{"id":"https://openalex.org/W4405633283","doi":"https://doi.org/10.1109/o-cocosda64382.2024.10800478","title":"Depression Classification Using Log-Mel Spectrograms: A Comparative Analysis of Window Size-Based Data Augmentation and Deep Learning Models","display_name":"Depression Classification Using Log-Mel Spectrograms: A Comparative Analysis of Window Size-Based Data Augmentation and Deep Learning Models","publication_year":2024,"publication_date":"2024-10-17","ids":{"openalex":"https://openalex.org/W4405633283","doi":"https://doi.org/10.1109/o-cocosda64382.2024.10800478"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda64382.2024.10800478","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda64382.2024.10800478","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5062749267","display_name":"Lokesh Kumar","orcid":"https://orcid.org/0000-0001-7544-9329"},"institutions":[{"id":"https://openalex.org/I4210152718","display_name":"Indian Institute of Technology Dharwad","ror":"https://ror.org/0509djg30","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210152718"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Lokesh Kumar","raw_affiliation_strings":["Indian Institute of Technology Dharwad,Department of Electrical, Electronics and Communication Engineering,Dharwad,India,580007"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Dharwad,Department of Electrical, Electronics and Communication Engineering,Dharwad,India,580007","institution_ids":["https://openalex.org/I4210152718"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022711580","display_name":"Kumar Kaustubh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152718","display_name":"Indian Institute of Technology Dharwad","ror":"https://ror.org/0509djg30","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210152718"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kumar Kaustubh","raw_affiliation_strings":["Indian Institute of Technology Dharwad,Department of Electrical, Electronics and Communication Engineering,Dharwad,India,580007"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Dharwad,Department of Electrical, Electronics and Communication Engineering,Dharwad,India,580007","institution_ids":["https://openalex.org/I4210152718"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041008413","display_name":"Shashaank Aswatha Mattur","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152718","display_name":"Indian Institute of Technology Dharwad","ror":"https://ror.org/0509djg30","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210152718"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shashaank Aswatha Mattur","raw_affiliation_strings":["Indian Institute of Technology Dharwad,Department of Electrical, Electronics and Communication Engineering,Dharwad,India,580007"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Dharwad,Department of Electrical, Electronics and Communication Engineering,Dharwad,India,580007","institution_ids":["https://openalex.org/I4210152718"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052129812","display_name":"S. R. Mahadeva Prasanna","orcid":"https://orcid.org/0000-0002-8135-7938"},"institutions":[{"id":"https://openalex.org/I4210152718","display_name":"Indian Institute of Technology Dharwad","ror":"https://ror.org/0509djg30","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210152718"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S. R. Mahadeva Prasanna","raw_affiliation_strings":["Indian Institute of Technology Dharwad,Department of Electrical, Electronics and Communication Engineering,Dharwad,India,580007"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Dharwad,Department of Electrical, Electronics and Communication Engineering,Dharwad,India,580007","institution_ids":["https://openalex.org/I4210152718"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210152718"],"apc_list":null,"apc_paid":null,"fwci":1.4603,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.84020292,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.7175999879837036,"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":0.7175999879837036,"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/T13283","display_name":"Mental Health Research Topics","score":0.6532999873161316,"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/T11519","display_name":"Digital Mental Health Interventions","score":0.6147000193595886,"subfield":{"id":"https://openalex.org/subfields/3202","display_name":"Applied 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/spectrogram","display_name":"Spectrogram","score":0.8820782899856567},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6276169419288635},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.5907148718833923},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5236718058586121},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47459718585014343},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.46532484889030457}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8820782899856567},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6276169419288635},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.5907148718833923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5236718058586121},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47459718585014343},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.46532484889030457},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda64382.2024.10800478","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda64382.2024.10800478","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1581105046","https://openalex.org/W1970528430","https://openalex.org/W2003502731","https://openalex.org/W2064057822","https://openalex.org/W2103285140","https://openalex.org/W2169217816","https://openalex.org/W2194775991","https://openalex.org/W2330219538","https://openalex.org/W2889056793","https://openalex.org/W3005688888","https://openalex.org/W3145157056","https://openalex.org/W3197558301","https://openalex.org/W4224924082","https://openalex.org/W4283219344","https://openalex.org/W4378364420","https://openalex.org/W4388854246","https://openalex.org/W4391547665","https://openalex.org/W6637373629","https://openalex.org/W6762718338"],"related_works":["https://openalex.org/W2731899572","https://openalex.org/W3215138031","https://openalex.org/W3009238340","https://openalex.org/W4360585206","https://openalex.org/W4321369474","https://openalex.org/W4285208911","https://openalex.org/W3082895349","https://openalex.org/W4213079790","https://openalex.org/W2248239756","https://openalex.org/W3086377361"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,27,112],"presents":[4],"an":[5,24,114],"innovative":[6],"approach":[7],"to":[8,35],"detecting":[9],"depression":[10,58],"by":[11],"analyzing":[12],"log-mel":[13,88],"spectrograms":[14],"from":[15],"speech":[16],"recordings":[17],"of":[18,116,121],"depressed":[19,126],"and":[20,39,65,69,96,105,118,123,127,140],"non-depressed":[21,128],"speakers.":[22],"As":[23],"augmentation":[25],"strategy,":[26],"leverage":[28],"multiple":[29,74],"window":[30,75],"sizes":[31,76],"for":[32,45,125],"spectrogram":[33],"generation":[34],"address":[36],"class":[37],"imbalance":[38],"explore":[40],"various":[41],"deep":[42],"learning":[43],"models":[44],"binary":[46],"classification.":[47],"U":[48],"sing":[49],"the":[50,109],"Emotion":[51],"Audio-Textual":[52],"Depression":[53],"corpus(EATD-Corpus),":[54],"a":[55],"Chinese":[56],"language":[57],"dataset,":[59],"four":[60],"models,":[61],"VGG-16,":[62],"ResNet50,":[63],"EfficientNet,":[64],"ConvMixer,":[66],"were":[67],"trained":[68],"compared.":[70],"Results":[71],"show":[72],"that":[73],"significantly":[77],"enhance":[78],"classification":[79],"accuracy,":[80],"with":[81],"ConvMixer":[82,110],"performing":[83],"exceptionally":[84],"well":[85],"on":[86],"multi-resolution":[87],"spectrograms.":[89],"Smaller":[90],"windows":[91,101],"capture":[92],"finer":[93],"temporal":[94],"details":[95],"high-frequency":[97],"content,":[98],"while":[99],"larger":[100],"improve":[102],"frequency":[103],"resolution":[104],"low-frequency":[106],"information.":[107],"For":[108],"model,":[111],"achieved":[113],"accuracy":[115],"80.90%":[117],"F-l":[119],"scores":[120],"0.79":[122],"0.82":[124],"classes,":[129],"respectively.":[130],"This":[131],"research":[132],"offers":[133],"valuable":[134],"insights":[135],"into":[136],"mental":[137],"health":[138],"diagnostics":[139],"could":[141],"aid":[142],"professionals":[143],"in":[144],"more":[145],"efficient":[146],"diagnostics.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}