{"id":"https://openalex.org/W4406203275","doi":"https://doi.org/10.1587/transinf.2024edl8083","title":"An Interpretable Multi-Level Feature Disentanglement Algorithm for Speech Emotion Recognition","display_name":"An Interpretable Multi-Level Feature Disentanglement Algorithm for Speech Emotion Recognition","publication_year":2025,"publication_date":"2025-01-09","ids":{"openalex":"https://openalex.org/W4406203275","doi":"https://doi.org/10.1587/transinf.2024edl8083"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2024edl8083","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2024edl8083","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/advpub/0/advpub_2024EDL8083/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/advpub/0/advpub_2024EDL8083/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075748715","display_name":"Huawei Tao","orcid":"https://orcid.org/0000-0002-9194-0297"},"institutions":[{"id":"https://openalex.org/I36152291","display_name":"Henan University of Technology","ror":"https://ror.org/05sbgwt55","country_code":"CN","type":"education","lineage":["https://openalex.org/I36152291"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huawei TAO","raw_affiliation_strings":["Key Laboratory of Food Information Processing and Control, Ministry of Education, Henan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Food Information Processing and Control, Ministry of Education, Henan University of Technology","institution_ids":["https://openalex.org/I36152291"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100578537","display_name":"Ziyi Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I36152291","display_name":"Henan University of Technology","ror":"https://ror.org/05sbgwt55","country_code":"CN","type":"education","lineage":["https://openalex.org/I36152291"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyi HU","raw_affiliation_strings":["Key Laboratory of Food Information Processing and Control, Ministry of Education, Henan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Food Information Processing and Control, Ministry of Education, Henan University of Technology","institution_ids":["https://openalex.org/I36152291"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100734294","display_name":"Shuo Li","orcid":"https://orcid.org/0000-0002-2395-6537"},"institutions":[{"id":"https://openalex.org/I36152291","display_name":"Henan University of Technology","ror":"https://ror.org/05sbgwt55","country_code":"CN","type":"education","lineage":["https://openalex.org/I36152291"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sixian LI","raw_affiliation_strings":["Key Laboratory of Food Information Processing and Control, Ministry of Education, Henan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Food Information Processing and Control, Ministry of Education, Henan University of Technology","institution_ids":["https://openalex.org/I36152291"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112506744","display_name":"Chunhua Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I36152291","display_name":"Henan University of Technology","ror":"https://ror.org/05sbgwt55","country_code":"CN","type":"education","lineage":["https://openalex.org/I36152291"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunhua ZHU","raw_affiliation_strings":["Key Laboratory of Food Information Processing and Control, Ministry of Education, Henan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Food Information Processing and Control, Ministry of Education, Henan University of Technology","institution_ids":["https://openalex.org/I36152291"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100432714","display_name":"Peng Li","orcid":"https://orcid.org/0000-0002-5235-6311"},"institutions":[{"id":"https://openalex.org/I36152291","display_name":"Henan University of Technology","ror":"https://ror.org/05sbgwt55","country_code":"CN","type":"education","lineage":["https://openalex.org/I36152291"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng LI","raw_affiliation_strings":["Center for Complexity Science, Henan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Complexity Science, Henan University of Technology","institution_ids":["https://openalex.org/I36152291"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052217750","display_name":"Yue Xie","orcid":"https://orcid.org/0000-0002-5750-5873"},"institutions":[{"id":"https://openalex.org/I2799736854","display_name":"Nanjing Institute of Technology","ror":"https://ror.org/00n6txq60","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799736854"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue XIE","raw_affiliation_strings":["School of Communication Engineering, Nanjing Institute of Technology","the School of Communication Engineering, Nanjing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Communication Engineering, Nanjing Institute of Technology","institution_ids":["https://openalex.org/I2799736854"]},{"raw_affiliation_string":"the School of Communication Engineering, Nanjing Institute of Technology","institution_ids":["https://openalex.org/I2799736854"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9024,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.6673691,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"E108.D","issue":"7","first_page":"841","last_page":"844"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.8306999802589417,"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/T10860","display_name":"Speech and Audio Processing","score":0.8306999802589417,"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":0.8076000213623047,"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":0.8419021368026733},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6761109232902527},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6580319404602051},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.511237382888794},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48889413475990295},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4782625436782837},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3813282549381256},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3210792541503906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8419021368026733},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6761109232902527},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6580319404602051},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.511237382888794},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48889413475990295},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4782625436782837},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3813282549381256},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3210792541503906},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2024edl8083","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2024edl8083","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/advpub/0/advpub_2024EDL8083/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2024edl8083","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2024edl8083","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/advpub/0/advpub_2024EDL8083/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G169177673","display_name":null,"funder_award_id":"2022ZKCJ13","funder_id":"https://openalex.org/F4320321955","funder_display_name":"Henan University of Technology"},{"id":"https://openalex.org/G174787991","display_name":null,"funder_award_id":"62001215","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7446930891","display_name":null,"funder_award_id":"No. 62001215","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/F4320321955","display_name":"Henan University of Technology","ror":"https://ror.org/05sbgwt55"},{"id":"https://openalex.org/F4320322878","display_name":"Henan University","ror":"https://ror.org/003xyzq10"},{"id":"https://openalex.org/F4320327051","display_name":"Science and Technology Department of Henan Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4406203275.pdf"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2146334809","https://openalex.org/W2899361462","https://openalex.org/W3015308237","https://openalex.org/W3168092536","https://openalex.org/W3209984917","https://openalex.org/W4221162793","https://openalex.org/W4282961091","https://openalex.org/W4285106979","https://openalex.org/W4286544676","https://openalex.org/W4312637065","https://openalex.org/W4391407069","https://openalex.org/W4392172995","https://openalex.org/W4392904026","https://openalex.org/W4392904377","https://openalex.org/W4400526612","https://openalex.org/W4402669711"],"related_works":["https://openalex.org/W3147584709","https://openalex.org/W2961085424","https://openalex.org/W2977677679","https://openalex.org/W1992327129","https://openalex.org/W2381986121","https://openalex.org/W2370918718","https://openalex.org/W4224009465","https://openalex.org/W2256933480","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Speech":[0],"Emotion":[1],"Recognition":[2],"(SER)":[3],"plays":[4],"a":[5,52,85,122],"pivotal":[6],"role":[7],"in":[8,102],"human-computer":[9],"interaction,":[10],"yet":[11],"its":[12],"performance":[13],"is":[14,95],"often":[15],"hindered":[16],"by":[17,69],"the":[18,66,70,103,113,128],"nonlinear":[19,100],"entanglement":[20],"of":[21,125],"emotional":[22,63,79],"and":[23,61,77,105],"speaker":[24],"features.":[25],"This":[26],"paper":[27],"proposes":[28],"an":[29],"interpretable":[30],"multi-level":[31,76],"feature":[32,80,108],"disentanglement":[33],"algorithm":[34,49,120],"for":[35],"speech":[36],"emotion":[37,43],"recognition,":[38],"aiming":[39],"to":[40],"effectively":[41],"separate":[42,59],"features":[44,64,67],"from":[45,65],"individual":[46],"speech.":[47],"The":[48],"first":[50],"constructs":[51],"novel":[53],"hybrid":[54],"auto-encoder":[55],"network":[56,72],"that":[57,117],"can":[58],"static":[60],"dynamic":[62],"extracted":[68],"self-supervised":[71],"emotion2vec,":[73],"thereby":[74],"obtaining":[75],"time-varying":[78],"representations.":[81],"Additionally,":[82],"we":[83],"implement":[84],"multi-layer":[86],"perceptual":[87],"classifier":[88],"based":[89],"on":[90,112],"Kolmogorov-Arnold":[91],"Networks":[92],"(KAN),":[93],"which":[94],"adept":[96],"at":[97],"capturing":[98],"complex":[99],"relationships":[101],"data":[104],"further":[106],"promote":[107],"disentanglement.":[109],"Experiments":[110],"results":[111],"IEMOCAP":[114],"database":[115],"show":[116],"our":[118],"proposed":[119],"achieves":[121],"WA":[123],"value":[124],"73.2%,":[126],"surpassing":[127],"current":[129],"state-of-the-art.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-31T23:11:33.660297","created_date":"2025-10-10T00:00:00"}
