{"id":"https://openalex.org/W4415433094","doi":"https://doi.org/10.21437/interspeech.2025-1789","title":"A Study on The Impact of Foundation Models on Automatic Depression Detection from Speech Signals","display_name":"A Study on The Impact of Foundation Models on Automatic Depression Detection from Speech Signals","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433094","doi":"https://doi.org/10.21437/interspeech.2025-1789"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-1789","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://researchprofiles.ku.dk/da/publications/95e4f1cf-c2d9-4005-aa65-3585e382a8fc","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005410399","display_name":"Bubai Maji","orcid":"https://orcid.org/0000-0002-6995-0317"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bubai Maji","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023575441","display_name":"Monorama Swain","orcid":"https://orcid.org/0000-0002-3768-857X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Monorama Swain","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043167162","display_name":"Shazia Nasreen","orcid":"https://orcid.org/0000-0002-8894-2670"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shazia Nasreen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111725712","display_name":"Debabrata Majumdar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Debabrata Majumdar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073333260","display_name":"Rajlakshmi Guha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rajlakshmi Guha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045754565","display_name":"Aurobinda Routray","orcid":"https://orcid.org/0000-0003-2750-6768"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aurobinda Routray","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5018138946","display_name":"Anders S\u00f8gaard","orcid":"https://orcid.org/0000-0001-5250-4276"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anders S\u00f8gaard","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.1973,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.95154101,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5258","last_page":"5262"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13243","display_name":"Innovation in Digital Healthcare Systems","score":0.692300021648407,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T13243","display_name":"Innovation in Digital Healthcare Systems","score":0.692300021648407,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6029000282287598,"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":0.5800999999046326,"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/leverage","display_name":"Leverage (statistics)","score":0.612500011920929},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5958999991416931},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5331000089645386},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.42260000109672546},{"id":"https://openalex.org/keywords/bengali","display_name":"Bengali","score":0.37959998846054077},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.37549999356269836},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.36250001192092896},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.34549999237060547}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6779999732971191},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.612500011920929},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5958999991416931},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5442000031471252},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5331000089645386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49470001459121704},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4803999960422516},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.42260000109672546},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41350001096725464},{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.37959998846054077},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.37549999356269836},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.36250001192092896},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.34549999237060547},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C11693617","wikidata":"https://www.wikidata.org/wiki/Q181839","display_name":"Pragmatics","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2581999897956848},{"id":"https://openalex.org/C2777853878","wikidata":"https://www.wikidata.org/wiki/Q743569","display_name":"Phonetic transcription","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-1789","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/95e4f1cf-c2d9-4005-aa65-3585e382a8fc","is_oa":true,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/95e4f1cf-c2d9-4005-aa65-3585e382a8fc","pdf_url":null,"source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Maji , B , Swain , M , Nasreen , S , Majumdar , D , Guha , R , Routray , A & S\u00f8gaard , A 2025 , A Study on The Impact of Foundation Models on Automatic Depression Detection from Speech Signals . in Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH . International Speech Communication Association , pp. 5258-5262 , 26th Interspeech Conference 2025 , Rotterdam , Netherlands , 17/08/2025 . https://doi.org/10.21437/Interspeech.2025-1789","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/95e4f1cf-c2d9-4005-aa65-3585e382a8fc","is_oa":true,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/95e4f1cf-c2d9-4005-aa65-3585e382a8fc","pdf_url":null,"source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Maji , B , Swain , M , Nasreen , S , Majumdar , D , Guha , R , Routray , A & S\u00f8gaard , A 2025 , A Study on The Impact of Foundation Models on Automatic Depression Detection from Speech Signals . in Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH . International Speech Communication Association , pp. 5258-5262 , 26th Interspeech Conference 2025 , Rotterdam , Netherlands , 17/08/2025 . https://doi.org/10.21437/Interspeech.2025-1789","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"An":[0],"automatic":[1,70],"depression":[2],"detection":[3],"(ADD)":[4],"system":[5],"using":[6],"spoken":[7],"language":[8,80,125],"offers":[9],"the":[10,91,110],"opportunity":[11],"to":[12,17,58,108],"develop":[13],"practical,":[14],"low-cost":[15],"tools":[16],"detect":[18],"symptoms":[19],"early.":[20],"However,":[21],"limited":[22],"data":[23],"availability,":[24],"privacy":[25],"concerns,":[26],"and":[27,41,67,72,75,96,105,124],"transcription":[28,71],"efforts":[29],"pose":[30],"significant":[31],"challenges.":[32],"Recent":[33],"advancements":[34],"in":[35,115],"foundational":[36],"models,":[37],"capable":[38],"of":[39,93,112],"understanding":[40],"processing":[42],"multimodal":[43],"inputs,":[44],"present":[45],"opportunities":[46],"for":[47,69],"enhancing":[48],"ADD":[49],"systems.":[50],"This":[51],"study":[52],"explores":[53],"various":[54],"speech":[55,74,123],"foundation":[56,126],"models":[57,127,130],"investigate":[59],"their":[60],"impact":[61],"on":[62,99,131],"ADD.":[63],"We":[64,102],"leverage":[65],"Whisper":[66],"MMS":[68],"integrate":[73],"text":[76],"embeddings":[77],"into":[78],"a":[79],"model":[81,100],"optimized":[82],"with":[83,118],"low-rank":[84],"adaptation":[85],"(LoRA).":[86],"In":[87],"addition,":[88],"we":[89],"examine":[90],"effects":[92],"fine-tuning":[94],"strategies":[95],"prompt":[97],"formats":[98],"performance.":[101],"used":[103],"English":[104],"Bengali":[106],"datasets":[107],"demonstrate":[109],"potential":[111],"our":[113],"method":[114],"ADD,":[116],"even":[117],"moderate-quality":[119],"transcriptions.":[120],"The":[121],"best":[122],"outperform":[128],"baseline":[129],"both":[132],"datasets.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-24T00:00:00"}