{"id":"https://openalex.org/W3160467219","doi":"https://doi.org/10.1109/icassp39728.2021.9413589","title":"Deep Neural Network Embeddings for the Estimation of the Degree of Sleepiness","display_name":"Deep Neural Network Embeddings for the Estimation of the Degree of Sleepiness","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160467219","doi":"https://doi.org/10.1109/icassp39728.2021.9413589","mag":"3160467219"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413589","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025953461","display_name":"Jos\u00e9 Vicente Egas-L\u00f3pez","orcid":"https://orcid.org/0000-0002-5622-9192"},"institutions":[{"id":"https://openalex.org/I227486990","display_name":"University of Szeged","ror":"https://ror.org/01pnej532","country_code":"HU","type":"education","lineage":["https://openalex.org/I227486990"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Jose Vicente Egas-Lopez","raw_affiliation_strings":["Institute of Informatics, University of Szeged, Szeged, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Informatics, University of Szeged, Szeged, Hungary","institution_ids":["https://openalex.org/I227486990"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088559776","display_name":"G\u00e1bor Gosztolya","orcid":"https://orcid.org/0000-0002-2864-6466"},"institutions":[{"id":"https://openalex.org/I227486990","display_name":"University of Szeged","ror":"https://ror.org/01pnej532","country_code":"HU","type":"education","lineage":["https://openalex.org/I227486990"]},{"id":"https://openalex.org/I4210152167","display_name":"MTA-SZTE Research Group on Artificial Intelligence","ror":"https://ror.org/0507fk326","country_code":"HU","type":"facility","lineage":["https://openalex.org/I227486990","https://openalex.org/I4210152167","https://openalex.org/I7597260"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Gabor Gosztolya","raw_affiliation_strings":["Institute of Informatics, University of Szeged, Szeged, Hungary","MTA-SZTE Research Group on Artificial Intelligence, Szeged, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Informatics, University of Szeged, Szeged, Hungary","institution_ids":["https://openalex.org/I227486990"]},{"raw_affiliation_string":"MTA-SZTE Research Group on Artificial Intelligence, Szeged, Hungary","institution_ids":["https://openalex.org/I4210152167"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0936,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.87539136,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7288","last_page":"7292"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9955999851226807,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9872000217437744,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/degree","display_name":"Degree (music)","score":0.7001329064369202},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6636359691619873},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6492486000061035},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6374313831329346},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.5968070030212402},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5925109386444092},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5525633096694946},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.5254089832305908},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4987146854400635},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4978785514831543},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4582897424697876},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4446144700050354},{"id":"https://openalex.org/keywords/correlation-coefficient","display_name":"Correlation coefficient","score":0.4359205365180969},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3422069549560547},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16172784566879272},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10394200682640076},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.07553067803382874}],"concepts":[{"id":"https://openalex.org/C2775997480","wikidata":"https://www.wikidata.org/wiki/Q586277","display_name":"Degree (music)","level":2,"score":0.7001329064369202},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6636359691619873},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6492486000061035},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6374313831329346},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.5968070030212402},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5925109386444092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5525633096694946},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.5254089832305908},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4987146854400635},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4978785514831543},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4582897424697876},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4446144700050354},{"id":"https://openalex.org/C2780092901","wikidata":"https://www.wikidata.org/wiki/Q3433612","display_name":"Correlation coefficient","level":2,"score":0.4359205365180969},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3422069549560547},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16172784566879272},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10394200682640076},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.07553067803382874},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413589","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:publicatio.bibl.u-szeged.hu:22156","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400436","display_name":"SZTE Publicatio Repozit\u00f3rium (University of Szeged)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I227486990","host_organization_name":"University of Szeged","host_organization_lineage":["https://openalex.org/I227486990"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"K\u00f6nyv r\u00e9sze"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320328991","display_name":"Innov\u00e1ci\u00f3s \u00e9s Technol\u00f3giai Miniszt\u00e9rium","ror":"https://ror.org/02ey3ab96"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W131819148","https://openalex.org/W326857837","https://openalex.org/W775622597","https://openalex.org/W2017647414","https://openalex.org/W2150769028","https://openalex.org/W2153635508","https://openalex.org/W2161051082","https://openalex.org/W2185755222","https://openalex.org/W2381789786","https://openalex.org/W2400677246","https://openalex.org/W2509287279","https://openalex.org/W2742965906","https://openalex.org/W2748488820","https://openalex.org/W2770604845","https://openalex.org/W2889334839","https://openalex.org/W2954863777","https://openalex.org/W2972393344","https://openalex.org/W2972455439","https://openalex.org/W2972850640","https://openalex.org/W2973025177","https://openalex.org/W2977806333","https://openalex.org/W3015859459","https://openalex.org/W3024096624","https://openalex.org/W3130533174","https://openalex.org/W4388243886","https://openalex.org/W6611326119","https://openalex.org/W6777532430"],"related_works":["https://openalex.org/W1979583797","https://openalex.org/W3082848404","https://openalex.org/W3161230432","https://openalex.org/W2372254676","https://openalex.org/W2090763504","https://openalex.org/W2793679056","https://openalex.org/W2168900540","https://openalex.org/W4367190712","https://openalex.org/W148178222","https://openalex.org/W2080135837"],"abstract_inverted_index":{"Estimating":[0],"the":[1,6,22,26,39,52,65,74,103,109],"degree":[2],"of":[3,41,43],"sleepiness":[4,42,97],"from":[5],"human":[7],"speech":[8],"is":[9],"an":[10],"emerging":[11],"research":[12],"problem":[13],"with":[14,59],"straightforward":[15],"applications.":[16],"In":[17,99],"this":[18],"study,":[19],"we":[20,56,101],"employ":[21],"x-vector":[23,82],"approach,":[24],"currently":[25],"state-of-the-art":[27],"in":[28,96],"speaker":[29],"recognition,":[30],"as":[31,84],"a":[32,44,116],"neural":[33],"network":[34],"feature":[35],"extractor":[36],"to":[37,64,69,92],"detect":[38],"level":[40],"speaker.":[45],"Besides":[46],"using":[47],"different":[48],"corpora":[49],"for":[50,73,86],"fitting":[51],"x-":[53],"vector":[54],"DNN,":[55],"also":[57],"experiment":[58],"adding":[60],"noise":[61],"and":[62],"reverberation":[63],"training":[66],"samples.":[67],"According":[68],"our":[70],"experimental":[71],"results":[72],"publicly":[75],"available":[76],"Dusseldorf":[77],"Sleepy":[78],"Language":[79],"Corpus,":[80],"utilizing":[81],"embeddings":[83],"features":[85],"Support":[87],"Vector":[88],"Regression":[89],"consistently":[90],"leads":[91],"competitive":[93],"performance":[94],"scores":[95],"detection.":[98],"particular,":[100],"present":[102],"highest":[104],"Spearman's":[105],"correlation":[106],"coefficient":[107],"on":[108],"public":[110],"corpus":[111],"that":[112],"was":[113],"achieved":[114],"by":[115],"single":[117],"method.":[118]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}