{"id":"https://openalex.org/W4375929004","doi":"https://doi.org/10.1109/tcds.2023.3273614","title":"Spatial\u2013Temporal Feature Network for Speech-Based Depression Recognition","display_name":"Spatial\u2013Temporal Feature Network for Speech-Based Depression Recognition","publication_year":2023,"publication_date":"2023-05-08","ids":{"openalex":"https://openalex.org/W4375929004","doi":"https://doi.org/10.1109/tcds.2023.3273614"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2023.3273614","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2023.3273614","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cognitive and Developmental Systems","raw_type":"journal-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/A5109604925","display_name":"Zhuojin Han","orcid":null},"institutions":[{"id":"https://openalex.org/I96852419","display_name":"Capital Normal University","ror":"https://ror.org/005edt527","country_code":"CN","type":"education","lineage":["https://openalex.org/I96852419"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhuojin Han","raw_affiliation_strings":["College of Information Engineering and the Beijing Key Laboratory of Electronic System Reliability Technology, Capital Normal University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"College of Information Engineering and the Beijing Key Laboratory of Electronic System Reliability Technology, Capital Normal University, Beijing, China","institution_ids":["https://openalex.org/I96852419"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101924786","display_name":"Yuanyuan Shang","orcid":"https://orcid.org/0000-0003-3135-0348"},"institutions":[{"id":"https://openalex.org/I96852419","display_name":"Capital Normal University","ror":"https://ror.org/005edt527","country_code":"CN","type":"education","lineage":["https://openalex.org/I96852419"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanyuan Shang","raw_affiliation_strings":["College of Information Engineering and the Beijing Key Laboratory of Electronic System Reliability Technology, Capital Normal University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"College of Information Engineering and the Beijing Key Laboratory of Electronic System Reliability Technology, Capital Normal University, Beijing, China","institution_ids":["https://openalex.org/I96852419"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026412163","display_name":"Zhuhong Shao","orcid":"https://orcid.org/0000-0002-4847-282X"},"institutions":[{"id":"https://openalex.org/I96852419","display_name":"Capital Normal University","ror":"https://ror.org/005edt527","country_code":"CN","type":"education","lineage":["https://openalex.org/I96852419"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuhong Shao","raw_affiliation_strings":["College of Information Engineering and the Beijing Engineering Research Center of Highly Reliable Embedded System, Capital Normal University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"College of Information Engineering and the Beijing Engineering Research Center of Highly Reliable Embedded System, Capital Normal University, Beijing, China","institution_ids":["https://openalex.org/I96852419"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100434412","display_name":"Jingyi Liu","orcid":"https://orcid.org/0000-0001-6251-6051"},"institutions":[{"id":"https://openalex.org/I96852419","display_name":"Capital Normal University","ror":"https://ror.org/005edt527","country_code":"CN","type":"education","lineage":["https://openalex.org/I96852419"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyi Liu","raw_affiliation_strings":["School of Mathematical Sciences and the Beijing Key Laboratory of Electronic System Reliability Technology, Capital Normal University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences and the Beijing Key Laboratory of Electronic System Reliability Technology, Capital Normal University, Beijing, China","institution_ids":["https://openalex.org/I96852419"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085022758","display_name":"Guodong Guo","orcid":"https://orcid.org/0000-0001-9583-0055"},"institutions":[{"id":"https://openalex.org/I12097938","display_name":"West Virginia University","ror":"https://ror.org/011vxgd24","country_code":"US","type":"education","lineage":["https://openalex.org/I12097938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guodong Guo","raw_affiliation_strings":["Lane Department of Computer Science and Electrical Engineering, West Virginia University, Morgantown, WV, USA"],"affiliations":[{"raw_affiliation_string":"Lane Department of Computer Science and Electrical Engineering, West Virginia University, Morgantown, WV, USA","institution_ids":["https://openalex.org/I12097938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101406961","display_name":"Tie Liu","orcid":"https://orcid.org/0000-0002-3251-0158"},"institutions":[{"id":"https://openalex.org/I96852419","display_name":"Capital Normal University","ror":"https://ror.org/005edt527","country_code":"CN","type":"education","lineage":["https://openalex.org/I96852419"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tie Liu","raw_affiliation_strings":["College of Information Engineering and the Beijing Engineering Research Center of Highly Reliable Embedded System, Capital Normal University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"College of Information Engineering and the Beijing Engineering Research Center of Highly Reliable Embedded System, Capital Normal University, Beijing, China","institution_ids":["https://openalex.org/I96852419"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027989885","display_name":"Hui Ding","orcid":"https://orcid.org/0000-0002-1920-7613"},"institutions":[{"id":"https://openalex.org/I96852419","display_name":"Capital Normal University","ror":"https://ror.org/005edt527","country_code":"CN","type":"education","lineage":["https://openalex.org/I96852419"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Ding","raw_affiliation_strings":["College of Information Engineering and the Beijing Engineering Research Center of Highly Reliable Embedded System, Capital Normal University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"College of Information Engineering and the Beijing Engineering Research Center of Highly Reliable Embedded System, Capital Normal University, Beijing, China","institution_ids":["https://openalex.org/I96852419"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101406449","display_name":"Qiang Hu","orcid":"https://orcid.org/0000-0002-7793-4835"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiang Hu","raw_affiliation_strings":["Department of Psychiatry, Zhenjiang Mental Health Center, Zhenjiang, China"],"affiliations":[{"raw_affiliation_string":"Department of Psychiatry, Zhenjiang Mental Health Center, Zhenjiang, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5109604925"],"corresponding_institution_ids":["https://openalex.org/I96852419"],"apc_list":null,"apc_paid":null,"fwci":13.8664,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":{"value":0.99199767,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"16","issue":"1","first_page":"308","last_page":"318"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9886000156402588,"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":0.9886000156402588,"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":0.9794999957084656,"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":0.8357740640640259},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5462212562561035},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5020253658294678},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.45936697721481323},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45264533162117004},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4440964460372925},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34940049052238464},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.0814085602760315}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8357740640640259},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5462212562561035},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5020253658294678},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.45936697721481323},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45264533162117004},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4440964460372925},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34940049052238464},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0814085602760315},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcds.2023.3273614","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2023.3273614","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cognitive and Developmental Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5092572783","display_name":null,"funder_award_id":"61876112","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6462025472","display_name":null,"funder_award_id":"61601311","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8612635382","display_name":null,"funder_award_id":"L201022","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1976066595","https://openalex.org/W1988008186","https://openalex.org/W2000149402","https://openalex.org/W2003502731","https://openalex.org/W2084253467","https://openalex.org/W2085662862","https://openalex.org/W2148562040","https://openalex.org/W2182295029","https://openalex.org/W2346454595","https://openalex.org/W2519531315","https://openalex.org/W2527824850","https://openalex.org/W2529925562","https://openalex.org/W2530421149","https://openalex.org/W2530431529","https://openalex.org/W2570412145","https://openalex.org/W2751214333","https://openalex.org/W2765407302","https://openalex.org/W2767043218","https://openalex.org/W2786906276","https://openalex.org/W2790748806","https://openalex.org/W2800833042","https://openalex.org/W2805409402","https://openalex.org/W2811099934","https://openalex.org/W2889056793","https://openalex.org/W2910141578","https://openalex.org/W2913434130","https://openalex.org/W2935705121","https://openalex.org/W2936774411","https://openalex.org/W2946585360","https://openalex.org/W2978855205","https://openalex.org/W2979476256","https://openalex.org/W2981501230","https://openalex.org/W2981660166","https://openalex.org/W2981677410","https://openalex.org/W2981882673","https://openalex.org/W2994403800","https://openalex.org/W3003922336","https://openalex.org/W3013235873","https://openalex.org/W3013492814","https://openalex.org/W3015554124","https://openalex.org/W3036601975","https://openalex.org/W3049426073","https://openalex.org/W3094644839","https://openalex.org/W3096709787","https://openalex.org/W3101080567","https://openalex.org/W3117337246","https://openalex.org/W3134427999","https://openalex.org/W3155665398","https://openalex.org/W3161731123","https://openalex.org/W3197558301","https://openalex.org/W3197994565","https://openalex.org/W3198860978","https://openalex.org/W3206733826","https://openalex.org/W4206144048","https://openalex.org/W4287068505","https://openalex.org/W6676218802","https://openalex.org/W6691669583","https://openalex.org/W6748532171","https://openalex.org/W6769196770","https://openalex.org/W6780218876","https://openalex.org/W6785262015","https://openalex.org/W6798417457"],"related_works":["https://openalex.org/W2560215812","https://openalex.org/W2949601986","https://openalex.org/W2788972299","https://openalex.org/W2521347458","https://openalex.org/W2498789492","https://openalex.org/W2729981612","https://openalex.org/W4233449973","https://openalex.org/W2925692864","https://openalex.org/W2972212393","https://openalex.org/W4386159726"],"abstract_inverted_index":{"Depression":[0],"is":[1],"a":[2,74,83],"serious":[3],"mental":[4],"disorder":[5],"that":[6,189],"has":[7],"received":[8],"increased":[9],"attention":[10],"from":[11],"society.":[12],"Due":[13],"to":[14,25,72,94,120,126,154,172,218],"the":[15,41,53,64,104,110,118,134,145,156,163,169,190,195,204,211],"advantage":[16],"of":[17,20,68,140,160,165,197,206],"easy":[18],"acquisition":[19],"speech,":[21,161],"researchers":[22],"have":[23],"tried":[24],"propose":[26,52],"various":[27],"automatic":[28],"depression":[29,46,59,79,198],"recognition":[30],"algorithms":[31],"based":[32],"on":[33,177],"speech.":[34],"Feature":[35],"selection":[36],"and":[37,98,123,184,213],"algorithm":[38],"design":[39],"are":[40,115],"main":[42],"difficulties":[43],"in":[44,109,117,152],"speech-based":[45],"recognition.":[47,199],"In":[48,137],"our":[49,142,207],"work,":[50],"we":[51,81],"spatial\u2013temporal":[54],"feature":[55,76,112],"network":[56,114,170],"(STFN)":[57],"for":[58,78],"recognition,":[60],"which":[61],"can":[62],"capture":[63,127,155],"long-term":[65,157],"temporal":[66,158],"dependence":[67],"audio":[69],"sequences.":[70],"First,":[71],"obtain":[73],"better":[75],"representation":[77],"analysis,":[80],"develop":[82],"self-supervised":[84],"learning":[85],"framework,":[86],"called":[87],"vector":[88],"quantized":[89],"wav2vec":[90],"transformer":[91],"net":[92],"(VQWTNet)":[93],"map":[95],"speech":[96],"features":[97],"phonemes":[99],"with":[100],"transfer":[101],"learning.":[102],"Second,":[103],"stacked":[105],"gated":[106],"residual":[107],"blocks":[108],"spatial":[111],"extraction":[113],"used":[116],"model":[119,192],"integrate":[121],"causal":[122],"dilated":[124],"convolutions":[125],"multiscale":[128],"contextual":[129],"information":[130],"by":[131],"continuously":[132],"expanding":[133],"receptive":[135],"field.":[136],"addition,":[138],"instead":[139],"LSTM,":[141],"method":[143,208],"employs":[144],"hierarchical":[146],"contrastive":[147],"predictive":[148],"coding":[149],"(HCPC)":[150],"loss":[151],"HCPCNet":[153],"dependencies":[159],"reducing":[162],"number":[164],"parameters":[166],"while":[167],"making":[168],"easier":[171],"train.":[173],"Finally,":[174],"experimental":[175],"results":[176,216],"DAIC-WOZ":[178],"(Audio/Visual":[179],"Emotion":[180],"Challenge":[181],"(AVEC)":[182],"2017)":[183],"E-DAIC":[185],"(AVEC":[186],"2019)":[187],"show":[188],"proposed":[191],"significantly":[193],"improves":[194],"accuracy":[196],"On":[200],"both":[201],"data":[202],"sets,":[203],"performance":[205],"far":[209],"exceeds":[210],"baseline":[212],"achieves":[214],"competitive":[215],"compared":[217],"state-of-the-art":[219],"methods.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":33},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}