{"id":"https://openalex.org/W4392902917","doi":"https://doi.org/10.1109/icassp48485.2024.10447805","title":"Dynamic Speech Emotion Recognition Using A Conditional Neural Process","display_name":"Dynamic Speech Emotion Recognition Using A Conditional Neural Process","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902917","doi":"https://doi.org/10.1109/icassp48485.2024.10447805"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447805","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447805","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/A5072064784","display_name":"Luz Martinez-Lucas","orcid":"https://orcid.org/0009-0000-6368-7039"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Luz Martinez-Lucas","raw_affiliation_strings":["The University of Texas at Dallas,Multimodal Signal Processing (MSP) Lab,Department of Electrical and Computer Engineering,Richardson,TX,USA,75080"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas,Multimodal Signal Processing (MSP) Lab,Department of Electrical and Computer Engineering,Richardson,TX,USA,75080","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040793194","display_name":"Carlos Busso","orcid":"https://orcid.org/0000-0002-4075-4072"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carlos Busso","raw_affiliation_strings":["The University of Texas at Dallas,Multimodal Signal Processing (MSP) Lab,Department of Electrical and Computer Engineering,Richardson,TX,USA,75080"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas,Multimodal Signal Processing (MSP) Lab,Department of Electrical and Computer Engineering,Richardson,TX,USA,75080","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5072064784"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":0.5031,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.64702215,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"80","issue":null,"first_page":"12036","last_page":"12040"},"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.984499990940094,"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":0.9696000218391418,"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":0.7284961938858032},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6248507499694824},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5477442741394043},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5196163058280945},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.508155107498169},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5038842558860779},{"id":"https://openalex.org/keywords/valence","display_name":"Valence (chemistry)","score":0.4782896637916565},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4638163447380066},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43374091386795044},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.42909106612205505},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3692404627799988},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36186739802360535},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.33213990926742554},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.22498595714569092}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7284961938858032},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6248507499694824},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5477442741394043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5196163058280945},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.508155107498169},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5038842558860779},{"id":"https://openalex.org/C168900304","wikidata":"https://www.wikidata.org/wiki/Q171407","display_name":"Valence (chemistry)","level":2,"score":0.4782896637916565},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4638163447380066},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43374091386795044},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.42909106612205505},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3692404627799988},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36186739802360535},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.33213990926742554},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.22498595714569092},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447805","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447805","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2032254851","https://openalex.org/W2064675550","https://openalex.org/W2092804630","https://openalex.org/W2134031328","https://openalex.org/W2313339984","https://openalex.org/W2401417847","https://openalex.org/W2404863510","https://openalex.org/W2550557083","https://openalex.org/W2742542661","https://openalex.org/W2806649730","https://openalex.org/W2981677410","https://openalex.org/W2996156641","https://openalex.org/W3094739760","https://openalex.org/W3095093565","https://openalex.org/W3161659450","https://openalex.org/W3175239729","https://openalex.org/W3198310004","https://openalex.org/W3198771897","https://openalex.org/W3209984917","https://openalex.org/W4252233326","https://openalex.org/W4285111045","https://openalex.org/W4322707285","https://openalex.org/W4361994820","https://openalex.org/W4385245566","https://openalex.org/W4390874415","https://openalex.org/W4392397287","https://openalex.org/W6752040014","https://openalex.org/W6755477022","https://openalex.org/W6840123999"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861","https://openalex.org/W2129455854"],"abstract_inverted_index":{"The":[0],"problem":[1,61],"of":[2,42,49,62,105,129],"predicting":[3,12,63,168],"emotional":[4,65,83,107,151,169],"attributes":[5],"from":[6,16,51,87,133,138],"speech":[7,52,69,119],"has":[8],"often":[9,25],"focused":[10],"on":[11,35,96],"a":[13,17,54,112,117,144,148,160],"single":[14],"value":[15],"sentence":[18],"or":[19],"short":[20],"speaking":[21],"turn.":[22],"These":[23],"methods":[24,100],"ignore":[26],"that":[27,80,146],"natural":[28],"emotions":[29,93],"are":[30,94],"both":[31],"dynamic":[32,40,68],"and":[33,136],"dependent":[34,95],"context.":[36],"To":[37],"model":[38,115,123,130,141,155],"the":[39,47,60,88,103,134,139],"nature":[41],"emotions,":[43],"we":[44],"can":[45],"treat":[46,81],"prediction":[48],"emotion":[50,70,120],"as":[53,67,85],"time-series":[55,135],"problem.":[56,126],"We":[57],"refer":[58],"to":[59,142],"these":[64,99],"traces":[66,84,170],"recognition.":[71],"Previous":[72],"studies":[73],"in":[74],"this":[75,125],"area":[76],"have":[77],"used":[78],"models":[79],"all":[82],"coming":[86],"same":[89],"underlying":[90],"distribution.":[91],"Since":[92],"contextual":[97],"information,":[98],"might":[101],"obscure":[102],"context":[104],"an":[106],"interaction.":[108],"This":[109,127],"paper":[110],"uses":[111],"neural":[113],"process":[114],"with":[116],"segment-level":[118],"recognition":[121],"(SER)":[122],"for":[124,171],"type":[128],"leverages":[131],"information":[132],"predictions":[137],"SER":[140],"learn":[143],"prior":[145],"defines":[147],"distribution":[149],"over":[150],"traces.":[152],"Our":[153],"proposed":[154],"performs":[156],"21%":[157],"better":[158],"than":[159],"bidirectional":[161],"long":[162],"short-term":[163],"memory":[164],"(BiLSTM)":[165],"baseline":[166],"when":[167],"valence.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}