{"id":"https://openalex.org/W3030135760","doi":"https://doi.org/10.1109/access.2020.2998532","title":"Recognition of Audio Depression Based on Convolutional Neural Network and Generative Antagonism Network Model","display_name":"Recognition of Audio Depression Based on Convolutional Neural Network and Generative Antagonism Network Model","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3030135760","doi":"https://doi.org/10.1109/access.2020.2998532","mag":"3030135760"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.2998532","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2998532","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09103527.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09103527.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007217610","display_name":"Zhiyong Wang","orcid":"https://orcid.org/0000-0001-8717-2320"},"institutions":[{"id":"https://openalex.org/I4210150411","display_name":"Shandong Youth University of Political Science","ror":"https://ror.org/04bwp4t29","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210150411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Wang","raw_affiliation_strings":["School of Information Engineering, Shandong Youth University of Political Science, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0001-8717-2320","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Shandong Youth University of Political Science, Jinan, China","institution_ids":["https://openalex.org/I4210150411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045691270","display_name":"Longxi Chen","orcid":"https://orcid.org/0000-0001-5545-4227"},"institutions":[{"id":"https://openalex.org/I4210150411","display_name":"Shandong Youth University of Political Science","ror":"https://ror.org/04bwp4t29","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210150411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longxi Chen","raw_affiliation_strings":["School of Information Engineering, Shandong Youth University of Political Science, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0001-5545-4227","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Shandong Youth University of Political Science, Jinan, China","institution_ids":["https://openalex.org/I4210150411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101435826","display_name":"Lifeng Wang","orcid":"https://orcid.org/0000-0003-1937-6676"},"institutions":[{"id":"https://openalex.org/I4210150411","display_name":"Shandong Youth University of Political Science","ror":"https://ror.org/04bwp4t29","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210150411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lifeng Wang","raw_affiliation_strings":["School of Information Engineering, Shandong Youth University of Political Science, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0003-1937-6676","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Shandong Youth University of Political Science, Jinan, China","institution_ids":["https://openalex.org/I4210150411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044899323","display_name":"Guangqiang Diao","orcid":"https://orcid.org/0000-0001-5655-2179"},"institutions":[{"id":"https://openalex.org/I4210150411","display_name":"Shandong Youth University of Political Science","ror":"https://ror.org/04bwp4t29","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210150411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangqiang Diao","raw_affiliation_strings":["School of Information Engineering, Shandong Youth University of Political Science, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0001-5655-2179","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Shandong Youth University of Political Science, Jinan, China","institution_ids":["https://openalex.org/I4210150411"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210150411"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":3.1862,"has_fulltext":true,"cited_by_count":56,"citation_normalized_percentile":{"value":0.92148979,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"8","issue":null,"first_page":"101181","last_page":"101191"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9871000051498413,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9779000282287598,"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/computer-science","display_name":"Computer science","score":0.7786637544631958},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6964640021324158},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5934417843818665},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5862751007080078},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5589120388031006},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5326558947563171},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5145470499992371},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.49898219108581543},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4612966477870941},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4564530849456787},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43076905608177185},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0910501480102539}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7786637544631958},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6964640021324158},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5934417843818665},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5862751007080078},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5589120388031006},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5326558947563171},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5145470499992371},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.49898219108581543},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4612966477870941},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4564530849456787},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43076905608177185},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0910501480102539},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2020.2998532","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2998532","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09103527.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:b403c8a1521d4f0db787c3c149015d85","is_oa":true,"landing_page_url":"https://doaj.org/article/b403c8a1521d4f0db787c3c149015d85","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 8, Pp 101181-101191 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2020.2998532","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2998532","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09103527.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3055100047","display_name":null,"funder_award_id":"ZR2016AM30","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"}],"funders":[{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null},{"id":"https://openalex.org/F4320329039","display_name":"Project of Shandong Province Higher Educational Science and Technology Program","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3030135760.pdf","grobid_xml":"https://content.openalex.org/works/W3030135760.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W2059595024","https://openalex.org/W2076462394","https://openalex.org/W2185887892","https://openalex.org/W2530421149","https://openalex.org/W2703895418","https://openalex.org/W2761246525","https://openalex.org/W2783626667","https://openalex.org/W2789362687","https://openalex.org/W2792217252","https://openalex.org/W2792311129","https://openalex.org/W2794939173","https://openalex.org/W2802052157","https://openalex.org/W2804686008","https://openalex.org/W2808939837","https://openalex.org/W2809002127","https://openalex.org/W2811186547","https://openalex.org/W2883281347","https://openalex.org/W2889325879","https://openalex.org/W2889717020","https://openalex.org/W2896866882","https://openalex.org/W2912789162","https://openalex.org/W2913459771","https://openalex.org/W2913960490","https://openalex.org/W2918334830","https://openalex.org/W2927999579","https://openalex.org/W2941951094","https://openalex.org/W2948893225","https://openalex.org/W2964440321","https://openalex.org/W2972404972","https://openalex.org/W3005452635","https://openalex.org/W6759692689"],"related_works":["https://openalex.org/W2349769824","https://openalex.org/W2914532148","https://openalex.org/W2591697403","https://openalex.org/W2944728705","https://openalex.org/W4252379076","https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W2422472940","https://openalex.org/W2019475500","https://openalex.org/W2548162870"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"an":[3],"audio":[4,41,65,144],"depression":[5,110,162],"recognition":[6,111,126,163],"method":[7,158],"based":[8,63,93],"on":[9,64,94,149,177],"convolution":[10],"neural":[11],"network":[12,16],"and":[13,34,58,99,124,140,151,170,173],"generative":[14],"antagonism":[15],"model.":[17],"First":[18],"of":[19,46,80,97,109,116,134],"all,":[20],"preprocess":[21],"the":[22,26,31,36,44,77,81,86,95,107,114,119,125,131,135,142,156,161,171,178,184],"data":[23,32,87],"set,":[24,33],"remove":[25],"long-term":[27],"mute":[28],"segments":[29,138],"in":[30],"splice":[35],"rest":[37],"into":[38],"a":[39],"new":[40],"file.":[42],"Then,":[43,92],"features":[45],"speech":[47],"signal,":[48],"such":[49],"as":[50],"Mel-scale":[51],"Frequency":[52],"Cepstral":[53],"Coefficients":[54],"(MFCCs),":[55],"short-term":[56],"energy":[57],"spectral":[59],"entropy,":[60],"are":[61,181],"extracted":[62,70],"difference":[66],"normalization":[67,132],"algorithm.":[68],"The":[69,146],"matrix":[71],"vector":[72],"feature":[73],"data,":[74],"which":[75],"represents":[76],"unique":[78],"attributes":[79],"subjects'":[82],"own":[83],"voice,":[84],"is":[85,103,122,128],"base":[88],"for":[89],"model":[90,108,121],"training.":[91],"combination":[96],"CNN":[98],"GAN,":[100],"DR":[101,117],"AudioNet":[102],"used":[104],"to":[105],"build":[106],"research.":[112],"With":[113],"help":[115],"AudioNet,":[118],"former":[120],"optimized":[123],"classification":[127],"completed":[129],"through":[130],"characteristics":[133],"two":[136,179],"adjacent":[137],"before":[139],"after":[141],"current":[143],"segment.":[145],"experimental":[147],"results":[148],"AViD-Corpus":[150],"DAIC-WOZ":[152],"datasets":[153,180],"show":[154],"that":[155],"proposed":[157],"effectively":[159],"reduces":[160],"error":[164],"compared":[165],"with":[166],"other":[167],"existing":[168],"methods,":[169],"RMSE":[172],"MAE":[174],"values":[175],"obtained":[176],"better":[182],"than":[183,189],"comparison":[185],"algorithm":[186],"by":[187],"more":[188],"5%.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":7}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}