{"id":"https://openalex.org/W4405491509","doi":"https://doi.org/10.1109/embc53108.2024.10781765","title":"Exploring Self-Supervised Models for Depressive Disorder Detection: A Study on Speech Corpora","display_name":"Exploring Self-Supervised Models for Depressive Disorder Detection: A Study on Speech Corpora","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4405491509","doi":"https://doi.org/10.1109/embc53108.2024.10781765","pmid":"https://pubmed.ncbi.nlm.nih.gov/40039538"},"language":"en","primary_location":{"id":"doi:10.1109/embc53108.2024.10781765","is_oa":false,"landing_page_url":"https://doi.org/10.1109/embc53108.2024.10781765","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5005410399","display_name":"Bubai Maji","orcid":"https://orcid.org/0000-0002-6995-0317"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Bubai Maji","raw_affiliation_strings":["IIT Kharagpur,Rekhi Centre of Excellence for the Science of Happiness,Kharagpur,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Kharagpur,Rekhi Centre of Excellence for the Science of Happiness,Kharagpur,India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043167162","display_name":"Shazia Nasreen","orcid":"https://orcid.org/0000-0002-8894-2670"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shazia Nasreen","raw_affiliation_strings":["IIT Kharagpur,Rekhi Centre of Excellence for the Science of Happiness,Kharagpur,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Kharagpur,Rekhi Centre of Excellence for the Science of Happiness,Kharagpur,India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073333260","display_name":"Rajlakshmi Guha","orcid":null},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rajlakshmi Guha","raw_affiliation_strings":["IIT Kharagpur,Rekhi Centre of Excellence for the Science of Happiness,Kharagpur,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Kharagpur,Rekhi Centre of Excellence for the Science of Happiness,Kharagpur,India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045754565","display_name":"Aurobinda Routray","orcid":"https://orcid.org/0000-0003-2750-6768"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Aurobinda Routray","raw_affiliation_strings":["IIT Kharagpur,Dept. of Electrical Engineering,Kharagpur,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Kharagpur,Dept. of Electrical Engineering,Kharagpur,India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111725712","display_name":"Debabrata Majumdar","orcid":null},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Debabrata Majumdar","raw_affiliation_strings":["IIT Kharagpur,B. C. Roy Tech Hospital,Kharagpur,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Kharagpur,B. C. Roy Tech Hospital,Kharagpur,India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062896274","display_name":"Km Poonam","orcid":"https://orcid.org/0000-0002-7130-4103"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Km Poonam","raw_affiliation_strings":["IIT Kharagpur,Centre of Artificial Intelligence,Kharagpur,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Kharagpur,Centre of Artificial Intelligence,Kharagpur,India","institution_ids":["https://openalex.org/I145894827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5005410399"],"corresponding_institution_ids":["https://openalex.org/I145894827"],"apc_list":null,"apc_paid":null,"fwci":1.3882,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.83526156,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"2024","issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9984999895095825,"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"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9984999895095825,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9973999857902527,"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/T11309","display_name":"Music and Audio Processing","score":0.9955000281333923,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6346521377563477},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5528579950332642},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5063415765762329},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3940351605415344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6346521377563477},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5528579950332642},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5063415765762329},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3940351605415344}],"mesh":[{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003866","descriptor_name":"Depressive Disorder","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":true},{"descriptor_ui":"D003866","descriptor_name":"Depressive Disorder","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":true},{"descriptor_ui":"D003866","descriptor_name":"Depressive Disorder","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":true},{"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":"D012815","descriptor_name":"Signal Processing, Computer-Assisted","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012815","descriptor_name":"Signal Processing, Computer-Assisted","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":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","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":true},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/embc53108.2024.10781765","is_oa":false,"landing_page_url":"https://doi.org/10.1109/embc53108.2024.10781765","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)","raw_type":"proceedings-article"},{"id":"pmid:40039538","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40039538","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":"Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W46663288","https://openalex.org/W1581105046","https://openalex.org/W2003502731","https://openalex.org/W2056403322","https://openalex.org/W2101234009","https://openalex.org/W2157741754","https://openalex.org/W2191779130","https://openalex.org/W2529925562","https://openalex.org/W2798571323","https://openalex.org/W2888872770","https://openalex.org/W2889056793","https://openalex.org/W2889378348","https://openalex.org/W2980110078","https://openalex.org/W2981677410","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4224924082","https://openalex.org/W4295682739","https://openalex.org/W4372338343","https://openalex.org/W4385823099","https://openalex.org/W4388782451","https://openalex.org/W4389538363","https://openalex.org/W6601957410","https://openalex.org/W6691669583","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Automatic":[0],"detection":[1,147],"of":[2,24,36,53,110,118,163],"depressive":[3],"disorder":[4],"from":[5],"speech":[6,54],"signals":[7],"can":[8],"help":[9],"improve":[10],"medical":[11],"diagnosis":[12],"reliability.":[13],"However,":[14],"a":[15,85],"significant":[16],"challenge":[17],"in":[18,114,145,160,166],"this":[19,41,167],"field":[20],"is":[21],"that":[22,126],"most":[23],"the":[25,34,51,75,108,115,127,135,149,161],"available":[26],"depression":[27,47,57,146],"datasets":[28],"are":[29,61],"relatively":[30],"small,":[31],"which":[32],"limits":[33],"effectiveness":[35],"sophisticated":[37],"deep-learning":[38],"approaches.":[39],"In":[40,104],"work,":[42],"we":[43,77,106],"study":[44],"low-resource,":[45],"speech-based":[46],"corpora":[48],"to":[49,101],"explore":[50],"effect":[52],"embeddings":[55,60],"for":[56],"detection.":[58],"The":[59,122],"extracted":[62],"via":[63],"self-supervised":[64],"learning":[65],"(SSL)":[66],"models":[67,165],"(Wav2Vec":[68],"2.0,":[69],"HuBERT,":[70],"and":[71,96,129],"WavLM).":[72],"After":[73],"extracting":[74],"embeddings,":[76],"benchmarked":[78],"them":[79],"with":[80],"several":[81],"traditional":[82],"classifiers,":[83],"including":[84],"support":[86],"vector":[87],"machine":[88],"(SVM),":[89],"Logistic":[90],"Regression":[91],"(LR),":[92],"Decision":[93],"Tree":[94],"(DT),":[95],"Naive":[97],"Bayes":[98],"classifier":[99],"(NBC)":[100],"detect":[102],"depression.":[103],"addition,":[105],"investigated":[107],"impact":[109],"different":[111],"layer":[112],"depths":[113],"upstream":[116],"networks":[117],"these":[119],"SSL":[120,164],"models.":[121],"experimental":[123],"results":[124],"revealed":[125],"Wav2Vec2.0":[128],"WavLM":[130,139],"features":[131,140,152],"generalize":[132],"better":[133],"than":[134],"HuBERT":[136],"features.":[137],"Notably,":[138],"improved":[141],"accuracy":[142],"by":[143],"13.1%":[144],"over":[148],"best":[150],"baseline":[151],"(MFCCs).":[153],"These":[154],"findings":[155],"will":[156],"aid":[157],"future":[158],"research":[159],"use":[162],"field.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-11T08:15:01.531666","created_date":"2025-10-10T00:00:00"}
