{"id":"https://openalex.org/W4392909557","doi":"https://doi.org/10.1109/icassp48485.2024.10445890","title":"Learning Arousal-Valence Representation from Categorical Emotion Labels of Speech","display_name":"Learning Arousal-Valence Representation from Categorical Emotion Labels of Speech","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909557","doi":"https://doi.org/10.1109/icassp48485.2024.10445890"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445890","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445890","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":["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/A5112843587","display_name":"Enting Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]},{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Enting Zhou","raw_affiliation_strings":["University of Rochester,Department of Computer Science,USA,NY","Department of Computer Science, University of Rochester, USA, NY","Department of Electrical and Computer Engineering, University of California, San Diego, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester,Department of Computer Science,USA,NY","institution_ids":["https://openalex.org/I5388228"]},{"raw_affiliation_string":"Department of Computer Science, University of Rochester, USA, NY","institution_ids":["https://openalex.org/I5388228"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100384568","display_name":"You Zhang","orcid":"https://orcid.org/0000-0002-4649-278X"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"You Zhang","raw_affiliation_strings":["University of Rochester,Department of Electrical and Computer Engineering,USA,NY","Department of Electrical and Computer Engineering, University of Rochester, USA, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester,Department of Electrical and Computer Engineering,USA,NY","institution_ids":["https://openalex.org/I5388228"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Rochester, USA, NY","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102749436","display_name":"Zhiyao Duan","orcid":"https://orcid.org/0000-0002-8334-9974"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiyao Duan","raw_affiliation_strings":["University of Rochester,Department of Electrical and Computer Engineering,USA,NY","Department of Electrical and Computer Engineering, University of Rochester, USA, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester,Department of Electrical and Computer Engineering,USA,NY","institution_ids":["https://openalex.org/I5388228"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Rochester, USA, NY","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.92,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.92046616,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"12126","last_page":"12130"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9283000230789185,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9283000230789185,"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/valence","display_name":"Valence (chemistry)","score":0.7997022867202759},{"id":"https://openalex.org/keywords/arousal","display_name":"Arousal","score":0.780063271522522},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.7225847244262695},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5983545780181885},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5891045331954956},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5098606944084167},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.4966300129890442},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.458800733089447},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.4291658103466034},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4005363881587982},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.13328957557678223},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.12653657793998718}],"concepts":[{"id":"https://openalex.org/C168900304","wikidata":"https://www.wikidata.org/wiki/Q171407","display_name":"Valence (chemistry)","level":2,"score":0.7997022867202759},{"id":"https://openalex.org/C36951298","wikidata":"https://www.wikidata.org/wiki/Q379784","display_name":"Arousal","level":2,"score":0.780063271522522},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.7225847244262695},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5983545780181885},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5891045331954956},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5098606944084167},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.4966300129890442},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.458800733089447},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4291658103466034},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4005363881587982},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.13328957557678223},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.12653657793998718},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10445890","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445890","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":[{"id":"https://metadata.un.org/sdg/5","score":0.4699999988079071,"display_name":"Gender equality"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W211912913","https://openalex.org/W1965868009","https://openalex.org/W2003653478","https://openalex.org/W2102548748","https://openalex.org/W2143172006","https://openalex.org/W2146334809","https://openalex.org/W2300884049","https://openalex.org/W2313339984","https://openalex.org/W2742542661","https://openalex.org/W2747172199","https://openalex.org/W2786672974","https://openalex.org/W2889717020","https://openalex.org/W2950374865","https://openalex.org/W2951442257","https://openalex.org/W3032325810","https://openalex.org/W3099284785","https://openalex.org/W3160329778","https://openalex.org/W3162538529","https://openalex.org/W3162811262","https://openalex.org/W3196543367","https://openalex.org/W3197580070","https://openalex.org/W3209984917","https://openalex.org/W3211224152","https://openalex.org/W3215155711","https://openalex.org/W4312951904","https://openalex.org/W4361994820","https://openalex.org/W6748816842","https://openalex.org/W6763984584","https://openalex.org/W6803378298"],"related_works":["https://openalex.org/W2029072726","https://openalex.org/W91913183","https://openalex.org/W2936882366","https://openalex.org/W1987182177","https://openalex.org/W2736893848","https://openalex.org/W2128698257","https://openalex.org/W1544055438","https://openalex.org/W3003450285","https://openalex.org/W2013608943","https://openalex.org/W2085024878"],"abstract_inverted_index":{"Dimensional":[0],"representations":[1],"of":[2,86,162,173],"speech":[3,47,97],"emotions":[4],"such":[5,29],"as":[6,30,50,61],"the":[7,42,79,113,171,174],"arousal-valence":[8],"(AV)":[9],"representation":[10,45,81,99,108],"provide":[11],"a":[12,51,92,131],"continuous":[13],"and":[14,17,34,94,103,167],"fine-grained":[15],"description":[16],"control":[18],"than":[19,69],"their":[20],"categorical":[21,70,83],"counterparts.":[22],"They":[23],"have":[24],"wide":[25],"applications":[26],"in":[27],"tasks":[28],"dynamic":[31],"emotion":[32,44,84,104],"understanding":[33],"expressive":[35],"text-to-speech":[36],"synthesis.":[37],"Existing":[38],"methods":[39,56,142],"that":[40,127],"predict":[41],"dimensional":[43,62],"from":[46,82],"cast":[48],"it":[49],"supervised":[52,140],"regression":[53,141],"task.":[54],"These":[55],"face":[57],"data":[58],"scarcity":[59],"issues,":[60],"annotations":[63,149],"are":[64],"much":[65],"harder":[66],"to":[67,77,112,118,138],"acquire":[68],"labels.":[71],"In":[72],"this":[73],"work,":[74],"we":[75],"propose":[76],"learn":[78],"AV":[80,115,148,158,163,176],"labels":[85],"speech.":[87],"We":[88],"start":[89],"by":[90],"learning":[91],"rich":[93],"emotion-relevant":[95],"high-dimensional":[96],"feature":[98],"using":[100],"self-supervised":[101],"pre-training":[102],"classification":[105],"fine-tuning.":[106],"This":[107,152],"is":[109],"then":[110],"mapped":[111],"2D":[114],"space":[116],"according":[117],"psychological":[119],"findings":[120],"through":[121],"anchored":[122],"dimensionality":[123],"reduction.":[124],"Experiments":[125],"show":[126],"our":[128,154],"method":[129],"achieves":[130],"Concordance":[132],"Correlation":[133],"Coefficient":[134],"(CCC)":[135],"performance":[136],"comparable":[137],"state-of-the-art":[139],"on":[143,157,165],"IEMO-CAP":[144],"without":[145],"leveraging":[146],"ground-truth":[147],"during":[150],"training.":[151],"validates":[153],"proposed":[155],"approach":[156],"prediction.":[159],"Furthermore,":[160],"visualization":[161],"predictions":[164],"MEAD":[166],"EmoDB":[168],"datasets":[169],"shows":[170],"interpretability":[172],"learned":[175],"representations.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}