{"id":"https://openalex.org/W4416250502","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229316","title":"ISL-MED: A General Iterative Self-Learning Framework for Speech Complex Emotion Detection","display_name":"ISL-MED: A General Iterative Self-Learning Framework for Speech Complex Emotion Detection","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416250502","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229316"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11229316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229316","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5101545801","display_name":"Xiaolong Wu","orcid":"https://orcid.org/0009-0003-7150-808X"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaolong Wu","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China,830046"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China,830046","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100308479","display_name":"Xinxin Luo","orcid":"https://orcid.org/0009-0001-2345-3841"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinxin Luo","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China,830046"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China,830046","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100538153","display_name":"Chang Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I4210156423","display_name":"National Engineering Research Center for Information Technology in Agriculture","ror":"https://ror.org/04c3j3t84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210156423"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chang Feng","raw_affiliation_strings":["Tsinghua University,Center for Speech and Language Technologies, Beijing National Research Center for Information Science and Technology,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Center for Speech and Language Technologies, Beijing National Research Center for Information Science and Technology,Beijing,China,100084","institution_ids":["https://openalex.org/I4210156423","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040465096","display_name":"Hankiz Yilahun","orcid":"https://orcid.org/0009-0004-8548-678X"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hankiz Yilahun","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China,830046"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China,830046","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083894790","display_name":"Mingxing Xu","orcid":"https://orcid.org/0000-0002-3215-3496"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I4210156423","display_name":"National Engineering Research Center for Information Technology in Agriculture","ror":"https://ror.org/04c3j3t84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210156423"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingxing Xu","raw_affiliation_strings":["Tsinghua University,Center for Speech and Language Technologies, Beijing National Research Center for Information Science and Technology,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Center for Speech and Language Technologies, Beijing National Research Center for Information Science and Technology,Beijing,China,100084","institution_ids":["https://openalex.org/I4210156423","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075133420","display_name":"Askar Hamdulla","orcid":"https://orcid.org/0000-0002-2321-308X"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Askar Hamdulla","raw_affiliation_strings":["Xinjiang University,School of Intelligence Science and Technology,Urumqi,China,830046"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Intelligence Science and Technology,Urumqi,China,830046","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084318285","display_name":"Thomas Fang Zheng","orcid":"https://orcid.org/0000-0002-0249-4767"},"institutions":[{"id":"https://openalex.org/I4210156423","display_name":"National Engineering Research Center for Information Technology in Agriculture","ror":"https://ror.org/04c3j3t84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210156423"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Thomas Fang Zheng","raw_affiliation_strings":["Tsinghua University,Center for Speech and Language Technologies, Beijing National Research Center for Information Science and Technology,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Center for Speech and Language Technologies, Beijing National Research Center for Information Science and Technology,Beijing,China,100084","institution_ids":["https://openalex.org/I4210156423","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101545801"],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38193843,"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":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9783999919891357,"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":0.9783999919891357,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.00570000009611249,"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/T12488","display_name":"Mental Health via Writing","score":0.00430000014603138,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.604200005531311},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5896000266075134},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5835999846458435},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.49779999256134033},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.45820000767707825},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.41839998960494995},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.40470001101493835},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.38909998536109924}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7750999927520752},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.604200005531311},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5896000266075134},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5835999846458435},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.542900025844574},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.49779999256134033},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.45820000767707825},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.41839998960494995},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4163999855518341},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.40470001101493835},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4004000127315521},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.38909998536109924},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3806999921798706},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.37860000133514404},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.35920000076293945},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.3522000014781952},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32910001277923584},{"id":"https://openalex.org/C117619785","wikidata":"https://www.wikidata.org/wiki/Q6094414","display_name":"Iterative learning control","level":3,"score":0.32120001316070557},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.29910001158714294},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2612000107765198}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11229316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229316","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2143673966","https://openalex.org/W2146334809","https://openalex.org/W2552810951","https://openalex.org/W2801959488","https://openalex.org/W2804664105","https://openalex.org/W2904005741","https://openalex.org/W3094767486","https://openalex.org/W3111099392","https://openalex.org/W3117369308","https://openalex.org/W3163091219","https://openalex.org/W3163187953","https://openalex.org/W3204087964","https://openalex.org/W4205781455","https://openalex.org/W4226239215","https://openalex.org/W4246682135","https://openalex.org/W4303649252","https://openalex.org/W4309391683","https://openalex.org/W4309969834","https://openalex.org/W4312938052","https://openalex.org/W4315630861","https://openalex.org/W4367281761","https://openalex.org/W4372269797","https://openalex.org/W4379619502","https://openalex.org/W4385572094","https://openalex.org/W4385823394","https://openalex.org/W4391188458","https://openalex.org/W4392172995","https://openalex.org/W4402675750"],"related_works":[],"abstract_inverted_index":{"Speech":[0],"complex":[1,93,189,195],"emotion":[2,9,94,106,118,130,196,211],"detection":[3,197],"(SCED)":[4],"aims":[5],"to":[6,29,58,89],"identify":[7],"all":[8],"categories":[10],"and":[11,134,157,166,172,199],"their":[12,135],"intensities":[13],"in":[14,61],"speech,":[15],"which":[16],"is":[17,31],"crucial":[18,63],"for":[19,110,115,193,209],"understanding":[20],"the":[21,32,46,55,75,91,112,178,183,188,206],"speaker\u2019s":[22],"genuine":[23],"intentions.":[24],"A":[25],"significant":[26],"challenge":[27],"inherent":[28],"SCED":[30],"coarse":[33,98],"nature":[34],"of":[35,50,185],"manual":[36],"annotations,":[37],"such":[38],"as":[39],"one-hot":[40,99],"labels.":[41,100],"These":[42],"labels":[43],"merely":[44],"indicate":[45],"presence":[47],"or":[48],"absence":[49],"an":[51,85],"emotion,":[52],"thereby":[53],"lacking":[54],"granularity":[56],"required":[57],"guide":[59],"models":[60],"capturing":[62],"intensity":[64,113],"information.":[65],"To":[66],"overcome":[67],"this":[68,146],"limitation,":[69],"we":[70],"propose":[71],"a":[72,116,149],"novel":[73],"framework:":[74],"Iterative":[76],"Self-Learning-based":[77],"Multiple":[78],"Emotion":[79],"Detector":[80],"(ISL-MED).":[81],"This":[82,161],"framework":[83],"utilizes":[84],"iterative":[86],"self-learning":[87],"approach":[88],"infer":[90],"latent":[92],"distribution":[95],"directly":[96],"from":[97,177],"Specifically,":[101],"ISL-MED":[102,186],"employs":[103],"multiple":[104],"dedicated":[105],"detectors,":[107],"each":[108],"responsible":[109],"estimating":[111],"component":[114],"distinct":[117],"category.":[119],"Notably,":[120],"these":[121],"detectors":[122],"can":[123,137],"be":[124,138],"instantiated":[125],"using":[126],"various":[127],"existing":[128],"speech":[129,194],"recognition":[131,212],"(SER)":[132],"models,":[133],"quantity":[136],"flexibly":[139],"configured":[140],"based":[141,153],"on":[142,154,187,205],"task":[143],"requirements.":[144],"Furthermore,":[145],"paper":[147],"proposes":[148],"data":[150],"selection":[151],"strategy":[152,162],"Curriculum":[155],"Learning":[156],"Human-Machine":[158],"Consensus":[159],"(HMCC).":[160],"enhances":[163],"model":[164],"performance":[165],"accelerates":[167],"convergence":[168],"by":[169],"systematically":[170],"identifying":[171],"excluding":[173],"highly":[174],"ambiguous":[175],"samples":[176],"training":[179],"set.":[180],"We":[181],"validated":[182],"effectiveness":[184],"emotions":[190],"dataset":[191,208],"CNSCED":[192],"tasks":[198],"further":[200],"evaluated":[201],"its":[202],"generalization":[203],"capability":[204],"IEMOCAP":[207],"single":[210],"tasks.":[213]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}