{"id":"https://openalex.org/W3022125708","doi":"https://doi.org/10.3233/jifs-191129","title":"Emotion recognition from speech using deep learning on spectrograms","display_name":"Emotion recognition from speech using deep learning on spectrograms","publication_year":2020,"publication_date":"2020-05-06","ids":{"openalex":"https://openalex.org/W3022125708","doi":"https://doi.org/10.3233/jifs-191129","mag":"3022125708"},"language":"en","primary_location":{"id":"doi:10.3233/jifs-191129","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jifs-191129","pdf_url":null,"source":{"id":"https://openalex.org/S179157397","display_name":"Journal of Intelligent & Fuzzy Systems","issn_l":"1064-1246","issn":["1064-1246","1875-8967"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent & Fuzzy 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/A5101678769","display_name":"Xingguang Li","orcid":"https://orcid.org/0000-0002-5964-8843"},"institutions":[{"id":"https://openalex.org/I106645853","display_name":"Changchun University of Science and Technology","ror":"https://ror.org/007mntk44","country_code":"CN","type":"education","lineage":["https://openalex.org/I106645853"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xingguang Li","raw_affiliation_strings":["Electronic Information Engineering, Changchun University of Science and Technology, Changchun, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronic Information Engineering, Changchun University of Science and Technology, Changchun, China","institution_ids":["https://openalex.org/I106645853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082889003","display_name":"Wenjun Song","orcid":"https://orcid.org/0009-0005-1111-2774"},"institutions":[{"id":"https://openalex.org/I106645853","display_name":"Changchun University of Science and Technology","ror":"https://ror.org/007mntk44","country_code":"CN","type":"education","lineage":["https://openalex.org/I106645853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjun Song","raw_affiliation_strings":["Electronic Information Engineering, Changchun University of Science and Technology, Changchun, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronic Information Engineering, Changchun University of Science and Technology, Changchun, China","institution_ids":["https://openalex.org/I106645853"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025331274","display_name":"Zonglin Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I106645853","display_name":"Changchun University of Science and Technology","ror":"https://ror.org/007mntk44","country_code":"CN","type":"education","lineage":["https://openalex.org/I106645853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zonglin Liang","raw_affiliation_strings":["Electronic Information Engineering, Changchun University of Science and Technology, Changchun, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronic Information Engineering, Changchun University of Science and Technology, Changchun, China","institution_ids":["https://openalex.org/I106645853"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101678769"],"corresponding_institution_ids":["https://openalex.org/I106645853"],"apc_list":null,"apc_paid":null,"fwci":0.8606,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.75017853,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"39","issue":"3","first_page":"2791","last_page":"2796"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9990000128746033,"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":0.9990000128746033,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.989799976348877,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9873999953269958,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7754940986633301},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7090215086936951},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6515196561813354},{"id":"https://openalex.org/keywords/sadness","display_name":"Sadness","score":0.6044568419456482},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4970457851886749},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.49453994631767273},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.460929811000824},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4481651782989502},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4394562542438507},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43788546323776245},{"id":"https://openalex.org/keywords/anger","display_name":"Anger","score":0.43279320001602173},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.334480345249176},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3194092810153961},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10164517164230347}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7754940986633301},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7090215086936951},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6515196561813354},{"id":"https://openalex.org/C2779812673","wikidata":"https://www.wikidata.org/wiki/Q169251","display_name":"Sadness","level":3,"score":0.6044568419456482},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4970457851886749},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.49453994631767273},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.460929811000824},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4481651782989502},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4394562542438507},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43788546323776245},{"id":"https://openalex.org/C2779302386","wikidata":"https://www.wikidata.org/wiki/Q79871","display_name":"Anger","level":2,"score":0.43279320001602173},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.334480345249176},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3194092810153961},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10164517164230347},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/jifs-191129","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jifs-191129","pdf_url":null,"source":{"id":"https://openalex.org/S179157397","display_name":"Journal of Intelligent & Fuzzy Systems","issn_l":"1064-1246","issn":["1064-1246","1875-8967"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent & Fuzzy Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.47999998927116394,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1483870316","https://openalex.org/W1600744878","https://openalex.org/W1922655562","https://openalex.org/W1994885532","https://openalex.org/W2046056978","https://openalex.org/W2047337856","https://openalex.org/W2087618018","https://openalex.org/W2193413348","https://openalex.org/W2295001676","https://openalex.org/W2339850901","https://openalex.org/W2398826216","https://openalex.org/W2399733683","https://openalex.org/W2408520939","https://openalex.org/W2422305492","https://openalex.org/W2570343428","https://openalex.org/W2579985080","https://openalex.org/W2583743457","https://openalex.org/W2747664154","https://openalex.org/W2803098682","https://openalex.org/W2889544113","https://openalex.org/W2889717020","https://openalex.org/W2949640717","https://openalex.org/W2962756039","https://openalex.org/W2963037989","https://openalex.org/W2963351448","https://openalex.org/W3106250896","https://openalex.org/W6712560600","https://openalex.org/W6731892127","https://openalex.org/W6732243160","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W2940772629","https://openalex.org/W4379653318","https://openalex.org/W2395256277","https://openalex.org/W4210738660","https://openalex.org/W132246485","https://openalex.org/W1923358586","https://openalex.org/W2938828312","https://openalex.org/W2374332471","https://openalex.org/W2763139457","https://openalex.org/W2959999730"],"abstract_inverted_index":{"In":[0,54],"speech":[1,41,66,71,133],"emotion":[2,42,134,150],"recognition,":[3],"most":[4],"emotional":[5,52],"corpora":[6],"generally":[7],"have":[8],"problems":[9],"such":[10],"as":[11],"inconsistent":[12],"sample":[13,18],"length":[14,28],"and":[15,48,85,90,118,147],"imbalance":[16],"of":[17,44,68,79,97,122,149],"categories.":[19],"Considering":[20],"these":[21],"problems,":[22],"in":[23,50],"this":[24,55],"paper,":[25],"a":[26,58],"variable":[27],"input":[29,64,81,98,101],"CRNN":[30],"deep":[31],"learning":[32],"model":[33],"based":[34],"on":[35],"Focal":[36],"Loss":[37],"is":[38,61,83,100,111],"proposed":[39],"for":[40,105,113],"recognition":[43,135],"anger,":[45],"happiness,":[46],"neutrality":[47],"sadness":[49],"IEMOCAP":[51],"corpus.":[53],"model,":[56,136],"Firstly,":[57],"variable-length":[59],"strategy":[60],"introduced":[62],"to":[63,116,125],"the":[65,69,76,80,94,108,120,126,131,145],"spectra":[67],"filled":[70],"samples":[72,124],"into":[73,102],"CNN.":[74],"Then":[75],"effective":[77,95],"part":[78],"sequence":[82,99],"preserved":[84],"output":[86,96],"by":[87],"masking":[88],"matrix":[89],"convolution":[91],"layer.":[92],"Thirdly,":[93],"BiGRU":[103],"network":[104,114],"learning.":[106],"Finally,":[107],"focal":[109],"loss":[110],"used":[112],"training":[115],"control":[117],"adjust":[119],"contribution":[121],"various":[123],"total":[127],"loss.":[128],"Compared":[129],"with":[130],"traditional":[132],"simulations":[137],"show":[138],"that":[139],"our":[140],"method":[141],"can":[142],"effectively":[143],"improve":[144],"accuracy":[146],"performance":[148],"recognition.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}