{"id":"https://openalex.org/W3036117766","doi":"https://doi.org/10.21437/interspeech.2020-1329","title":"Are you Wearing a Mask? Improving Mask Detection from Speech Using Augmentation by Cycle-Consistent GANs","display_name":"Are you Wearing a Mask? Improving Mask Detection from Speech Using Augmentation by Cycle-Consistent GANs","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3036117766","doi":"https://doi.org/10.21437/interspeech.2020-1329","mag":"3036117766"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1329","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1329","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2006.10147","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083932459","display_name":"Nicolae-C\u0103t\u0103lin Ristea","orcid":"https://orcid.org/0000-0002-7880-9307"},"institutions":[{"id":"https://openalex.org/I4210131793","display_name":"Infineon Technologies (Austria)","ror":"https://ror.org/03msng824","country_code":"AT","type":"company","lineage":["https://openalex.org/I137594350","https://openalex.org/I4210131793"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Nicolae-C\u0103t\u0103lin Ristea","raw_affiliation_strings":["INFINEON TECHNOLOGIES AUSTRIA AG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INFINEON TECHNOLOGIES AUSTRIA AG","institution_ids":["https://openalex.org/I4210131793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081017623","display_name":"Radu Tudor Ionescu","orcid":"https://orcid.org/0000-0002-9301-1950"},"institutions":[{"id":"https://openalex.org/I141595442","display_name":"University of Bucharest","ror":"https://ror.org/02x2v6p15","country_code":"RO","type":"education","lineage":["https://openalex.org/I141595442"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Radu Tudor Ionescu","raw_affiliation_strings":["University of Bucharest,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bucharest,","institution_ids":["https://openalex.org/I141595442"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6574,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.6549593,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2102","last_page":"2106"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.998199999332428,"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":0.998199999332428,"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":0.9883999824523926,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.986299991607666,"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":0.8526626825332642},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.631700336933136},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5697659254074097},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.547153115272522},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.52486652135849},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5125164985656738},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.510982871055603},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.48642826080322266},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.46198779344558716},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.44185763597488403},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4418374001979828},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40537378191947937},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3251023292541504},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32142049074172974}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8526626825332642},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.631700336933136},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5697659254074097},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.547153115272522},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.52486652135849},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5125164985656738},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.510982871055603},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.48642826080322266},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46198779344558716},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.44185763597488403},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4418374001979828},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40537378191947937},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3251023292541504},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32142049074172974},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2020-1329","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1329","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:2006.10147","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.10147","pdf_url":"https://arxiv.org/pdf/2006.10147","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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:3036117766","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2006.10147","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2006.10147","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2006.10147","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2006.10147","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.10147","pdf_url":"https://arxiv.org/pdf/2006.10147","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":0.5699999928474426,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320335198","display_name":"EEA Grants","ror":"https://ror.org/02dfxg175"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3036117766.pdf"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1510073064","https://openalex.org/W1903029394","https://openalex.org/W2115144768","https://openalex.org/W2119821739","https://openalex.org/W2125389028","https://openalex.org/W2147768505","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2282821441","https://openalex.org/W2293291943","https://openalex.org/W2407080277","https://openalex.org/W2508457150","https://openalex.org/W2795144650","https://openalex.org/W2919115771","https://openalex.org/W2936774411","https://openalex.org/W2962793481","https://openalex.org/W2964121744","https://openalex.org/W2972640480","https://openalex.org/W2995910740","https://openalex.org/W2997222478","https://openalex.org/W3096216346","https://openalex.org/W3137695714","https://openalex.org/W3191026187"],"related_works":["https://openalex.org/W3097158535","https://openalex.org/W3158521267","https://openalex.org/W3080091772","https://openalex.org/W3048786306","https://openalex.org/W3165957370","https://openalex.org/W3034924009","https://openalex.org/W2967804986","https://openalex.org/W2980581183","https://openalex.org/W3162424266","https://openalex.org/W3108855822","https://openalex.org/W3186843219","https://openalex.org/W2933148111","https://openalex.org/W1980336251","https://openalex.org/W3174102645","https://openalex.org/W2798949062","https://openalex.org/W2936774411","https://openalex.org/W1495019370","https://openalex.org/W3040867037","https://openalex.org/W2887894196","https://openalex.org/W1603553412"],"abstract_inverted_index":{"The":[0,116],"task":[1],"of":[2,109,140,164],"detecting":[3],"whether":[4],"a":[5,8,39,107,124,161],"person":[6],"wears":[7],"face":[9],"mask":[10,45,71],"from":[11,47],"speech":[12,17],"is":[13,51],"useful":[14],"in":[15,18,135],"modelling":[16],"forensic":[19],"investigations,":[20],"communication":[21],"between":[22,67],"surgeons":[23],"or":[24],"people":[25],"protecting":[26],"themselves":[27],"against":[28],"infectious":[29],"diseases":[30],"such":[31],"as":[32,104],"COVID-19.":[33],"In":[34],"this":[35,131],"paper,":[36],"we":[37,133,172],"propose":[38],"novel":[40],"data":[41,157,176],"augmentation":[42,158,177,187],"approach":[43,50,178],"for":[44],"detection":[46],"speech.":[48],"Our":[49,156],"based":[52],"on":[53,76,166],"(i)":[54],"training":[55,80],"Generative":[56],"Adversarial":[57],"Networks":[58],"(GANs)":[59],"with":[60,113],"cycle-consistency":[61],"loss":[62],"to":[63,89,106],"translate":[64],"unpaired":[65],"utterances":[66,81,96],"two":[68],"classes":[69],"(with":[70],"and":[72,75,94,185],"without":[73],"mask),":[74],"(ii)":[77],"generating":[78],"new":[79],"using":[82],"the":[83,136,141,148,152,167],"cycle-consistent":[84],"GANs,":[85],"assigning":[86],"opposite":[87],"labels":[88],"each":[90],"translated":[91,95],"utterance.":[92],"Original":[93],"are":[97,102,118],"converted":[98],"into":[99,120],"spectrograms":[100],"which":[101],"provided":[103,160],"input":[105],"set":[108],"ResNet":[110],"neural":[111],"networks":[112,117],"various":[114],"depths.":[115],"combined":[119],"an":[121],"ensemble":[122],"through":[123],"Support":[125],"Vector":[126],"Machines":[127],"(SVM)":[128],"classifier.":[129],"With":[130],"system,":[132],"participated":[134],"Mask":[137],"Sub-Challenge":[138],"(MSC)":[139],"INTERSPEECH":[142],"2020":[143],"Computational":[144],"Paralinguistics":[145],"Challenge,":[146],"surpassing":[147],"baseline":[149,184],"proposed":[150],"by":[151,154],"organizers":[153],"2.8%.":[155],"technique":[159],"performance":[162],"boost":[163],"0.9%":[165],"private":[168],"test":[169],"set.":[170],"Furthermore,":[171],"show":[173],"that":[174],"our":[175],"yields":[179],"better":[180],"results":[181],"than":[182],"other":[183],"state-of-the-art":[186],"methods.":[188]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}