{"id":"https://openalex.org/W4225327688","doi":"https://doi.org/10.1109/icassp43922.2022.9746068","title":"Automatic Assessment of the Degree of Clinical Depression from Speech Using X-Vectors","display_name":"Automatic Assessment of the Degree of Clinical Depression from Speech Using X-Vectors","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225327688","doi":"https://doi.org/10.1109/icassp43922.2022.9746068"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746068","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746068","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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":["University of Szeged, Institute of Informatics,Szeged,Hungary","University of Szeged, Institute of Informatics, Szeged, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Szeged, Institute of Informatics,Szeged,Hungary","institution_ids":["https://openalex.org/I227486990"]},{"raw_affiliation_string":"University of Szeged, Institute of Informatics, Szeged, Hungary","institution_ids":["https://openalex.org/I227486990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091684390","display_name":"G\u00e1bor Kiss","orcid":"https://orcid.org/0000-0002-0447-9376"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Gabor Kiss","raw_affiliation_strings":["Budapest University of Technology and Economics,Budapest,Hungary","Budapest University of Technology and Economics, Budapest, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Budapest University of Technology and Economics,Budapest,Hungary","institution_ids":["https://openalex.org/I29770179"]},{"raw_affiliation_string":"Budapest University of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083596812","display_name":"D\u00e1vid Sztah\u00f3","orcid":"https://orcid.org/0000-0002-7361-4260"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"David Sztaho","raw_affiliation_strings":["Budapest University of Technology and Economics,Budapest,Hungary","Budapest University of Technology and Economics, Budapest, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Budapest University of Technology and Economics,Budapest,Hungary","institution_ids":["https://openalex.org/I29770179"]},{"raw_affiliation_string":"Budapest University of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]}]},{"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":["University of Szeged, Institute of Informatics,Szeged,Hungary","ELRN, MTA-SZTE Research Group on Artificial Intelligence, Szeged, Hungary","University of Szeged, Institute of Informatics, Szeged, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Szeged, Institute of Informatics,Szeged,Hungary","institution_ids":["https://openalex.org/I227486990"]},{"raw_affiliation_string":"ELRN, MTA-SZTE Research Group on Artificial Intelligence, Szeged, Hungary","institution_ids":["https://openalex.org/I4210152167"]},{"raw_affiliation_string":"University of Szeged, Institute of Informatics, Szeged, Hungary","institution_ids":["https://openalex.org/I227486990"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6605,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.85767294,"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":"8502","last_page":"8506"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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/T12488","display_name":"Mental Health via Writing","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9952999949455261,"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/extractor","display_name":"Extractor","score":0.879621148109436},{"id":"https://openalex.org/keywords/depression","display_name":"Depression (economics)","score":0.674542248249054},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5934249758720398},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5436444282531738},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5430949926376343},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5155732035636902},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4892308712005615},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4518151581287384},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4466026723384857},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4430765211582184},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4167683720588684},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3896084427833557},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08720380067825317}],"concepts":[{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.879621148109436},{"id":"https://openalex.org/C2776867660","wikidata":"https://www.wikidata.org/wiki/Q1814941","display_name":"Depression (economics)","level":2,"score":0.674542248249054},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5934249758720398},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5436444282531738},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5430949926376343},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5155732035636902},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4892308712005615},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4518151581287384},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4466026723384857},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4430765211582184},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4167683720588684},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3896084427833557},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08720380067825317},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746068","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746068","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:publicatio.bibl.u-szeged.hu:24268","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":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W775622597","https://openalex.org/W1965229149","https://openalex.org/W1993882792","https://openalex.org/W2000149402","https://openalex.org/W2003502731","https://openalex.org/W2055134133","https://openalex.org/W2094341593","https://openalex.org/W2150769028","https://openalex.org/W2292075035","https://openalex.org/W2587150483","https://openalex.org/W2605671917","https://openalex.org/W2658929981","https://openalex.org/W2748488820","https://openalex.org/W2755258422","https://openalex.org/W2889378348","https://openalex.org/W2901611695","https://openalex.org/W2972921407","https://openalex.org/W3004047823","https://openalex.org/W3034717997","https://openalex.org/W3049426073","https://openalex.org/W3094977969","https://openalex.org/W3160467219","https://openalex.org/W3197490082","https://openalex.org/W4295682739","https://openalex.org/W6733275487"],"related_works":["https://openalex.org/W3082848404","https://openalex.org/W1979583797","https://openalex.org/W2016864125","https://openalex.org/W2372254676","https://openalex.org/W2080135837","https://openalex.org/W2793679056","https://openalex.org/W4283332091","https://openalex.org/W3145050838","https://openalex.org/W2393154870","https://openalex.org/W4237873526"],"abstract_inverted_index":{"Depression":[0],"is":[1,24,54,120],"a":[2,63,72],"frequent":[3],"and":[4,16,82,140],"curable":[5],"psychiatric":[6],"disorder,":[7],"detrimentally":[8],"affecting":[9],"daily":[10],"activities,":[11],"harming":[12],"both":[13],"work-place":[14],"productivity":[15],"personal":[17],"relationships.":[18],"Among":[19],"many":[20],"other":[21],"symptoms,":[22],"depression":[23,70,109],"associated":[25],"with":[26,77],"disordered":[27],"speech":[28,40],"production,":[29],"which":[30,133],"might":[31],"permit":[32],"its":[33],"automatic":[34],"screening":[35],"by":[36],"means":[37],"of":[38,41,47,88,117,121,138,144,151],"the":[39,42,45,52,86,115,118,126],"subject.":[43],"However,":[44],"choice":[46],"actual":[48],"features":[49],"extracted":[50],"from":[51,71],"recordings":[53],"not":[55],"trivial.":[56],"In":[57],"this":[58],"study,":[59],"we":[60,83],"employ":[61],"x-vectors,":[62],"DNN-based":[64],"feature":[65,128],"extractor":[66,119],"technique,":[67],"to":[68,100,125],"detect":[69],"Hungarian":[73],"corpus.":[74],"We":[75,111],"experiment":[76],"training":[78],"custom":[79],"x-vector":[80],"extractors,":[81],"also":[84,112],"explore":[85],"performance":[87],"an":[89,135,141],"out-of-domain":[90],"pre-trained":[91],"one.":[92],"Our":[93],"findings":[94],"confirm":[95],"that":[96,105,114],"x-vectors":[97],"are":[98],"able":[99],"capture":[101],"meaningful":[102],"speaker":[103],"traits":[104],"contain":[106],"information":[107],"for":[108],"discrimination.":[110],"show":[113],"language":[116],"secondary":[122],"importance":[123],"compared":[124],"frame-level":[127],"set:":[129],"our":[130],"best":[131],"model,":[132],"achieved":[134],"AUC":[136],"score":[137,143],"0.940":[139],"RMSE":[142],"9.54,":[145],"was":[146],"trained":[147],"on":[148],"log-energies":[149],"instead":[150],"MFCCs.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2022-05-05T00:00:00"}