{"id":"https://openalex.org/W4200271458","doi":"https://doi.org/10.5753/stil.2021.17793","title":"Audio MFCC-gram Transformers for respiratory insufficiency detection in COVID-19","display_name":"Audio MFCC-gram Transformers for respiratory insufficiency detection in COVID-19","publication_year":2021,"publication_date":"2021-11-29","ids":{"openalex":"https://openalex.org/W4200271458","doi":"https://doi.org/10.5753/stil.2021.17793"},"language":"en","primary_location":{"id":"doi:10.5753/stil.2021.17793","is_oa":true,"landing_page_url":"https://doi.org/10.5753/stil.2021.17793","pdf_url":"https://sol.sbc.org.br/index.php/stil/article/download/17793/17627","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Anais do XIII Simp\u00f3sio Brasileiro de Tecnologia da Informa\u00e7\u00e3o e da Linguagem Humana (STIL 2021)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://sol.sbc.org.br/index.php/stil/article/download/17793/17627","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084920198","display_name":"Marcelo Matheus Gauy","orcid":"https://orcid.org/0000-0001-8902-0435"},"institutions":[{"id":"https://openalex.org/I4210131481","display_name":"Universidad San Pedro","ror":"https://ror.org/03fehwj53","country_code":"PE","type":"education","lineage":["https://openalex.org/I4210131481"]},{"id":"https://openalex.org/I4210131883","display_name":"Brazilian Society of Computational and Applied Mathematics","ror":"https://ror.org/03kcw4w74","country_code":"BR","type":"other","lineage":["https://openalex.org/I4210131883"]},{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR","PE"],"is_corresponding":true,"raw_author_name":"Marcelo Matheus Gauy","raw_affiliation_strings":["USP","Instituto de Matem\u00e1tica e Estat\u00edstica -Universidade de S\u00e3o Paulo (USP)"],"affiliations":[{"raw_affiliation_string":"USP","institution_ids":["https://openalex.org/I4210131481"]},{"raw_affiliation_string":"Instituto de Matem\u00e1tica e Estat\u00edstica -Universidade de S\u00e3o Paulo (USP)","institution_ids":["https://openalex.org/I4210131883","https://openalex.org/I17974374"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024395125","display_name":"Marcelo Finger","orcid":"https://orcid.org/0000-0002-1391-1175"},"institutions":[{"id":"https://openalex.org/I4210131883","display_name":"Brazilian Society of Computational and Applied Mathematics","ror":"https://ror.org/03kcw4w74","country_code":"BR","type":"other","lineage":["https://openalex.org/I4210131883"]},{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]},{"id":"https://openalex.org/I4210131481","display_name":"Universidad San Pedro","ror":"https://ror.org/03fehwj53","country_code":"PE","type":"education","lineage":["https://openalex.org/I4210131481"]}],"countries":["BR","PE"],"is_corresponding":false,"raw_author_name":"Marcelo Finger","raw_affiliation_strings":["USP","Instituto de Matem\u00e1tica e Estat\u00edstica -Universidade de S\u00e3o Paulo (USP)"],"affiliations":[{"raw_affiliation_string":"USP","institution_ids":["https://openalex.org/I4210131481"]},{"raw_affiliation_string":"Instituto de Matem\u00e1tica e Estat\u00edstica -Universidade de S\u00e3o Paulo (USP)","institution_ids":["https://openalex.org/I4210131883","https://openalex.org/I17974374"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5084920198"],"corresponding_institution_ids":["https://openalex.org/I17974374","https://openalex.org/I4210131481","https://openalex.org/I4210131883"],"apc_list":null,"apc_paid":null,"fwci":0.42,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.70771819,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"143","last_page":"152"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9426000118255615,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9426000118255615,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9395999908447266,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9279000163078308,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6950943470001221},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6553224325180054},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6180895566940308},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5257083773612976},{"id":"https://openalex.org/keywords/respiratory-sounds","display_name":"Respiratory sounds","score":0.5209152102470398},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5089783668518066},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5038339495658875},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4732763469219208},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4081670939922333},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3497534990310669},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.18973785638809204},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14727026224136353},{"id":"https://openalex.org/keywords/internal-medicine","display_name":"Internal medicine","score":0.09434634447097778},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08067977428436279}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6950943470001221},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6553224325180054},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6180895566940308},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5257083773612976},{"id":"https://openalex.org/C2777402568","wikidata":"https://www.wikidata.org/wiki/Q779038","display_name":"Respiratory sounds","level":3,"score":0.5209152102470398},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5089783668518066},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5038339495658875},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4732763469219208},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4081670939922333},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3497534990310669},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.18973785638809204},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14727026224136353},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.09434634447097778},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08067977428436279},{"id":"https://openalex.org/C2776042228","wikidata":"https://www.wikidata.org/wiki/Q35869","display_name":"Asthma","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5753/stil.2021.17793","is_oa":true,"landing_page_url":"https://doi.org/10.5753/stil.2021.17793","pdf_url":"https://sol.sbc.org.br/index.php/stil/article/download/17793/17627","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Anais do XIII Simp\u00f3sio Brasileiro de Tecnologia da Informa\u00e7\u00e3o e da Linguagem Humana (STIL 2021)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2210.14085","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.14085","pdf_url":"https://arxiv.org/pdf/2210.14085","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":"doi:10.5753/stil.2021.17793","is_oa":true,"landing_page_url":"https://doi.org/10.5753/stil.2021.17793","pdf_url":"https://sol.sbc.org.br/index.php/stil/article/download/17793/17627","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Anais do XIII Simp\u00f3sio Brasileiro de Tecnologia da Informa\u00e7\u00e3o e da Linguagem Humana (STIL 2021)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320997","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","ror":"https://ror.org/02ddkpn78"},{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4200271458.pdf","grobid_xml":"https://content.openalex.org/works/W4200271458.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W114762147","https://openalex.org/W2028045978","https://openalex.org/W2270070752","https://openalex.org/W2896457183","https://openalex.org/W2900484088","https://openalex.org/W2939692598","https://openalex.org/W2950813464","https://openalex.org/W2970597249","https://openalex.org/W2972451902","https://openalex.org/W2973049979","https://openalex.org/W2979476256","https://openalex.org/W2982223350","https://openalex.org/W3035079953","https://openalex.org/W3036601975","https://openalex.org/W3041561163","https://openalex.org/W3089168043","https://openalex.org/W3091468319","https://openalex.org/W3096485810","https://openalex.org/W3108822321","https://openalex.org/W3174751856","https://openalex.org/W3196974791","https://openalex.org/W4385245566","https://openalex.org/W4394666973","https://openalex.org/W6600721412","https://openalex.org/W6657822989","https://openalex.org/W6739901393","https://openalex.org/W6784202175"],"related_works":["https://openalex.org/W2349769824","https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W4293232884","https://openalex.org/W2422472940","https://openalex.org/W2019475500","https://openalex.org/W2548162870","https://openalex.org/W2144773493","https://openalex.org/W2138847091","https://openalex.org/W2916890284"],"abstract_inverted_index":{"This":[0,74],"work":[1,20],"explores":[2],"speech":[3,17],"as":[4],"a":[5,26,40,90],"biomarker":[6],"and":[7,34],"investigates":[8],"the":[9,50,69,84],"detection":[10],"of":[11,28,39,47,78,99],"respiratory":[12,29],"insufficiency":[13,30],"(RI)":[14],"by":[15,37],"analyzing":[16],"samples.":[18],"Previous":[19],"[Casanova":[21],"et":[22],"al.":[23],"2021]":[24],"constructed":[25],"dataset":[27],"COVID-19":[31],"patient":[32],"utterances":[33],"analyzed":[35],"it":[36],"means":[38],"convolutional":[41],"neural":[42,64],"network":[43,65],"achieving":[44],"an":[45,79],"accuracy":[46],"87.04%,":[48],"validating":[49],"hypothesis":[51],"that":[52],"one":[53],"can":[54,67],"detect":[55],"RI":[56,72,102],"through":[57],"speech.":[58],"Here,":[59],"we":[60,88],"study":[61],"how":[62],"Transformer":[63],"architectures":[66],"improve":[68],"performance":[70,97],"on":[71],"detection.":[73,103],"approach":[75],"enables":[76],"construction":[77],"acoustic":[80,92],"model.":[81],"By":[82],"choosing":[83],"correct":[85],"pretraining":[86],"technique,":[87],"generate":[89],"self-supervised":[91],"model,":[93],"leading":[94],"to":[95],"improved":[96],"(96.53%)":[98],"Transformers":[100],"for":[101]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2021-12-31T00:00:00"}