{"id":"https://openalex.org/W4392903514","doi":"https://doi.org/10.1109/icassp48485.2024.10446974","title":"Emotion Neural Transducer for Fine-Grained Speech Emotion Recognition","display_name":"Emotion Neural Transducer for Fine-Grained Speech Emotion Recognition","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903514","doi":"https://doi.org/10.1109/icassp48485.2024.10446974"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446974","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446974","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":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2403.19224","any_repository_has_fulltext":true},"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/I4210093653","display_name":"Midea Group (China)","ror":"https://ror.org/006fm2278","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093653"]},{"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":"Siyuan Shen","raw_affiliation_strings":["East China Normal University,Shanghai Institute of AI for Education,Shanghai,China","AI Innovation Center, Midea Group, Shanghai, China","School of Computer Science and Technology, East China Normal University, Shanghai, China","Shanghai Institute of AI for Education, East China Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University,Shanghai Institute of AI for Education,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"AI Innovation Center, Midea Group, Shanghai, China","institution_ids":["https://openalex.org/I4210093653"]},{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"Shanghai Institute of AI for Education, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020803502","display_name":"Yu Gao","orcid":"https://orcid.org/0000-0002-2135-7872"},"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":"Yu Gao","raw_affiliation_strings":["Midea Group,AI Innovation Center,Shanghai,China","AI Innovation Center, Midea Group, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Midea Group,AI Innovation Center,Shanghai,China","institution_ids":["https://openalex.org/I4210093653"]},{"raw_affiliation_string":"AI Innovation Center, Midea Group, Shanghai, China","institution_ids":["https://openalex.org/I4210093653"]}]},{"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/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":"Feng Liu","raw_affiliation_strings":["East China Normal University,Shanghai Institute of AI for Education,Shanghai,China","Shanghai Institute of AI for Education, East China Normal University, Shanghai, China","School of Computer Science and Technology, East China Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University,Shanghai Institute of AI for Education,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"Shanghai Institute of AI for Education, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051945922","display_name":"Hanyang Wang","orcid":"https://orcid.org/0000-0002-8171-6398"},"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":"Hanyang Wang","raw_affiliation_strings":["East China Normal University,Shanghai Institute of AI for Education,Shanghai,China","Shanghai Institute of AI for Education, East China Normal University, Shanghai, China","School of Computer Science and Technology, East China Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University,Shanghai Institute of AI for Education,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"Shanghai Institute of AI for Education, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"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":["East China Normal University,Shanghai Institute of AI for Education,Shanghai,China","Shanghai Institute of AI for Education, East China Normal University, Shanghai, China","School of Computer Science and Technology, East China Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University,Shanghai Institute of AI for Education,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"Shanghai Institute of AI for Education, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":33,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10111","last_page":"10115"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9958999752998352,"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/computer-science","display_name":"Computer science","score":0.7811616063117981},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6869993209838867},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5948655009269714},{"id":"https://openalex.org/keywords/emotion-classification","display_name":"Emotion classification","score":0.4713667631149292},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4486234784126282},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4343975782394409},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4284512996673584},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39635518193244934},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34913650155067444}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7811616063117981},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6869993209838867},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5948655009269714},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.4713667631149292},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4486234784126282},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4343975782394409},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4284512996673584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39635518193244934},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34913650155067444}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446974","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446974","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"},{"id":"pmh:oai:arXiv.org:2403.19224","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.19224","pdf_url":"https://arxiv.org/pdf/2403.19224","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2403.19224","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.19224","pdf_url":"https://arxiv.org/pdf/2403.19224","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"},{"id":"https://openalex.org/F4320324787","display_name":"Peking University","ror":"https://ror.org/02v51f717"},{"id":"https://openalex.org/F4320338440","display_name":"HORIZON EUROPE Health","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392903514.pdf"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2144499799","https://openalex.org/W2146334809","https://openalex.org/W2625297138","https://openalex.org/W2889286050","https://openalex.org/W2963686995","https://openalex.org/W3015686596","https://openalex.org/W3016010032","https://openalex.org/W3016234571","https://openalex.org/W3016238098","https://openalex.org/W3036601975","https://openalex.org/W3096147072","https://openalex.org/W3097827011","https://openalex.org/W3152221657","https://openalex.org/W3197580070","https://openalex.org/W3197642003","https://openalex.org/W3198528147","https://openalex.org/W3202419788","https://openalex.org/W3208480086","https://openalex.org/W4226063021","https://openalex.org/W4296069165","https://openalex.org/W4304080189","https://openalex.org/W4372259942","https://openalex.org/W4372263296","https://openalex.org/W4372267500","https://openalex.org/W4372341110","https://openalex.org/W4385822707","https://openalex.org/W4385823394","https://openalex.org/W4391021638","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W3126677997","https://openalex.org/W1610857240","https://openalex.org/W4281557318","https://openalex.org/W4308351423","https://openalex.org/W1550318927","https://openalex.org/W4305042383","https://openalex.org/W2546649374","https://openalex.org/W2773396412","https://openalex.org/W4380854332","https://openalex.org/W2184859701"],"abstract_inverted_index":{"The":[0],"mainstream":[1],"paradigm":[2],"of":[3,14,20,37,110,156],"speech":[4,38,51,56,147],"emotion":[5,12,24,52,68,73,115,148,158],"recognition":[6,53,57],"(SER)":[7],"is":[8,162],"identifying":[9],"the":[10,15,23,85,107,145,154],"single":[11],"label":[13],"entire":[16],"utterance.":[17],"This":[18],"line":[19],"works":[21],"neglect":[22],"dynamics":[25],"at":[26,164],"fine":[27],"temporal":[28],"granularity":[29],"and":[30,92,144],"mostly":[31],"fail":[32],"to":[33,71,88,99],"leverage":[34],"linguistic":[35],"information":[36],"signal":[39],"explicitly.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44,79,103],"propose":[45,80],"Emotion":[46,121],"Neural":[47,122],"Transducer":[48],"for":[49,75],"fine-grained":[50,76,97,157],"with":[54,67],"automatic":[55],"(ASR)":[58],"joint":[59,69],"training.":[60],"We":[61],"first":[62],"extend":[63],"typical":[64,125],"neural":[65],"transducer":[66,100],"network":[70],"construct":[72],"lattice":[74,81,87],"SER.":[77],"Then":[78],"max":[82],"pooling":[83],"on":[84,134,142],"alignment":[86],"facilitate":[89],"distinguishing":[90],"emotional":[91],"non-emotional":[93],"frames.":[94],"To":[95],"adapt":[96],"SER":[98],"inference":[101],"manner,":[102],"further":[104],"make":[105],"blank,":[106],"special":[108],"symbol":[109],"ASR,":[111],"serve":[112],"as":[113,117],"underlying":[114],"indicator":[116],"well,":[118],"yielding":[119],"Factorized":[120],"Transducer.":[123],"For":[124],"utterance-level":[126],"SER,":[127],"our":[128],"ENT":[129],"models":[130],"outperform":[131],"state-of-the-art":[132],"methods":[133],"IEMOCAP":[135,143],"in":[136],"low":[137],"word":[138],"error":[139],"rate.":[140],"Experiments":[141],"latest":[146],"diarization":[149],"dataset":[150],"ZED":[151],"also":[152],"demonstrate":[153],"superiority":[155],"modeling.":[159],"Our":[160],"code":[161],"available":[163],"https://github.com/ECNU-Cross-Innovation-Lab/ENT.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":7}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}