{"id":"https://openalex.org/W4406860134","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849284","title":"Speech Depression Recognition from the Selfreference Effect Using LSTM with ResNet","display_name":"Speech Depression Recognition from the Selfreference Effect Using LSTM with ResNet","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406860134","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849284"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10849284","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849284","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5085489048","display_name":"Daimin Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I68986083","display_name":"Northwest Normal University","ror":"https://ror.org/00gx3j908","country_code":"CN","type":"education","lineage":["https://openalex.org/I68986083"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Daimin Shi","raw_affiliation_strings":["Northwest Normal University,School of Physics and Electronic Engineering,Lanzhou,China"],"affiliations":[{"raw_affiliation_string":"Northwest Normal University,School of Physics and Electronic Engineering,Lanzhou,China","institution_ids":["https://openalex.org/I68986083"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112306287","display_name":"Xiaoyong Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I68986083","display_name":"Northwest Normal University","ror":"https://ror.org/00gx3j908","country_code":"CN","type":"education","lineage":["https://openalex.org/I68986083"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyong Lu","raw_affiliation_strings":["Northwest Normal University,School of Physics and Electronic Engineering,Lanzhou,China"],"affiliations":[{"raw_affiliation_string":"Northwest Normal University,School of Physics and Electronic Engineering,Lanzhou,China","institution_ids":["https://openalex.org/I68986083"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002453567","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0002-0420-2211"},"institutions":[{"id":"https://openalex.org/I68986083","display_name":"Northwest Normal University","ror":"https://ror.org/00gx3j908","country_code":"CN","type":"education","lineage":["https://openalex.org/I68986083"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["Northwest Normal University,School of Physics and Electronic Engineering,Lanzhou,China"],"affiliations":[{"raw_affiliation_string":"Northwest Normal University,School of Physics and Electronic Engineering,Lanzhou,China","institution_ids":["https://openalex.org/I68986083"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071836230","display_name":"Jingyi Yuan","orcid":"https://orcid.org/0000-0002-2850-1582"},"institutions":[{"id":"https://openalex.org/I68986083","display_name":"Northwest Normal University","ror":"https://ror.org/00gx3j908","country_code":"CN","type":"education","lineage":["https://openalex.org/I68986083"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyi Yuan","raw_affiliation_strings":["Northwest Normal University,School of Physics and Electronic Engineering,Lanzhou,China"],"affiliations":[{"raw_affiliation_string":"Northwest Normal University,School of Physics and Electronic Engineering,Lanzhou,China","institution_ids":["https://openalex.org/I68986083"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101730104","display_name":"Tao Pan","orcid":"https://orcid.org/0000-0002-6447-8893"},"institutions":[{"id":"https://openalex.org/I68986083","display_name":"Northwest Normal University","ror":"https://ror.org/00gx3j908","country_code":"CN","type":"education","lineage":["https://openalex.org/I68986083"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Pan","raw_affiliation_strings":["Northwest Normal University,School of Physics and Electronic Engineering,Lanzhou,China"],"affiliations":[{"raw_affiliation_string":"Northwest Normal University,School of Physics and Electronic Engineering,Lanzhou,China","institution_ids":["https://openalex.org/I68986083"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5085489048"],"corresponding_institution_ids":["https://openalex.org/I68986083"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32841684,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T10667","display_name":"Emotion and Mood Recognition","score":0.3529999852180481,"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":0.3529999852180481,"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":0.2635999917984009,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.155799999833107,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/residual-neural-network","display_name":"Residual neural network","score":0.8032463192939758},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6664426922798157},{"id":"https://openalex.org/keywords/depression","display_name":"Depression (economics)","score":0.6215709447860718},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5207907557487488},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.4416927695274353},{"id":"https://openalex.org/keywords/audiology","display_name":"Audiology","score":0.4132595360279083},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3829476833343506},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3464324474334717},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.20039579272270203},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.19000965356826782}],"concepts":[{"id":"https://openalex.org/C2944601119","wikidata":"https://www.wikidata.org/wiki/Q43744058","display_name":"Residual neural network","level":3,"score":0.8032463192939758},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6664426922798157},{"id":"https://openalex.org/C2776867660","wikidata":"https://www.wikidata.org/wiki/Q1814941","display_name":"Depression (economics)","level":2,"score":0.6215709447860718},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5207907557487488},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4416927695274353},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.4132595360279083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3829476833343506},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3464324474334717},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.20039579272270203},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.19000965356826782},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10849284","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849284","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2767088461","https://openalex.org/W2786711953","https://openalex.org/W2865118579","https://openalex.org/W2883797124","https://openalex.org/W2889056793","https://openalex.org/W2889717020","https://openalex.org/W2897444637","https://openalex.org/W2903254714","https://openalex.org/W2914070767","https://openalex.org/W2994403800","https://openalex.org/W3003417734","https://openalex.org/W3030135760","https://openalex.org/W3094120200","https://openalex.org/W3197558301","https://openalex.org/W4408343817","https://openalex.org/W6600284362","https://openalex.org/W6674330103","https://openalex.org/W6758413867","https://openalex.org/W6771667380"],"related_works":["https://openalex.org/W2599472179","https://openalex.org/W4323057981","https://openalex.org/W3178607569","https://openalex.org/W4310870954","https://openalex.org/W4308408209","https://openalex.org/W4301783946","https://openalex.org/W3196952692","https://openalex.org/W3177025895","https://openalex.org/W4383503462","https://openalex.org/W3034026275"],"abstract_inverted_index":{"Deep":[0],"neural":[1,55],"networks":[2,79,130],"(DNNs)":[3],"have":[4,14],"recently":[5],"achieved":[6],"great":[7],"success":[8],"in":[9,29,46,67],"various":[10],"learning":[11],"tasks":[12],"and":[13,48,80,95,141],"also":[15],"been":[16],"used":[17],"for":[18,58],"the":[19,30,37,42,50,59,107,115,122,126,135,139,162,173,179],"classification":[20,31],"of":[21,44,52,61,75,128,134,138,168,181],"depression.":[22],"While":[23],"DNNs":[24],"are":[25],"showing":[26],"their":[27],"potential":[28],"task,":[32],"they":[33],"cannot":[34],"fully":[35],"utilize":[36],"temporal":[38],"information.":[39],"To":[40],"mine":[41],"relevance":[43],"signals":[45],"audios":[47],"increase":[49],"diversity":[51],"information,":[53],"a":[54],"network":[56],"architecture":[57],"purpose":[60],"using":[62],"sequential":[63],"information":[64],"is":[65,73],"proposed":[66,71,174],"this":[68],"paper.":[69],"The":[70,99,111],"structure":[72,176],"composed":[74],"two":[76,129],"separated":[77],"lower":[78],"one":[81],"upper":[82],"network.":[83],"We":[84],"refer":[85],"to":[86,131,148],"these":[87],"as":[88],"LSTM":[89,100,140],"layers,":[90,94,97],"Residual":[91],"Networks":[92],"(ResNet)":[93],"connected":[96,123],"respectively.":[98],"layers":[101,113,124],"can":[102,177],"learn":[103,114],"long-term":[104],"dependencies":[105],"from":[106,118],"learned":[108],"local":[109],"features.":[110],"ResNet":[112,142],"spectro-temporal":[116],"locality":[117],"spectrogram":[119],"images.":[120],"Finally,":[121],"summarize":[125],"outputs":[127],"take":[132],"advantage":[133],"complementary":[136],"features":[137],"by":[143],"combining":[144],"them.":[145],"In":[146],"addition":[147],"this,":[149],"we":[150],"experiment":[151],"on":[152,161],"our":[153],"own":[154],"designed":[155,159],"dataset,":[156],"which":[157],"was":[158],"based":[160],"Self-reference":[163],"Effect":[164],"(SRE)":[165],"experimental":[166],"paradigm":[167],"psychology.":[169],"Our":[170],"results":[171],"show":[172],"combination":[175],"improve":[178],"accuracy":[180],"speech":[182],"depression":[183],"recognition.":[184]},"counts_by_year":[],"updated_date":"2026-03-03T08:47:05.690250","created_date":"2025-10-10T00:00:00"}