{"id":"https://openalex.org/W4392908941","doi":"https://doi.org/10.1109/icassp48485.2024.10448044","title":"Disentanglement Network: Disentangle the Emotional Features from Acoustic Features for Speech Emotion Recognition","display_name":"Disentanglement Network: Disentangle the Emotional Features from Acoustic Features for Speech Emotion Recognition","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392908941","doi":"https://doi.org/10.1109/icassp48485.2024.10448044"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448044","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5113145350","display_name":"Zhichen Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhichen Yuan","raw_affiliation_strings":["South China University of Technology,School of Computer Science and Engineering,Guangzhou,China","School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Computer Science and Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100643265","display_name":"C. L. Philip Chen","orcid":"https://orcid.org/0000-0001-5451-7230"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"C. L. Philip Chen","raw_affiliation_strings":["South China University of Technology,School of Computer Science and Engineering,Guangzhou,China","School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Computer Science and Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027023224","display_name":"Shuzhen Li","orcid":"https://orcid.org/0000-0001-6847-6740"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuzhen Li","raw_affiliation_strings":["South China University of Technology,School of Computer Science and Engineering,Guangzhou,China","School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Computer Science and Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100378800","display_name":"Tong Zhang","orcid":"https://orcid.org/0000-0002-7025-6365"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Zhang","raw_affiliation_strings":["South China University of Technology,School of Computer Science and Engineering,Guangzhou,China","School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Computer Science and Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.672,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.9754702,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"11686","last_page":"11690"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9290000200271606,"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":0.9290000200271606,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9035000205039978,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.7805628776550293},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6469897031784058},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6153393387794495}],"concepts":[{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.7805628776550293},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6469897031784058},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6153393387794495}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448044","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7599999904632568}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W2146334809","https://openalex.org/W2295001676","https://openalex.org/W2602034649","https://openalex.org/W2793383796","https://openalex.org/W2796339975","https://openalex.org/W2803098682","https://openalex.org/W2963217615","https://openalex.org/W3015308237","https://openalex.org/W3093895424","https://openalex.org/W3161958798","https://openalex.org/W3197642003","https://openalex.org/W3204087964","https://openalex.org/W3209059054","https://openalex.org/W4212774754","https://openalex.org/W4221162793","https://openalex.org/W4221162872","https://openalex.org/W4285106979","https://openalex.org/W4372269797","https://openalex.org/W4372341110","https://openalex.org/W4375869379","https://openalex.org/W4385382111","https://openalex.org/W6734335776","https://openalex.org/W6780218876","https://openalex.org/W6855332964"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Speech":[0],"emotion":[1,20,113],"recognition":[2],"plays":[3],"a":[4,50,79,93],"crucial":[5],"role":[6],"in":[7],"human-computer":[8],"interaction.":[9],"However,":[10],"data":[11],"distribution":[12],"of":[13,41,92,127,137,145],"speech":[14],"signals":[15],"varies":[16],"among":[17],"individuals":[18],"for":[19,112],"recognition.":[21,114],"It":[22],"may":[23],"guide":[24],"models":[25],"to":[26,55,82,106],"focus":[27],"more":[28,108],"on":[29,117,139,147,155],"identity":[30,67,99],"information":[31],"rather":[32],"than":[33],"emotional":[34,57,84,110],"information,":[35],"which":[36],"impairs":[37],"the":[38,90,97,104,125,140,148,152],"generalization":[39],"ability":[40],"models.":[42],"To":[43],"address":[44],"this":[45,47,130],"issue,":[46],"paper":[48],"proposes":[49],"novel":[51],"Disentanglement":[52],"Network":[53],"(DTNet)":[54],"disentangle":[56,83],"features":[58,68,71,85,88,111],"from":[59,69,86],"acoustic":[60,70,87],"features.":[61,100],"Specifically,":[62],"DTNet":[63,105],"first":[64],"captures":[65],"hidden":[66,98],"through":[72],"an":[73,133],"identity-aware":[74],"module.":[75],"Then,":[76],"we":[77],"design":[78],"disentanglement":[80],"module":[81,95],"within":[89],"constraints":[91],"reconstruction":[94],"and":[96,120,129,143],"These":[101],"modules":[102],"enable":[103],"extract":[107],"discriminative":[109],"Experimental":[115],"results":[116],"both":[118,156],"speaker-independent":[119],"speaker-dependent":[121],"settings":[122],"have":[123],"proven":[124],"effectiveness":[126],"DTNet,":[128],"method":[131],"achieves":[132],"unweighted":[134],"accuracy":[135],"(UA)":[136],"74.8%":[138],"IEMOCAP":[141],"dataset":[142],"UA":[144],"95.5%":[146],"Emo-DB":[149],"dataset,":[150],"outperforming":[151],"state-of-the-art":[153],"methods":[154],"datasets.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":5}],"updated_date":"2026-06-16T09:24:06.705377","created_date":"2025-10-10T00:00:00"}