp43922.2022.9746205","title":"Supervised and Self-Supervised Pretraining Based Covid-19 Detection Using Acoustic Breathing/Cough/Speech Signals","display_name":"Supervised and Self-Supervised Pretraining Based Covid-19 Detection Using Acoustic Breathing/Cough/Speech Signals","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4221163652","doi":"https://doi.org/10.1109/icassp43922.2022.9746205"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746205","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746205","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2201.08934","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100387352","display_name":"Xingyu Chen","orcid":"https://orcid.org/0000-0002-9998-3443"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xing-Yu Chen","raw_affiliation_strings":["University of Science and Technology of China (USTC),NEL-SLIP,Hefei,China","NEL-SLIP, University of Science and Technology of China (USTC), Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),NEL-SLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NEL-SLIP, University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045966396","display_name":"Qiushi Zhu","orcid":"https://orcid.org/0000-0002-1196-7781"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiu-Shi Zhu","raw_affiliation_strings":["University of Science and Technology of China (USTC),NEL-SLIP,Hefei,China","NEL-SLIP, University of Science and Technology of China (USTC), Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),NEL-SLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NEL-SLIP, University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100436848","display_name":"Jie Zhang","orcid":"https://orcid.org/0000-0003-1124-0854"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhang","raw_affiliation_strings":["University of Science and Technology of China (USTC),NEL-SLIP,Hefei,China","NEL-SLIP, University of Science and Technology of China (USTC), Hefei, China","State Key Laboratory of Acoustics, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),NEL-SLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NEL-SLIP, University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"State Key Laboratory of Acoustics, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li-Rong Dai","raw_affiliation_strings":["University of Science and Technology of China (USTC),NEL-SLIP,Hefei,China","NEL-SLIP, University of Science and Technology of China (USTC), Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),NEL-SLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NEL-SLIP, University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100387352"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":3.7879,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.9704698,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"561","last_page":"565"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9983999729156494,"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"}},"topics":[{"id":"https://openalex.org/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9983999729156494,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9968000054359436,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9965000152587891,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8214646577835083},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7851245403289795},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6659339666366577},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6407859921455383},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5894403457641602},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5572896003723145},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5342103242874146},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5003376007080078},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49618297815322876},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4522373080253601},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4480658769607544}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8214646577835083},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7851245403289795},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6659339666366577},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6407859921455383},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5894403457641602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5572896003723145},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5342103242874146},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5003376007080078},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49618297815322876},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4522373080253601},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4480658769607544},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746205","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746205","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2201.08934","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2201.08934","pdf_url":"https://arxiv.org/pdf/2201.08934","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2201.08934","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2201.08934","pdf_url":"https://arxiv.org/pdf/2201.08934","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.8500000238418579,"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2064675550","https://openalex.org/W2547875792","https://openalex.org/W2842511635","https://openalex.org/W2933138175","https://openalex.org/W2936774411","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2979476256","https://openalex.org/W3028563376","https://openalex.org/W3035378948","https://openalex.org/W3036601975","https://openalex.org/W3081012644","https://openalex.org/W3091000562","https://openalex.org/W3100270690","https://openalex.org/W3109783949","https://openalex.org/W3125709657","https://openalex.org/W3127573699","https://openalex.org/W3131326546","https://openalex.org/W3152531055","https://openalex.org/W3166597180","https://openalex.org/W3195216351","https://openalex.org/W3196324719","https://openalex.org/W3196772091","https://openalex.org/W3196786467","https://openalex.org/W3196952172","https://openalex.org/W3197683356","https://openalex.org/W4287018967","https://openalex.org/W4297808394","https://openalex.org/W6631190155","https://openalex.org/W6729448088","https://openalex.org/W6769196770","https://openalex.org/W6777889263","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W1985458517","https://openalex.org/W2355833770","https://openalex.org/W3031039437","https://openalex.org/W4226466875","https://openalex.org/W2977257638","https://openalex.org/W4288095186","https://openalex.org/W3210541621","https://openalex.org/W4252379076"],"abstract_inverted_index":{"A":[0],"rapid-accurate":[1],"detection":[2,27,88,165],"method":[3,28,83,178],"for":[4,9,46,68,208],"COVID-19":[5,26],"is":[6,62,77,94,116,136,167,196,206],"rather":[7],"important":[8],"avoiding":[10],"its":[11],"pandemic.":[12],"In":[13],"this":[14],"work,":[15],"we":[16,101],"propose":[17],"a":[18,120],"bi-directional":[19],"long":[20],"short-term":[21],"memory":[22],"(BiLSTM)":[23],"network":[24,42],"based":[25,98,140],"using":[29,111,199],"breath/speech/cough":[30],"signals.":[31],"Three":[32],"kinds":[33],"of":[34,73,186],"acoustic":[35],"signals":[36],"are":[37,49,54,160],"taken":[38],"to":[39,56,118,127],"train":[40],"the":[41,66,69,87,112,124,144,149,170,192],"and":[43,108,157,173],"individual":[44],"models":[45],"three":[47,91],"tasks":[48],"built,":[50],"respectively,":[51],"whose":[52],"parameters":[53],"averaged":[55],"obtain":[57],"an":[58,81,103,180],"average":[59],"model,":[60],"which":[61,115],"then":[63],"used":[64],"as":[65,123],"initialization":[67,82],"BiLSTM":[70],"model":[71,107,125,166],"training":[72],"each":[74],"task.":[75],"It":[76,195],"shown":[78,197],"that":[79,176,198],"such":[80],"can":[84],"significantly":[85],"improve":[86],"performance":[89],"on":[90,169,188],"tasks.":[92],"This":[93,135],"called":[95,137],"supervised":[96],"pre-training":[97,139],"detection.":[99,141],"Besides,":[100],"utilize":[102],"existing":[104],"pre-trained":[105],"wav2vec2.0":[106],"pre-train":[109],"it":[110],"DiCOVA":[113,171],"dataset,":[114],"utilized":[117],"extract":[119],"high-level":[121,200],"representation":[122],"input":[126],"replace":[128],"conventional":[129],"mel-frequency":[130],"cepstral":[131],"coefficients":[132],"(MFCC)":[133],"features.":[134],"self-supervised":[138],"To":[142],"reduce":[143],"information":[145],"redundancy":[146],"contained":[147],"in":[148,191],"recorded":[150],"sounds,":[151],"silent":[152],"segment":[153],"removal,":[154],"amplitude":[155],"normalization":[156],"time-frequency":[158],"masking":[159],"also":[161],"considered.":[162],"The":[163],"proposed":[164],"evaluated":[168],"dataset":[172],"results":[174],"show":[175],"our":[177],"achieves":[179],"area":[181],"under":[182],"curve":[183],"(AUC)":[184],"score":[185],"88.44%":[187],"blind":[189],"test":[190],"fusion":[193],"track.":[194],"features":[201,205],"together":[202],"with":[203],"MFCC":[204],"helpful":[207],"diagnosing":[209],"accuracy.":[210]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":2}],"updated_date":"2026-03-24T08:02:53.985720","created_date":"2025-10-10T00:00:00"}