{"id":"https://openalex.org/W7164864178","doi":"https://doi.org/10.1109/access.2026.3703882","title":"ProtoGEN: A Prototype-Guided Emotion Network for Multimodal Speech Emotion Recognition","display_name":"ProtoGEN: A Prototype-Guided Emotion Network for Multimodal Speech Emotion Recognition","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7164864178","doi":"https://doi.org/10.1109/access.2026.3703882"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3703882","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3703882","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3703882","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124607348","display_name":"Levon Avetisyan","orcid":null},"institutions":[{"id":"https://openalex.org/I188529364","display_name":"Russian-Armenian University","ror":"https://ror.org/01v4e7289","country_code":"AM","type":"education","lineage":["https://openalex.org/I188529364"]}],"countries":["AM"],"is_corresponding":false,"raw_author_name":"Levon A. Avetisyan","raw_affiliation_strings":["Russian-Armenian University, Yerevan, Armenia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Russian-Armenian University, Yerevan, Armenia","institution_ids":["https://openalex.org/I188529364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063902837","display_name":"Shahane Tigranyan","orcid":"https://orcid.org/0000-0003-1536-9954"},"institutions":[{"id":"https://openalex.org/I4210133484","display_name":"Institute for Informatics and Automation Problems","ror":"https://ror.org/04a8k4p47","country_code":"AM","type":"facility","lineage":["https://openalex.org/I4210133484","https://openalex.org/I99064381"]}],"countries":["AM"],"is_corresponding":false,"raw_author_name":"Shahane T. Tigranyan","raw_affiliation_strings":["IIAP NAS RA, Yerevan, Armenia"],"raw_orcid":"https://orcid.org/0000-0003-1536-9954","affiliations":[{"raw_affiliation_string":"IIAP NAS RA, Yerevan, Armenia","institution_ids":["https://openalex.org/I4210133484"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121620919","display_name":"Aram Avetisyan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133156","display_name":"Education Trust","ror":"https://ror.org/0337vmn97","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210133156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aram A. Avetisyan","raw_affiliation_strings":["Trusted AI Research Center, RAS, Moscow, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Trusted AI Research Center, RAS, Moscow, Russia","institution_ids":["https://openalex.org/I4210133156"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.80392268,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"93027","last_page":"93041"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9704999923706055,"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":0.9704999923706055,"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":0.003599999938160181,"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/T11309","display_name":"Music and Audio Processing","score":0.003100000089034438,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.7228999733924866},{"id":"https://openalex.org/keywords/emotion-classification","display_name":"Emotion classification","score":0.33970001339912415},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.33959999680519104},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.32089999318122864},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3133000135421753},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.27129998803138733}],"concepts":[{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.7228999733924866},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7031999826431274},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6373000144958496},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.33970001339912415},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31040000915527344},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2662000060081482},{"id":"https://openalex.org/C202101335","wikidata":"https://www.wikidata.org/wiki/Q7002166","display_name":"Neurocomputational speech processing","level":4,"score":0.26579999923706055},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2623000144958496},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.25450000166893005}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3703882","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3703882","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:31b93a81f42e40528e432f1056e53f29","is_oa":false,"landing_page_url":"https://doaj.org/article/31b93a81f42e40528e432f1056e53f29","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 93027-93041 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3703882","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3703882","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Speech":[0],"Emotion":[1],"Recognition":[2],"in":[3,84,222],"Russian":[4,93,133,211],"remains":[5,181],"underexplored":[6],"compared":[7],"to":[8,12,52,91],"English,":[9],"largely":[10],"due":[11],"limited":[13],"multimodal":[14,92,167,207],"resources,":[15],"heterogeneous":[16,106],"annotation":[17],"schemes,":[18],"and":[19,45,66,95,138,143,148,160,214],"the":[20,53,117,128,155,178,191,194,204,216],"absence":[21],"of":[22,193,203,218],"strong":[23,159],"baselines":[24],"across":[25,209],"datasets.":[26,108],"To":[27],"address":[28],"these":[29,71],"challenges,":[30],"we":[31,87],"propose":[32],"a":[33,46,100],"unified":[34],"bimodal":[35],"audio-text":[36],"architecture":[37],"that":[38,60,154],"integrates":[39],"speech":[40,145],"representations":[41],"with":[42,70,166],"text":[43],"embeddings":[44,69],"cross-modal":[47],"Co-Attention":[48],"fusion":[49,168],"module.":[50],"Central":[51],"framework":[54],"is":[55],"an":[56,112],"auxiliary":[57,102,195,220],"prototype-based":[58,77,196],"objective":[59,110],"introduces":[61],"trainable":[62],"class-specific":[63],"emotion":[64,85],"prototypes":[65],"aligns":[67],"acoustic":[68],"anchors":[72],"through":[73],"cosine-based":[74],"classification.":[75],"While":[76],"representation":[78],"learning":[79],"has":[80],"been":[81],"explored":[82],"previously":[83],"recognition,":[86],"adapt":[88],"this":[89,199,223],"formulation":[90],"SER":[94,212],"investigate":[96],"its":[97],"effectiveness":[98,192,217],"as":[99],"stable":[101],"supervision":[103,221],"mechanism":[104],"for":[105,116],"low-resource":[107],"This":[109],"provides":[111,201],"additional":[113],"structural":[114],"signal":[115],"audio":[118],"encoder":[119],"without":[120],"relying":[121],"on":[122,130,172,183],"batch-dependent":[123],"pair":[124],"construction.":[125],"We":[126],"evaluate":[127],"system":[129],"four":[131],"diverse":[132],"datasets:":[134],"RESD,":[135],"REPV,":[136],"SCES-1,":[137],"Dusha,":[139],"covering":[140],"both":[141],"acted":[142],"spontaneous":[144],"from":[146],"adult":[147],"child":[149],"speakers.":[150],"Extensive":[151],"experiments":[152],"demonstrate":[153],"proposed":[156],"model":[157],"achieves":[158],"consistent":[161],"improvements":[162],"over":[163],"existing":[164],"baselines,":[165],"yielding":[169],"substantial":[170],"gains":[171],"datasets":[173,213],"containing":[174],"informative":[175],"transcripts,":[176],"whereas":[177],"audio-only":[179],"variant":[180],"competitive":[182],"lexically":[184],"constrained":[185],"corpora.":[186],"Ablation":[187],"studies":[188],"further":[189],"highlight":[190],"objective.":[197],"Overall,":[198],"work":[200],"one":[202],"first":[205],"systematic":[206],"evaluations":[208],"multiple":[210],"demonstrates":[215],"prototype-guided":[219],"setting.":[224]},"counts_by_year":[],"updated_date":"2026-06-25T06:16:34.145877","created_date":"2026-06-16T00:00:00"}