{"id":"https://openalex.org/W4372269226","doi":"https://doi.org/10.1109/icassp49357.2023.10094910","title":"Self-Supervised Representations in Speech-Based Depression Detection","display_name":"Self-Supervised Representations in Speech-Based Depression Detection","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372269226","doi":"https://doi.org/10.1109/icassp49357.2023.10094910"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094910","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2305.12263","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079268196","display_name":"Wen Wu","orcid":"https://orcid.org/0000-0001-8116-7715"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wen Wu","raw_affiliation_strings":["University of Cambridge,Department of Engineering,Cambridge,UK","Department of Engineering, University of Cambridge, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge,Department of Engineering,Cambridge,UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Department of Engineering, University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460206","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0002-7730-5131"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["University of Cambridge,Department of Engineering,Cambridge,UK","Department of Engineering, University of Cambridge, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge,Department of Engineering,Cambridge,UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Department of Engineering, University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002191410","display_name":"Philip C. Woodland","orcid":"https://orcid.org/0000-0001-9069-0225"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Philip C. Woodland","raw_affiliation_strings":["University of Cambridge,Department of Engineering,Cambridge,UK","Department of Engineering, University of Cambridge, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge,Department of Engineering,Cambridge,UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Department of Engineering, University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":30,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9986000061035156,"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":0.9986000061035156,"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":0.9976000189781189,"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/T12488","display_name":"Mental Health via Writing","score":0.992900013923645,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7621314525604248},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.6163027286529541},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.604608416557312},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5871124863624573},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5774872303009033},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5671464204788208},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4918208122253418},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4293321669101715},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.42453712224960327},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3729364275932312},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2302960753440857}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7621314525604248},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.6163027286529541},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.604608416557312},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5871124863624573},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5774872303009033},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5671464204788208},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4918208122253418},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4293321669101715},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.42453712224960327},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3729364275932312},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2302960753440857},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094910","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2305.12263","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.12263","pdf_url":"https://arxiv.org/pdf/2305.12263","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2305.12263","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.12263","pdf_url":"https://arxiv.org/pdf/2305.12263","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.699999988079071}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4372269226.pdf","grobid_xml":"https://content.openalex.org/works/W4372269226.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W2003502731","https://openalex.org/W2018096495","https://openalex.org/W2103011877","https://openalex.org/W2109636054","https://openalex.org/W2127141656","https://openalex.org/W2144723972","https://openalex.org/W2531271152","https://openalex.org/W2742542661","https://openalex.org/W2767030624","https://openalex.org/W2889056793","https://openalex.org/W2965373594","https://openalex.org/W3036601975","https://openalex.org/W3040796747","https://openalex.org/W3098431772","https://openalex.org/W3195577433","https://openalex.org/W3197580070","https://openalex.org/W3204696009","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4224923621","https://openalex.org/W4224924082","https://openalex.org/W4225635674","https://openalex.org/W4226380987","https://openalex.org/W4285044984","https://openalex.org/W4296069164","https://openalex.org/W6676218802","https://openalex.org/W6766673545","https://openalex.org/W6780218876","https://openalex.org/W6780800997","https://openalex.org/W6800751262"],"related_works":["https://openalex.org/W2073713056","https://openalex.org/W3110702597","https://openalex.org/W2381393187","https://openalex.org/W2332779545","https://openalex.org/W2078761926","https://openalex.org/W2110441383","https://openalex.org/W2125620709","https://openalex.org/W1498872724","https://openalex.org/W4233149903","https://openalex.org/W4293864700"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"handling":[3],"training":[4],"data":[5],"sparsity":[6],"in":[7],"speech-based":[8],"automatic":[9,54],"depression":[10,46],"detection":[11],"(SDD)":[12],"using":[13],"foundation":[14,32,66,103],"models":[15,33],"pre-trained":[16,31],"with":[17,93],"self-supervised":[18],"learning":[19],"(SSL).":[20],"An":[21],"analysis":[22],"of":[23,30,73,86],"SSL":[24],"representations":[25,85,100],"derived":[26],"from":[27,53,101],"different":[28],"layers":[29],"is":[34,50,90],"first":[35],"presented":[36],"for":[37,45],"SDD,":[38],"which":[39],"provides":[40],"insight":[41],"to":[42,61],"suitable":[43],"indicator":[44],"detection.":[47],"Knowledge":[48],"transfer":[49],"then":[51],"performed":[52],"speech":[55],"recognition":[56,60],"(ASR)":[57],"and":[58,75],"emotion":[59],"SDD":[62,80,106],"by":[63],"fine-tuning":[64],"the":[65,71,83,87,94,115],"models.":[67],"Results":[68],"show":[69],"that":[70],"uses":[72],"oracle":[74],"ASR":[76,88,95,111],"transcriptions":[77],"yield":[78],"similar":[79],"performance":[81],"when":[82],"hidden":[84],"model":[89],"incorporated":[91],"along":[92],"textual":[96],"information.":[97],"By":[98],"integrating":[99],"multiple":[102],"models,":[104],"state-of-the-art":[105],"results":[107],"based":[108],"on":[109,114],"real":[110],"were":[112],"achieved":[113],"DAIC-WOZ":[116],"dataset.":[117]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}