{"id":"https://openalex.org/W3048579937","doi":"https://doi.org/10.21437/interspeech.2020-1692","title":"Surgical Mask Detection with Convolutional Neural Networks and Data Augmentations on Spectrograms","display_name":"Surgical Mask Detection with Convolutional Neural Networks and Data Augmentations on Spectrograms","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3048579937","doi":"https://doi.org/10.21437/interspeech.2020-1692","mag":"3048579937"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1692","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2008.04590","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069846773","display_name":"Steffen Illium","orcid":"https://orcid.org/0000-0003-0021-436X"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Steffen Illium","raw_affiliation_strings":["Ludwig-Maximilian University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ludwig-Maximilian University of Munich","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052914309","display_name":"Robert M\u00fcller","orcid":"https://orcid.org/0000-0003-3108-713X"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Robert M\u00fcller","raw_affiliation_strings":["Ludwig-Maximilian University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ludwig-Maximilian University of Munich","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024006892","display_name":"Andreas Sedlmeier","orcid":null},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Sedlmeier","raw_affiliation_strings":["Ludwig-Maximilian University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ludwig-Maximilian University of Munich","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064469861","display_name":"Claudia Linnhoff\u2013Popien","orcid":"https://orcid.org/0000-0001-6284-9286"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Claudia Linnhoff-Popien","raw_affiliation_strings":["Ludwig-Maximilian University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ludwig-Maximilian University of Munich","institution_ids":["https://openalex.org/I8204097"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3041,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.54187321,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2052","last_page":"2056"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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":0.9951000213623047,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8762868046760559},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8036336898803711},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7795700430870056},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6882323026657104},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.5800238251686096},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5668289065361023},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.5268834233283997},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5198255181312561},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4825593829154968},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.46908846497535706},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46618932485580444},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4533103108406067},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4508674740791321},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42863529920578003},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.4263862073421478},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4120536744594574},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3859465718269348},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37177324295043945}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8762868046760559},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8036336898803711},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7795700430870056},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6882323026657104},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.5800238251686096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5668289065361023},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.5268834233283997},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5198255181312561},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4825593829154968},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.46908846497535706},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46618932485580444},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4533103108406067},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4508674740791321},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42863529920578003},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4263862073421478},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4120536744594574},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3859465718269348},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37177324295043945},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2020-1692","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2008.04590","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.04590","pdf_url":"https://arxiv.org/pdf/2008.04590","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"},{"id":"mag:3048579937","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2008.04590.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2008.04590","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2008.04590","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2008.04590","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.04590","pdf_url":"https://arxiv.org/pdf/2008.04590","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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3048579937.pdf","grobid_xml":"https://content.openalex.org/works/W3048579937.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1836465849","https://openalex.org/W1972567154","https://openalex.org/W2059652044","https://openalex.org/W2405274704","https://openalex.org/W2407080277","https://openalex.org/W2559688696","https://openalex.org/W2896271387","https://openalex.org/W2914166397","https://openalex.org/W2949251039","https://openalex.org/W2952356812","https://openalex.org/W2962711843","https://openalex.org/W2963232038","https://openalex.org/W2973109987","https://openalex.org/W3015995734","https://openalex.org/W3096216346"],"related_works":["https://openalex.org/W3097426020","https://openalex.org/W3098357269","https://openalex.org/W3124268183","https://openalex.org/W2526969612","https://openalex.org/W3091762728","https://openalex.org/W2760244101","https://openalex.org/W2515503816","https://openalex.org/W3046316711","https://openalex.org/W2980280361","https://openalex.org/W3042834815","https://openalex.org/W3175103763","https://openalex.org/W3034207266","https://openalex.org/W2808991257","https://openalex.org/W2986395879","https://openalex.org/W2996082862","https://openalex.org/W2973546605","https://openalex.org/W3091309678","https://openalex.org/W2883276922","https://openalex.org/W2759969338","https://openalex.org/W3117786798"],"abstract_inverted_index":{"In":[0],"many":[1],"fields":[2],"of":[3,21,27,46,77,84,92,98,119],"research,":[4],"labeled":[5],"datasets":[6],"are":[7,125],"hard":[8],"to":[9,17,38,42,54,60,110],"acquire.":[10],"This":[11],"is":[12,37],"where":[13],"data":[14,23,57,85],"augmentation":[15,58,86,113],"promises":[16],"overcome":[18],"the":[19,25,43,64,82,88,120],"lack":[20],"training":[22,50],"in":[24,63,96],"context":[26],"neural":[28,72],"network":[29],"engineering":[30],"and":[31],"classification":[32,90],"tasks.":[33],"The":[34],"idea":[35],"here":[36],"reduce":[39],"model":[40],"over-fitting":[41],"feature":[44],"distribution":[45],"a":[47],"small":[48],"under-descriptive":[49],"dataset.":[51],"We":[52,80],"try":[53],"evaluate":[55],"such":[56],"techniques":[59],"gather":[61],"insights":[62],"performance":[65],"boost":[66],"they":[67],"provide":[68],"for":[69,112],"several":[70],"convolutional":[71],"networks":[73],"on":[74,87],"mel-spectrogram":[75],"representations":[76],"audio":[78],"data.":[79],"show":[81,116],"impact":[83],"binary":[89],"task":[91],"surgical":[93],"mask":[94],"detection":[95],"samples":[97],"human":[99],"voice":[100],"(ComParE":[101],"Challenge":[102],"2020).":[103],"Also":[104],"we":[105],"consider":[106],"four":[107],"varying":[108],"architectures":[109],"account":[111],"robustness.":[114],"Results":[115],"that":[117],"most":[118],"baselines":[121],"given":[122],"by":[123],"ComParE":[124],"outperformed.":[126]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}