{"id":"https://openalex.org/W4409154675","doi":"https://doi.org/10.1109/taffc.2025.3558222","title":"Towards Speaker-Unknown Emotion Recognition in Conversation via Progressive Contrastive Deep Supervision","display_name":"Towards Speaker-Unknown Emotion Recognition in Conversation via Progressive Contrastive Deep Supervision","publication_year":2025,"publication_date":"2025-04-04","ids":{"openalex":"https://openalex.org/W4409154675","doi":"https://doi.org/10.1109/taffc.2025.3558222"},"language":"en","primary_location":{"id":"doi:10.1109/taffc.2025.3558222","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taffc.2025.3558222","pdf_url":null,"source":{"id":"https://openalex.org/S104780363","display_name":"IEEE Transactions on Affective Computing","issn_l":"1949-3045","issn":["1949-3045","2371-9850"],"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 Transactions on Affective Computing","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/A5101980691","display_name":"Siyuan Shen","orcid":"https://orcid.org/0000-0001-9732-9600"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyuan Shen","raw_affiliation_strings":["Research and Development Department, Baidu Inc., Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9732-9600","affiliations":[{"raw_affiliation_string":"Research and Development Department, Baidu Inc., Shanghai, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085891781","display_name":"Feng Liu","orcid":"https://orcid.org/0000-0002-5289-5761"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Liu","raw_affiliation_strings":["School of Psychology, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-5289-5761","affiliations":[{"raw_affiliation_string":"School of Psychology, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006106876","display_name":"Hanyang Wang","orcid":"https://orcid.org/0000-0002-5227-5765"},"institutions":[{"id":"https://openalex.org/I4210093653","display_name":"Midea Group (China)","ror":"https://ror.org/006fm2278","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093653"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanyang Wang","raw_affiliation_strings":["AI Research Center, Midea Group Inc., Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-5227-5765","affiliations":[{"raw_affiliation_string":"AI Research Center, Midea Group Inc., Shanghai, China","institution_ids":["https://openalex.org/I4210093653"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050248676","display_name":"Aimin Zhou","orcid":"https://orcid.org/0000-0002-4768-5946"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aimin Zhou","raw_affiliation_strings":["Institute of AI Education, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4768-5946","affiliations":[{"raw_affiliation_string":"Institute of AI Education, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":17.2627,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.99034622,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"16","issue":"3","first_page":"2261","last_page":"2273"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9593999981880188,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9593999981880188,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9387999773025513,"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/conversation","display_name":"Conversation","score":0.8647710084915161},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.666415810585022},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.5842658281326294},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.566802442073822},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5598301291465759},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4086947739124298},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4071533679962158},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36755135655403137},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.3619655966758728},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35295939445495605},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.27463817596435547}],"concepts":[{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.8647710084915161},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.666415810585022},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.5842658281326294},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.566802442073822},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5598301291465759},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4086947739124298},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4071533679962158},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36755135655403137},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3619655966758728},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35295939445495605},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.27463817596435547},{"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:10.1109/taffc.2025.3558222","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taffc.2025.3558222","pdf_url":null,"source":{"id":"https://openalex.org/S104780363","display_name":"IEEE Transactions on Affective Computing","issn_l":"1949-3045","issn":["1949-3045","2371-9850"],"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 Transactions on Affective Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3925441564","display_name":null,"funder_award_id":"32471151","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5686620817","display_name":null,"funder_award_id":"22511105901","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W2038101708","https://openalex.org/W2046056978","https://openalex.org/W2049462786","https://openalex.org/W2114925438","https://openalex.org/W2115599677","https://openalex.org/W2125462608","https://openalex.org/W2146334809","https://openalex.org/W2150769028","https://openalex.org/W2460742184","https://openalex.org/W2512449761","https://openalex.org/W2587150483","https://openalex.org/W2618843390","https://openalex.org/W2805657784","https://openalex.org/W2805662932","https://openalex.org/W2889418727","https://openalex.org/W2890964092","https://openalex.org/W2891359673","https://openalex.org/W2896538040","https://openalex.org/W2902200737","https://openalex.org/W2962870549","https://openalex.org/W2963470929","https://openalex.org/W2963686995","https://openalex.org/W2963745998","https://openalex.org/W2964057995","https://openalex.org/W2964300796","https://openalex.org/W2964351684","https://openalex.org/W2972949456","https://openalex.org/W2985882473","https://openalex.org/W3015308237","https://openalex.org/W3035524453","https://openalex.org/W3038115231","https://openalex.org/W3095212884","https://openalex.org/W3099056802","https://openalex.org/W3108655343","https://openalex.org/W3137249133","https://openalex.org/W3156636935","https://openalex.org/W3169022486","https://openalex.org/W3170581063","https://openalex.org/W3171007011","https://openalex.org/W3173396651","https://openalex.org/W3173751215","https://openalex.org/W3175552668","https://openalex.org/W3175593095","https://openalex.org/W3176399185","https://openalex.org/W3176849538","https://openalex.org/W3198668286","https://openalex.org/W3212886388","https://openalex.org/W4221162793","https://openalex.org/W4226025958","https://openalex.org/W4226425326","https://openalex.org/W4308222518","https://openalex.org/W4312176099","https://openalex.org/W4312523492","https://openalex.org/W4318563436","https://openalex.org/W4385194642","https://openalex.org/W4385573172","https://openalex.org/W4385823101","https://openalex.org/W4389519350","https://openalex.org/W4392562716"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W4313854686","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2368768466","https://openalex.org/W2757081366","https://openalex.org/W3197877226"],"abstract_inverted_index":{"Emotion":[0],"recognition":[1,73,82],"in":[2,12,74],"conversation":[3,75],"has":[4],"attained":[5],"increasing":[6],"attention":[7],"for":[8,70],"perceiving":[9],"user":[10],"emotion":[11,72,81,96,184],"practical":[13],"conversational":[14],"applications.":[15],"Conversational":[16],"utterances":[17],"spoken":[18],"alternately":[19],"by":[20],"different":[21],"speakers":[22,134,145],"inspire":[23],"most":[24],"studies":[25],"to":[26,128],"leverage":[27],"speaker":[28,33,46,55,78,94,117,122,140,181],"information":[29],"based":[30],"on":[31,152],"golden":[32],"labels.":[34],"In":[35],"this":[36],"work,":[37],"we":[38,92,119],"challenge":[39],"the":[40,54,99,107,111,130,161,164,177],"existing":[41],"paradigm":[42],"of":[43,57,132,144,163],"utilizing":[44],"available":[45,189],"labels":[47],"with":[48,106],"a":[49,121,149],"more":[50],"realistic":[51],"scenario,":[52],"where":[53],"identity":[56],"each":[58],"utterance":[59],"is":[60,146,188],"unknown":[61],"during":[62],"inference.":[63],"We":[64,167],"propose":[65,120],"Progressive":[66],"Contrastive":[67],"Deep":[68],"Supervision":[69],"multimodal":[71],"(PCDS),":[76],"incorporating":[77],"diarization":[79,182],"and":[80,95,124,158,183],"into":[83,98,135],"one":[84],"unified":[85],"framework.":[86],"To":[87,114],"facilitate":[88],"joint":[89],"task":[90],"learning,":[91],"inject":[93],"bias":[97],"network":[100],"progressively":[101],"via":[102],"contrastive":[103,172],"deep":[104,173],"supervision,":[105],"task-irrelevant":[108],"contrast":[109,123],"being":[110],"intermediate":[112],"transition.":[113],"obtain":[115],"explicit":[116],"dependency,":[118],"clustering":[125],"module":[126],"(SCC)":[127],"endow":[129],"capability":[131],"partitioning":[133],"groups":[136],"even":[137],"when":[138],"neither":[139],"label":[141],"nor":[142],"number":[143],"known":[147],"as":[148],"priori.":[150],"Experiments":[151],"two":[153],"ERC":[154],"benchmarks,":[155],"including":[156],"IEMOCAP":[157],"MELD":[159],"demonstrate":[160],"effectiveness":[162],"proposed":[165],"method.":[166],"also":[168],"show":[169],"that":[170],"progressive":[171],"supervision":[174],"helps":[175],"reconcile":[176],"underlying":[178],"tension":[179],"between":[180],"recognition.":[185],"Source":[186],"code":[187],"from":[190],"Github[https://github.com/Cross-Innovation-Lab/PCDS/].":[191]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":6}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}