{"id":"https://openalex.org/W4410358460","doi":"https://doi.org/10.1109/lsp.2025.3570245","title":"Multi-Stage Confidence-Guided Diffusion and Emotional Bidirectional Mamba for Robust Speech Emotion Recognition","display_name":"Multi-Stage Confidence-Guided Diffusion and Emotional Bidirectional Mamba for Robust Speech Emotion Recognition","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4410358460","doi":"https://doi.org/10.1109/lsp.2025.3570245"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2025.3570245","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3570245","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","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/A5066331204","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0002-9976-8671"},"institutions":[{"id":"https://openalex.org/I143413998","display_name":"Qingdao University of Science and Technology","ror":"https://ror.org/041j8js14","country_code":"CN","type":"education","lineage":["https://openalex.org/I143413998"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yang Liu","raw_affiliation_strings":["School of Information Science and Technology, Qingdao University of Science and Technology, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0002-9976-8671","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Qingdao University of Science and Technology, Qingdao, China","institution_ids":["https://openalex.org/I143413998"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100724151","display_name":"Xin Chen","orcid":"https://orcid.org/0000-0003-2706-5069"},"institutions":[{"id":"https://openalex.org/I143413998","display_name":"Qingdao University of Science and Technology","ror":"https://ror.org/041j8js14","country_code":"CN","type":"education","lineage":["https://openalex.org/I143413998"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Chen","raw_affiliation_strings":["School of Information Science and Technology, Qingdao University of Science and Technology, Qingdao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Qingdao University of Science and Technology, Qingdao, China","institution_ids":["https://openalex.org/I143413998"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100717753","display_name":"Yongwei Li","orcid":"https://orcid.org/0000-0001-7799-366X"},"institutions":[{"id":"https://openalex.org/I4210131870","display_name":"Institute of Psychology, Chinese Academy of Sciences","ror":"https://ror.org/03j7v5j15","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210131870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongwei Li","raw_affiliation_strings":["CAS Key Laboratory of Behavioral Science, Institute of Psychology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7799-366X","affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of Behavioral Science, Institute of Psychology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210131870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101745213","display_name":"Longbiao Wang","orcid":"https://orcid.org/0000-0002-8094-6861"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longbiao Wang","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-8094-6861","affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":null,"display_name":"Zhen Zhao","orcid":"https://orcid.org/0000-0002-7898-8974"},"institutions":[{"id":"https://openalex.org/I143413998","display_name":"Qingdao University of Science and Technology","ror":"https://ror.org/041j8js14","country_code":"CN","type":"education","lineage":["https://openalex.org/I143413998"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Zhao","raw_affiliation_strings":["School of Information Science and Technology, Qingdao University of Science and Technology, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0002-7898-8974","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Qingdao University of Science and Technology, Qingdao, China","institution_ids":["https://openalex.org/I143413998"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5066331204"],"corresponding_institution_ids":["https://openalex.org/I143413998"],"apc_list":null,"apc_paid":null,"fwci":3.8259,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.92950392,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"32","issue":null,"first_page":"2184","last_page":"2188"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9909999966621399,"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":0.9909999966621399,"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":0.9448999762535095,"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/speech-recognition","display_name":"Speech recognition","score":0.6442777514457703},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6213885545730591},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.615449070930481},{"id":"https://openalex.org/keywords/stage","display_name":"Stage (stratigraphy)","score":0.48739320039749146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3808318078517914},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3610173463821411},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.112720787525177}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6442777514457703},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6213885545730591},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.615449070930481},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.48739320039749146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3808318078517914},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3610173463821411},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.112720787525177},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lsp.2025.3570245","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3570245","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:/ir.psych.ac.cn:311026/50461","is_oa":false,"landing_page_url":"https://ir.psych.ac.cn/handle/311026/50461","pdf_url":null,"source":{"id":"https://openalex.org/S4377196583","display_name":"Institutional Repository of Institute of Psychology, Chinese Academy of Sciences (Institute of Psychology, Chinese Academy of Sciences)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210131870","host_organization_name":"Institute of Psychology, Chinese Academy of Sciences","host_organization_lineage":["https://openalex.org/I4210131870"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"\u671f\u520a\u8bba\u6587"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4280680737","display_name":null,"funder_award_id":"62201314","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6219155711","display_name":null,"funder_award_id":"62471333","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6221875512","display_name":null,"funder_award_id":"62201571","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2017608047","https://openalex.org/W2146334809","https://openalex.org/W2842511635","https://openalex.org/W2972614117","https://openalex.org/W2997399314","https://openalex.org/W3015267357","https://openalex.org/W3015489952","https://openalex.org/W3015884429","https://openalex.org/W3037988796","https://openalex.org/W3161428216","https://openalex.org/W3192216513","https://openalex.org/W4224933371","https://openalex.org/W4312198907","https://openalex.org/W4377700521","https://openalex.org/W4385823310","https://openalex.org/W4389752793","https://openalex.org/W4392903524","https://openalex.org/W4392939451","https://openalex.org/W4393148016","https://openalex.org/W4395022733","https://openalex.org/W4399274003","https://openalex.org/W4399735948","https://openalex.org/W4402081443","https://openalex.org/W4408354310","https://openalex.org/W6810146603","https://openalex.org/W6868783769","https://openalex.org/W6871745284","https://openalex.org/W6873253340"],"related_works":["https://openalex.org/W2329386257","https://openalex.org/W2503350049","https://openalex.org/W2397616145","https://openalex.org/W2397320258","https://openalex.org/W4324058133","https://openalex.org/W648618910","https://openalex.org/W2033914206","https://openalex.org/W2042327336","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Speech":[0],"Emotion":[1],"Recognition":[2],"(SER)":[3],"in":[4,28,133],"noisy":[5,29,38,108],"environments":[6],"is":[7,74],"challenging":[8],"due":[9],"to":[10,24,37,56,76,90,121],"the":[11,82,102,111,116,119,127],"overlap":[12],"between":[13],"emotional":[14,33,58,79,93],"and":[15,50,138,149],"noise-related":[16],"signals.":[17],"We":[18],"propose":[19],"a":[20,41,67],"novel":[21],"emotion-diffusion":[22],"approach":[23],"enhance":[25],"SER":[26],"performance":[27],"conditions":[30],"that":[31],"transfers":[32],"information":[34],"from":[35],"clean":[36],"speech":[39],"through":[40],"multi-stage":[42],"diffusion":[43],"process.":[44],"First,":[45],"Mel":[46],"Frequency":[47],"Cepstral":[48],"Coefficients":[49],"their":[51],"delta":[52],"features":[53,109],"are":[54,151],"extracted":[55],"capture":[57,77],"dynamics.":[59],"Additionally,":[60],"an":[61],"Emotional":[62],"Bidirectional":[63,70],"Mamba":[64],"Encoder":[65],"with":[66],"Multi-time":[68],"View":[69],"State":[71],"Space":[72],"Model":[73],"designed":[75],"temporal":[78],"patterns.":[80],"Next,":[81],"Emotion-Transferring":[83],"Diffusion":[84],"Network":[85,113],"(ETDN)":[86],"applies":[87],"confidence":[88],"filtering":[89],"retain":[91],"key":[92],"features,":[94],"ensuring":[95],"effective":[96],"emotion":[97],"transfer":[98],"despite":[99],"noise.":[100],"Finally,":[101],"Confidence-Guided":[103],"Mutual":[104],"Learning":[105],"strategy":[106],"refines":[107],"for":[110],"Classification":[112],"(CN),":[114],"while":[115],"CN":[117],"supervises":[118],"ETDN":[120],"maintain":[122],"label":[123],"consistency.":[124],"Experiments":[125],"on":[126],"IEMOCAP":[128],"dataset":[129],"show":[130],"significant":[131],"improvements":[132],"weighted":[134,139],"accuracy,":[135,137],"unweighted":[136],"F1":[140],"score":[141],"across":[142],"various":[143],"signal-to-noise":[144],"ratios.":[145],"b":[146],"Our":[147],"code":[148],"model":[150],"available":[152],"at":[153],"<uri":[154],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[155],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/Littleznnz/ETDN.</uri>":[156]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
