{"id":"https://openalex.org/W4322730953","doi":"https://doi.org/10.1109/taslp.2023.3250840","title":"Learning Speech Emotion Representations in the Quaternion Domain","display_name":"Learning Speech Emotion Representations in the Quaternion Domain","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4322730953","doi":"https://doi.org/10.1109/taslp.2023.3250840"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3250840","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3250840","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10057076.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10057076.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014462103","display_name":"Eric Guizzo","orcid":"https://orcid.org/0000-0002-2857-4140"},"institutions":[{"id":"https://openalex.org/I125768316","display_name":"Northampton Community College","ror":"https://ror.org/05j27jv73","country_code":"US","type":"education","lineage":["https://openalex.org/I125768316"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Guizzo","raw_affiliation_strings":["Department of Computer Science, City, University of London, Northampton Square, London, U.K"],"raw_orcid":"https://orcid.org/0000-0002-2857-4140","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City, University of London, Northampton Square, London, U.K","institution_ids":["https://openalex.org/I125768316"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018493892","display_name":"Tillman Weyde","orcid":"https://orcid.org/0000-0001-8028-9905"},"institutions":[{"id":"https://openalex.org/I125768316","display_name":"Northampton Community College","ror":"https://ror.org/05j27jv73","country_code":"US","type":"education","lineage":["https://openalex.org/I125768316"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tillman Weyde","raw_affiliation_strings":["Department of Computer Science, City, University of London, Northampton Square, London, U.K"],"raw_orcid":"https://orcid.org/0000-0001-8028-9905","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City, University of London, Northampton Square, London, U.K","institution_ids":["https://openalex.org/I125768316"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022153057","display_name":"Simone Scardapane","orcid":"https://orcid.org/0000-0003-0881-8344"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Simone Scardapane","raw_affiliation_strings":["Department of Information Engineering, Electronics and Telecommunications (DIET), Sapienza University of Rome, Rome, Italy"],"raw_orcid":"https://orcid.org/0000-0003-0881-8344","affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Electronics and Telecommunications (DIET), Sapienza University of Rome, Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019647783","display_name":"Danilo Comminiello","orcid":"https://orcid.org/0000-0003-4067-4504"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Danilo Comminiello","raw_affiliation_strings":["Department of Information Engineering, Electronics and Telecommunications (DIET), Sapienza University of Rome, Rome, Italy"],"raw_orcid":"https://orcid.org/0000-0003-4067-4504","affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Electronics and Telecommunications (DIET), Sapienza University of Rome, Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.9663,"has_fulltext":true,"cited_by_count":32,"citation_normalized_percentile":{"value":0.97529298,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"31","issue":null,"first_page":"1200","last_page":"1212"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9891999959945679,"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":0.9891999959945679,"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/T14394","display_name":"Cognitive Science and Education Research","score":0.9638000130653381,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9569000005722046,"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/quaternion","display_name":"Quaternion","score":0.8072822093963623},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5919361114501953},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.4587216377258301},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4502871632575989},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4393937885761261},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3940998613834381},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.3800176680088043},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.3423774242401123},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.33164823055267334},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3238903284072876},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2270049750804901},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.10619732737541199}],"concepts":[{"id":"https://openalex.org/C200127275","wikidata":"https://www.wikidata.org/wiki/Q173853","display_name":"Quaternion","level":2,"score":0.8072822093963623},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5919361114501953},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4587216377258301},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4502871632575989},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4393937885761261},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3940998613834381},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.3800176680088043},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3423774242401123},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.33164823055267334},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3238903284072876},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2270049750804901},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.10619732737541199},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2023.3250840","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3250840","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10057076.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:iris.uniroma1.it:11573/1684326","is_oa":true,"landing_page_url":"https://hdl.handle.net/11573/1684326","pdf_url":"https://iris.uniroma1.it/bitstream/11573/1684326/1/Guizzo_Learning_2023.pdf","source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:openaccess.city.ac.uk:30187","is_oa":true,"landing_page_url":"https://openaccess.city.ac.uk/view/creators_id/t=2Ee=2Eweyde.html>","pdf_url":"https://openaccess.city.ac.uk/id/eprint/30187/1/Learning_Speech_Emotion_Representations_in_the_Quaternion_Domain.pdf","source":{"id":"https://openalex.org/S4306401940","display_name":"City Research Online (City University London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I180825142","host_organization_name":"City, University of London","host_organization_lineage":["https://openalex.org/I180825142"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2023.3250840","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3250840","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10057076.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6207027699","display_name":null,"funder_award_id":"RG11916B88E1942F","funder_id":"https://openalex.org/F4320322510","funder_display_name":"Sapienza Universit\u00e0 di Roma"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320322510","display_name":"Sapienza Universit\u00e0 di Roma","ror":"https://ror.org/02be6w209"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4322730953.pdf","grobid_xml":"https://content.openalex.org/works/W4322730953.grobid-xml"},"referenced_works_count":82,"referenced_works":["https://openalex.org/W79136065","https://openalex.org/W175750906","https://openalex.org/W1800809792","https://openalex.org/W1844030040","https://openalex.org/W1940245494","https://openalex.org/W1972280480","https://openalex.org/W1976393675","https://openalex.org/W1985348972","https://openalex.org/W2009059481","https://openalex.org/W2011688148","https://openalex.org/W2028685794","https://openalex.org/W2032254851","https://openalex.org/W2055911634","https://openalex.org/W2074788634","https://openalex.org/W2080853599","https://openalex.org/W2087618018","https://openalex.org/W2090550497","https://openalex.org/W2097854005","https://openalex.org/W2111926505","https://openalex.org/W2118911453","https://openalex.org/W2130071409","https://openalex.org/W2141853407","https://openalex.org/W2146334809","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2222099799","https://openalex.org/W2295001676","https://openalex.org/W2399733683","https://openalex.org/W2408520939","https://openalex.org/W2583743457","https://openalex.org/W2598207902","https://openalex.org/W2741036097","https://openalex.org/W2759270896","https://openalex.org/W2785737646","https://openalex.org/W2903311573","https://openalex.org/W2905556235","https://openalex.org/W2937291509","https://openalex.org/W2952383053","https://openalex.org/W2963196848","https://openalex.org/W2963230471","https://openalex.org/W2963719423","https://openalex.org/W2973042454","https://openalex.org/W2985332775","https://openalex.org/W3008039831","https://openalex.org/W3014475539","https://openalex.org/W3015449694","https://openalex.org/W3024464021","https://openalex.org/W3076928706","https://openalex.org/W3081192838","https://openalex.org/W3097681340","https://openalex.org/W3107298252","https://openalex.org/W3108618362","https://openalex.org/W3116016199","https://openalex.org/W3122349645","https://openalex.org/W3135018693","https://openalex.org/W3144479330","https://openalex.org/W3161108810","https://openalex.org/W3162589478","https://openalex.org/W3163157357","https://openalex.org/W3163462841","https://openalex.org/W3196711847","https://openalex.org/W3197642003","https://openalex.org/W3201040525","https://openalex.org/W4210600196","https://openalex.org/W4225982742","https://openalex.org/W4226095941","https://openalex.org/W4283698005","https://openalex.org/W4287637191","https://openalex.org/W4289516314","https://openalex.org/W4311903586","https://openalex.org/W4312984359","https://openalex.org/W4372259942","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6638349531","https://openalex.org/W6684191040","https://openalex.org/W6733353833","https://openalex.org/W6747815419","https://openalex.org/W6757382257","https://openalex.org/W6784350903","https://openalex.org/W6796753186","https://openalex.org/W6800666689"],"related_works":["https://openalex.org/W3127350447","https://openalex.org/W3108700312","https://openalex.org/W4225472102","https://openalex.org/W2382948573","https://openalex.org/W2887325221","https://openalex.org/W2084651007","https://openalex.org/W2184550115","https://openalex.org/W3121191907","https://openalex.org/W2391028436","https://openalex.org/W2600085362"],"abstract_inverted_index":{"The":[0,15,241],"modeling":[1],"of":[2,19,29,39,78,95,119,123,129,186,224,238],"human":[3],"emotion":[4,21,83,104,171],"expression":[5],"in":[6,42,99,211],"speech":[7,20,82,170],"signals":[8],"is":[9,61,87,244],"an":[10,50,158],"important,":[11],"yet":[12],"challenging":[13],"task.":[14],"high":[16],"resource":[17],"demand":[18,223],"recognition":[22,84,172],"models,":[23],"combined":[24],"with":[25,200,204],"the":[26,35,76,111,114,124,127,141,147,184,201,212,221,236],"general":[27],"scarcity":[28],"emotion-labelled":[30],"data":[31],"are":[32,155],"obstacles":[33],"to":[34,52,101,117,150],"development":[36],"and":[37,106,137,181,195,231],"application":[38],"effective":[40,159],"solutions":[41],"this":[43,46],"field.":[44],"In":[45],"paper,":[47],"we":[48,227],"present":[49],"approach":[51,168],"jointly":[53],"circumvent":[54],"these":[55],"difficulties.":[56],"Our":[57],"method,":[58],"named":[59],"RH-emo,":[60],"a":[62,88,96,102,107,130,162,208],"novel":[63],"semi-supervised":[64],"architecture":[65],"aimed":[66],"at":[67],"extracting":[68],"quaternion":[69,144,163],"embeddings":[70,125,202],"from":[71],"real-valued":[72,97,103,189],"monoaural":[73],"spectrograms,":[74],"enabling":[75],"use":[77],"quaternion-valued":[79,108,197],"networks":[80],"for":[81,126,157,215],"tasks.":[85],"RH-emo":[86,242],"hybrid":[89],"real/quaternion":[90],"autoencoder":[91],"network":[92],"that":[93,154,234],"consists":[94],"encoder":[98],"parallel":[100],"classifier":[105,115],"decoder.":[109],"On":[110,140],"one":[112],"hand,":[113,143],"permits":[116],"optimization":[118],"each":[120],"latent":[121,148],"axis":[122],"classification":[128],"specific":[131],"emotion-related":[132],"characteristic:":[133],"valence,":[134],"arousal,":[135],"dominance,":[136],"overall":[138],"emotion.":[139],"other":[142],"reconstruction":[145],"enables":[146],"dimension":[149],"develop":[151],"intra-channel":[152],"correlations":[153],"required":[156],"representation":[160],"as":[161],"entity.":[164],"We":[165,206],"test":[166,213],"our":[167,239],"on":[169],"tasks":[173],"using":[174],"four":[175],"popular":[176],"datasets:":[177],"IEMOCAP,":[178],"RAVDESS,":[179],"EmoDB,":[180],"TESS,":[182],"comparing":[183],"performance":[185],"three":[187],"well-established":[188],"CNN":[190],"architectures":[191],"(AlexNet,":[192],"ResNet-50,":[193],"VGG)":[194],"their":[196],"equivalent":[198],"fed":[199],"created":[203],"RH-emo.":[205],"obtain":[207],"consistent":[209],"improvement":[210],"accuracy":[214],"all":[216],"datasets,":[217],"while":[218],"drastically":[219],"reducing":[220],"resources'":[222],"models.":[225],"Moreover,":[226],"performed":[228],"additional":[229],"experiments":[230],"ablation":[232],"studies":[233],"confirm":[235],"effectiveness":[237],"approach.":[240],"repository":[243],"available":[245],"at:":[246],"<uri":[247],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[248],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/ispamm/rhemo</uri>":[249],".":[250]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}