{"id":"https://openalex.org/W7140097045","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.212","title":"Emotion Recognition in Multi-Speaker Conversations through Speaker Identification, Knowledge Distillation, and Hierarchical Fusion","display_name":"Emotion Recognition in Multi-Speaker Conversations through Speaker Identification, Knowledge Distillation, and Hierarchical Fusion","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140097045","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.212"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.212","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.212","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.212","pdf_url":"https://aclanthology.org/2026.findings-eacl.212.pdf","source":{"id":"https://openalex.org/S7407087051","display_name":"Findings of the Association for Computational Linguistics: EACL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.findings-eacl.212.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130389817","display_name":"Li Xiao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069989297","display_name":"Kotaro Funakoshi","orcid":"https://orcid.org/0000-0002-4529-4634","observed_orcids":["https://orcid.org/0000-0002-4529-4634"]},"institutions":[{"id":"https://openalex.org/I4400009020","display_name":"Institute of Science Tokyo","ror":"https://ror.org/05dqf9946","country_code":"JP","type":"education","lineage":["https://openalex.org/I4400009020"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kotaro Funakoshi","raw_affiliation_strings":["Institute of Science Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo","institution_ids":["https://openalex.org/I4400009020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035876897","display_name":"Manabu Okumura","orcid":"https://orcid.org/0009-0001-7730-1536","observed_orcids":["https://orcid.org/0009-0001-7730-1536"]},"institutions":[{"id":"https://openalex.org/I4400009020","display_name":"Institute of Science Tokyo","ror":"https://ror.org/05dqf9946","country_code":"JP","type":"education","lineage":["https://openalex.org/I4400009020"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Manabu Okumura","raw_affiliation_strings":["Institute of Science Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo","institution_ids":["https://openalex.org/I4400009020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":20.5333,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.97803247,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4091","last_page":"4106"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9970999956130981,"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":0.9970999956130981,"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":0.0010000000474974513,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.0006000000284984708,"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/emotion-recognition","display_name":"emotion recognition","score":0.8659999966621399},{"id":"https://openalex.org/keywords/multi-speaker-conversations","display_name":"multi-speaker conversations","score":0.9890000224113464},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"speaker identification","score":0.9570000171661377},{"id":"https://openalex.org/keywords/knowledge-distillation","display_name":"knowledge distillation","score":0.8339999914169312},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.8130000233650208},{"id":"https://openalex.org/keywords/audio-visual-synchronization","display_name":"audio-video synchronization","score":0.9580000042915344},{"id":"https://openalex.org/keywords/multimodal-fusion","display_name":"multimodal fusion","score":0.7639999985694885},{"id":"https://openalex.org/keywords/meld","display_name":"MELD","score":0.6359999775886536},{"id":"https://openalex.org/keywords/iemocap","display_name":"IEMOCAP","score":0.9990000128746033}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5651000142097473},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.48410001397132874},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48260000348091125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4262000024318695},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3671000003814697},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3296999931335449},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.325300008058548},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.2816999852657318},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.212","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.212","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.212","pdf_url":"https://aclanthology.org/2026.findings-eacl.212.pdf","source":{"id":"https://openalex.org/S7407087051","display_name":"Findings of the Association for Computational Linguistics: EACL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.13731","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2511.13731","pdf_url":"https://arxiv.org/pdf/2511.13731","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50754163","doi":null,"is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100942139","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"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":"Conference Paper"},{"id":"doi:10.48550/arxiv.2511.13731","doi":"https://doi.org/10.48550/arxiv.2511.13731","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.13731","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.212","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.212","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.212","pdf_url":"https://aclanthology.org/2026.findings-eacl.212.pdf","source":{"id":"https://openalex.org/S7407087051","display_name":"Findings of the Association for Computational Linguistics: EACL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140097045.pdf","grobid_xml":"https://content.openalex.org/works/W7140097045.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7126045555","https://openalex.org/W7157806801","https://openalex.org/W4392904377","https://openalex.org/W4409154675","https://openalex.org/W7137990808","https://openalex.org/W4360853195","https://openalex.org/W4408851154","https://openalex.org/W4385823101","https://openalex.org/W4408352935","https://openalex.org/W4387426799"],"abstract_inverted_index":{"Emotion":[0],"recognition":[1],"in":[2],"multi-speaker":[3],"conversations":[4],"faces":[5],"significant":[6],"challenges":[7],"due":[8],"to":[9,37,54,68],"speaker":[10,30],"ambiguity":[11],"and":[12,56,59,75,83],"severe":[13],"class":[14,70],"imbalance.We":[15],"propose":[16],"a":[17,29,44],"novel":[18],"architecture":[19],"that":[20,33,48],"addresses":[21],"these":[22],"issues":[23],"through":[24],"three":[25],"key":[26],"innovations:":[27],"(1)":[28],"identification":[31],"module":[32],"leverages":[34],"audio-visual":[35],"synchronization":[36],"accurately":[38],"identify":[39],"the":[40],"active":[41],"speaker,":[42],"(2)":[43],"knowledge":[45],"distillation":[46],"strategy":[47],"transfers":[49],"superior":[50,79],"textual":[51],"emotion":[52,95],"understanding":[53],"audio":[55],"visual":[57],"modalities,":[58],"(3)":[60],"hierarchical":[61],"attention":[62],"fusion":[63],"with":[64,89],"composite":[65],"loss":[66],"functions":[67],"handle":[69],"imbalance.Comprehensive":[71],"evaluations":[72],"on":[73,93],"MELD":[74],"IEMOCAP":[76],"datasets":[77],"demonstrate":[78],"performance,":[80],"achieving":[81],"67.75%":[82],"72.44%":[84],"weighted":[85],"F1":[86],"scores":[87],"respectively,":[88],"particularly":[90],"notable":[91],"improvements":[92],"minority":[94],"classes.":[96]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-22T18:32:59.640997","created_date":"2026-03-24T00:00:00"}