{"id":"https://openalex.org/W7126080867","doi":"https://doi.org/10.1109/bibm66473.2025.11356469","title":"TFCAF-Net: A Time-Frequency Co-Attentive Fusion Network for Speech-Based Depression Detection","display_name":"TFCAF-Net: A Time-Frequency Co-Attentive Fusion Network for Speech-Based Depression Detection","publication_year":2025,"publication_date":"2025-12-15","ids":{"openalex":"https://openalex.org/W7126080867","doi":"https://doi.org/10.1109/bibm66473.2025.11356469"},"language":null,"primary_location":{"id":"doi:10.1109/bibm66473.2025.11356469","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356469","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","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/A5023438713","display_name":"Zhuoran Liu","orcid":"https://orcid.org/0009-0000-5295-2183"},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhiwei Liu","raw_affiliation_strings":["East China University of Science and Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"East China University of Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I143593769"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124263129","display_name":"Dongdong Li","orcid":null},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongdong Li","raw_affiliation_strings":["East China University of Science and Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"East China University of Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I143593769"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124156460","display_name":"Ke Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I27781120","display_name":"Wenzhou Medical University","ror":"https://ror.org/00rd5t069","country_code":"CN","type":"education","lineage":["https://openalex.org/I27781120"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Zhao","raw_affiliation_strings":["Wenzhou Medical University,Wenzhou,China"],"affiliations":[{"raw_affiliation_string":"Wenzhou Medical University,Wenzhou,China","institution_ids":["https://openalex.org/I27781120"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5023438713"],"corresponding_institution_ids":["https://openalex.org/I143593769"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.75914499,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6708","last_page":"6714"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.8402000069618225,"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":0.8402000069618225,"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":0.08799999952316284,"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/T11519","display_name":"Digital Mental Health Interventions","score":0.016100000590085983,"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/pooling","display_name":"Pooling","score":0.5770000219345093},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5497999787330627},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.47380000352859497},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4489000141620636},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.396699994802475},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.37229999899864197},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.35679998993873596},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.3492000102996826}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7135000228881836},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5770000219345093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.574400007724762},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5497999787330627},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.47380000352859497},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4489000141620636},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42080000042915344},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.396699994802475},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.37229999899864197},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.35679998993873596},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35030001401901245},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.3492000102996826},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3199999928474426},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C131584629","wikidata":"https://www.wikidata.org/wiki/Q4308705","display_name":"Coupling (piping)","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.25690001249313354},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.25529998540878296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm66473.2025.11356469","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356469","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1425916118","display_name":null,"funder_award_id":"ZS2024001","funder_id":"https://openalex.org/F4320324224","funder_display_name":"Wenzhou Municipal Science and Technology Bureau"},{"id":"https://openalex.org/G8628124579","display_name":null,"funder_award_id":"62276098","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324224","display_name":"Wenzhou Municipal Science and Technology Bureau","ror":"https://ror.org/02fr0s482"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2112796928","https://openalex.org/W2157331557","https://openalex.org/W2160815625","https://openalex.org/W2607644382","https://openalex.org/W2767043218","https://openalex.org/W2889056793","https://openalex.org/W2935705121","https://openalex.org/W2946585360","https://openalex.org/W2978855205","https://openalex.org/W3015554124","https://openalex.org/W3038342317","https://openalex.org/W3169801598","https://openalex.org/W3197558301","https://openalex.org/W3205969292","https://openalex.org/W4224916778","https://openalex.org/W4224924082","https://openalex.org/W4285176735","https://openalex.org/W4288804239","https://openalex.org/W4313890099","https://openalex.org/W4375929004","https://openalex.org/W4377292557","https://openalex.org/W4379382378","https://openalex.org/W4385605894","https://openalex.org/W4386813249","https://openalex.org/W4395467463","https://openalex.org/W4413152299","https://openalex.org/W4414480338","https://openalex.org/W7083584513"],"related_works":[],"abstract_inverted_index":{"Speech":[0],"contains":[1],"important":[2],"cues":[3],"related":[4],"to":[5,39,66,105,153],"mental":[6],"health":[7],"status,":[8],"making":[9],"it":[10],"a":[11,51,78,88],"valuable":[12],"signal":[13],"source":[14],"for":[15,147],"automatic":[16],"depression":[17,154],"detection.":[18,155],"However,":[19],"existing":[20,136],"approaches":[21],"often":[22],"exhibit":[23],"insufficient":[24],"modeling":[25],"of":[26,64,74,141],"the":[27,37,108,123,139,142],"coupling":[28],"between":[29],"temporal":[30,60,79],"and":[31,61,87,125],"spectral":[32,62,89],"dynamics":[33,84],"in":[34,85],"speech,":[35],"limiting":[36],"ability":[38],"capture":[40],"their":[41],"complementary":[42,149],"information":[43,151],"associated":[44],"with":[45,135],"depressive":[46],"symptoms.":[47],"This":[48],"paper":[49],"presents":[50],"Time-Frequency":[52,97],"Co-Attentive":[53,98],"Fusion":[54],"Network":[55],"(TFCAF-Net)":[56],"that":[57,81,91,129],"jointly":[58],"models":[59],"representations":[63],"speech":[65,86],"enhance":[67],"detection":[68],"reliability.":[69],"The":[70],"proposed":[71,143],"architecture":[72],"consists":[73],"two":[75,109],"attention-enhanced":[76],"branches:":[77],"branch":[80,90],"captures":[82],"sequential":[83],"focuses":[92],"on":[93,122],"frequency-domain":[94],"characteristics.":[95],"A":[96],"Pooling":[99],"(TFCAP)":[100],"module":[101],"is":[102],"further":[103],"introduced":[104],"adaptively":[106],"integrate":[107],"feature":[110,118],"streams":[111],"through":[112],"attention,":[113],"enabling":[114],"mutual":[115],"guidance":[116],"during":[117],"fusion.":[119],"Experiments":[120],"conducted":[121],"CMDC":[124],"DAIC_WOZ":[126],"datasets":[127],"show":[128],"TFCAF-Net":[130],"achieves":[131],"competitive":[132],"performance":[133],"compared":[134],"baselines,":[137],"validating":[138],"effectiveness":[140],"attention-based":[144],"fusion":[145],"strategy":[146],"capturing":[148],"time-frequency":[150],"relevant":[152]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-30T00:00:00"}