{"id":"https://openalex.org/W4229071437","doi":"https://doi.org/10.1109/jbhi.2022.3173128","title":"Capturing Time Dynamics From Speech Using Neural Networks for Surgical Mask Detection","display_name":"Capturing Time Dynamics From Speech Using Neural Networks for Surgical Mask Detection","publication_year":2022,"publication_date":"2022-05-06","ids":{"openalex":"https://openalex.org/W4229071437","doi":"https://doi.org/10.1109/jbhi.2022.3173128","pmid":"https://pubmed.ncbi.nlm.nih.gov/35522639"},"language":"en","primary_location":{"id":"doi:10.1109/jbhi.2022.3173128","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jbhi.2022.3173128","pdf_url":null,"source":{"id":"https://openalex.org/S2495854775","display_name":"IEEE Journal of Biomedical and Health Informatics","issn_l":"2168-2194","issn":["2168-2194","2168-2208"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Biomedical and Health Informatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/6651976","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079742987","display_name":"Shuo Liu","orcid":"https://orcid.org/0000-0001-8133-8588"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Shuo Liu","raw_affiliation_strings":["Chair of Embedded Intelligence for Health Care & Wellbeing, University of Augsburg, Augsburg, Germany"],"raw_orcid":"https://orcid.org/0000-0001-8133-8588","affiliations":[{"raw_affiliation_string":"Chair of Embedded Intelligence for Health Care & Wellbeing, University of Augsburg, Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048720202","display_name":"Adria Mallol-Ragolta","orcid":null},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Adria Mallol-Ragolta","raw_affiliation_strings":["Chair of Embedded Intelligence for Health Care & Wellbeing, University of Augsburg, Augsburg, Germany"],"raw_orcid":"https://orcid.org/0000-0001-6855-485X","affiliations":[{"raw_affiliation_string":"Chair of Embedded Intelligence for Health Care & Wellbeing, University of Augsburg, Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101742217","display_name":"Tianhao Yan","orcid":"https://orcid.org/0000-0003-1851-6075"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianhao Yan","raw_affiliation_strings":["College of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0003-1851-6075","affiliations":[{"raw_affiliation_string":"College of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032971738","display_name":"Kun Qian","orcid":"https://orcid.org/0000-0002-1918-6453"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Qian","raw_affiliation_strings":["School of Medical Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1918-6453","affiliations":[{"raw_affiliation_string":"School of Medical Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073718976","display_name":"Emilia Parada\u2010Cabaleiro","orcid":"https://orcid.org/0000-0003-1843-3632"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Emilia Parada-Cabaleiro","raw_affiliation_strings":["Institute of Computational Perception, Johannes Kepler University Linz, Linz, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computational Perception, Johannes Kepler University Linz, Linz, Austria","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100380066","display_name":"Bin Hu","orcid":"https://orcid.org/0000-0003-3514-5413"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Hu","raw_affiliation_strings":["School of Medical Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3514-5413","affiliations":[{"raw_affiliation_string":"School of Medical Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["DE","GB"],"is_corresponding":false,"raw_author_name":"Bjorn W. Schuller","raw_affiliation_strings":["Chair of Embedded Intelligence for Health Care & Wellbeing, University of Augsburg, Augsburg, Germany","Group on Language, Audio, & Music, Imperial College London, London, U.K"],"raw_orcid":"https://orcid.org/0000-0002-6478-8699","affiliations":[{"raw_affiliation_string":"Chair of Embedded Intelligence for Health Care & Wellbeing, University of Augsburg, Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]},{"raw_affiliation_string":"Group on Language, Audio, & Music, Imperial College London, London, U.K","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5079742987"],"corresponding_institution_ids":["https://openalex.org/I179225836"],"apc_list":null,"apc_paid":null,"fwci":0.4464,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.56587725,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"26","issue":"8","first_page":"4291","last_page":"4302"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9969000220298767,"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/T10860","display_name":"Speech and Audio Processing","score":0.9969000220298767,"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/T11448","display_name":"Face recognition and analysis","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.983299970626831,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.850724458694458},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6295477747917175},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.608890950679779},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6019512414932251},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5268263220787048},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.48636940121650696},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.46554598212242126},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4222668409347534},{"id":"https://openalex.org/keywords/hybrid-neural-network","display_name":"Hybrid neural network","score":0.4155113399028778},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4097784161567688},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3240906000137329}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.850724458694458},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6295477747917175},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.608890950679779},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6019512414932251},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5268263220787048},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.48636940121650696},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.46554598212242126},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4222668409347534},{"id":"https://openalex.org/C2779990667","wikidata":"https://www.wikidata.org/wiki/Q5953266","display_name":"Hybrid neural network","level":3,"score":0.4155113399028778},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4097784161567688},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3240906000137329},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000086382","descriptor_name":"COVID-19","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000086382","descriptor_name":"COVID-19","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000086382","descriptor_name":"COVID-19","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008397","descriptor_name":"Masks","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008397","descriptor_name":"Masks","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008397","descriptor_name":"Masks","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1109/jbhi.2022.3173128","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jbhi.2022.3173128","pdf_url":null,"source":{"id":"https://openalex.org/S2495854775","display_name":"IEEE Journal of Biomedical and Health Informatics","issn_l":"2168-2194","issn":["2168-2194","2168-2208"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Biomedical and Health Informatics","raw_type":"journal-article"},{"id":"pmid:35522639","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35522639","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":"IEEE journal of biomedical and health informatics","raw_type":null},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:98399","is_oa":false,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/98399","pdf_url":null,"source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},{"id":"pmh:oai:zenodo.org:6651976","is_oa":true,"landing_page_url":"https://zenodo.org/record/6651976","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Journal of Biomedical and Health Informatics","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:6651976","is_oa":true,"landing_page_url":"https://zenodo.org/record/6651976","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Journal of Biomedical and Health Informatics","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.7300000190734863}],"awards":[{"id":"https://openalex.org/G8246290944","display_name":null,"funder_award_id":"No. 202006680068","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"}],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W1902237438","https://openalex.org/W1979651826","https://openalex.org/W1980276147","https://openalex.org/W2064370490","https://openalex.org/W2105482032","https://openalex.org/W2194775991","https://openalex.org/W2407080277","https://openalex.org/W2526050071","https://openalex.org/W2756182389","https://openalex.org/W2810135932","https://openalex.org/W2915760784","https://openalex.org/W2919115771","https://openalex.org/W2922475962","https://openalex.org/W2936774411","https://openalex.org/W2954996726","https://openalex.org/W2962962542","https://openalex.org/W2963925437","https://openalex.org/W2964110616","https://openalex.org/W2964334034","https://openalex.org/W2965655638","https://openalex.org/W2990751682","https://openalex.org/W2999309192","https://openalex.org/W3014348725","https://openalex.org/W3027360693","https://openalex.org/W3032742287","https://openalex.org/W3032857945","https://openalex.org/W3034825141","https://openalex.org/W3042086946","https://openalex.org/W3045576536","https://openalex.org/W3046292371","https://openalex.org/W3048827124","https://openalex.org/W3048937063","https://openalex.org/W3088517395","https://openalex.org/W3090893422","https://openalex.org/W3094907801","https://openalex.org/W3095513995","https://openalex.org/W3096216346","https://openalex.org/W3096383643","https://openalex.org/W3097158535","https://openalex.org/W3097426020","https://openalex.org/W3105153358","https://openalex.org/W3113255501","https://openalex.org/W3118643387","https://openalex.org/W3123664835","https://openalex.org/W3128392043","https://openalex.org/W3128758033","https://openalex.org/W3131356212","https://openalex.org/W3137769009","https://openalex.org/W3152912772","https://openalex.org/W3157365046","https://openalex.org/W3160747020","https://openalex.org/W3168903682","https://openalex.org/W3171336755","https://openalex.org/W3174657965","https://openalex.org/W3180187578","https://openalex.org/W4221122497","https://openalex.org/W4234776729","https://openalex.org/W6739901393","https://openalex.org/W6747381837","https://openalex.org/W6751923770","https://openalex.org/W6783914088","https://openalex.org/W6804948693"],"related_works":["https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W1847088711","https://openalex.org/W3036642985","https://openalex.org/W3032952384","https://openalex.org/W3017902212","https://openalex.org/W2964335273","https://openalex.org/W2982145560","https://openalex.org/W2969450769"],"abstract_inverted_index":{"The":[0,80,133],"importance":[1],"of":[2,19,32,100,128,142,149,175,206,216],"detecting":[3],"whether":[4,187],"a":[5,8,24,107,143,150],"person":[6],"wears":[7],"face":[9,49],"mask":[10,25],"while":[11],"speaking":[12],"has":[13],"tremendously":[14],"increased":[15],"since":[16],"the":[17,30,33,37,57,97,101,115,122,126,139,146,173,204,207,217,221,229],"outbreak":[18],"SARS-CoV-2":[20],"(COVID-19),":[21],"as":[22,92],"wearing":[23],"can":[26,162],"help":[27],"to":[28,47,74,113,155,157],"reduce":[29],"spread":[31],"virus":[34],"and":[35,60,177,198],"mitigate":[36],"public":[38],"health":[39],"crisis.":[40],"Besides":[41],"affecting":[42],"human":[43],"speech":[44],"characteristics":[45],"related":[46],"frequency,":[48],"masks":[50,77],"cause":[51],"temporal":[52,131,168],"interferences":[53],"in":[54,179],"speech,":[55],"altering":[56],"pace,":[58],"rhythm,":[59],"pronunciation":[61],"speed.":[62],"In":[63,153],"this":[64,66],"regard,":[65],"paper":[67],"presents":[68],"two":[69],"effective":[70],"neural":[71],"network":[72,112],"models":[73,219],"detect":[75],"surgical":[76],"from":[78],"audio.":[79],"proposed":[81,208],"architectures":[82,161],"are":[83],"both":[84,160],"based":[85],"on":[86],"Convolutional":[87],"Neural":[88],"Networks":[89],"(CNNs),":[90],"chosen":[91],"an":[93,118],"optimal":[94],"approach":[95],"for":[96,228],"spatial":[98],"processing":[99],"audio":[102,196],"signals.":[103],"One":[104],"architecture":[105,124,135],"applies":[106],"Long":[108],"Short-Term":[109],"Memory":[110],"(LSTM)":[111],"model":[114],"time-dependencies.":[116],"Through":[117],"additional":[119],"attention":[120],"mechanism,":[121],"LSTM-based":[123],"enables":[125],"extraction":[127],"more":[129],"salient":[130],"information.":[132],"other":[134,165],"(named":[136],"ConvTx)":[137],"retrieves":[138],"relative":[140],"position":[141],"sequence":[144],"through":[145],"positional":[147],"encoder":[148],"transformer":[151],"module.":[152],"order":[154],"assess":[156],"which":[158],"extent":[159],"complement":[163],"each":[164],"when":[166],"modelling":[167],"dynamics,":[169],"we":[170,184],"also":[171,185],"explore":[172],"combination":[174],"LSTM":[176],"Transformers":[178],"three":[180],"hybrid":[181,218],"models.":[182],"Finally,":[183],"investigate":[186],"data":[188],"augmentation":[189],"techniques,":[190],"such":[191],"as,":[192],"using":[193],"transitions":[194],"between":[195],"frames":[197],"considering":[199],"gender-dependent":[200],"frameworks":[201],"might":[202],"impact":[203],"performance":[205],"architectures.":[209],"Our":[210],"experimental":[211],"results":[212,227],"show":[213],"that":[214],"one":[215],"achieves":[220],"best":[222],"performance,":[223],"surpassing":[224],"existing":[225],"state-of-the-art":[226],"task":[230],"at":[231],"hand.":[232]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}