{"id":"https://openalex.org/W4392931772","doi":"https://doi.org/10.1109/icassp48485.2024.10446997","title":"Improving Domain Generalization in Speech Emotion Recognition with Whisper","display_name":"Improving Domain Generalization in Speech Emotion Recognition with Whisper","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392931772","doi":"https://doi.org/10.1109/icassp48485.2024.10446997"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446997","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446997","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/A5033923197","display_name":"Erik Goron","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Erik Goron","raw_affiliation_strings":["Maaind Technologies"],"affiliations":[{"raw_affiliation_string":"Maaind Technologies","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094186396","display_name":"Lena Asai","orcid":null},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lena Asai","raw_affiliation_strings":["Maaind Technologies","University College London"],"affiliations":[{"raw_affiliation_string":"Maaind Technologies","institution_ids":[]},{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073864210","display_name":"Elias Rut","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elias Rut","raw_affiliation_strings":["Maaind Technologies"],"affiliations":[{"raw_affiliation_string":"Maaind Technologies","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103257294","display_name":"Martin Dinov","orcid":"https://orcid.org/0000-0003-3644-0115"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin Dinov","raw_affiliation_strings":["Maaind Technologies"],"affiliations":[{"raw_affiliation_string":"Maaind Technologies","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5033923197"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.4787,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.9687101,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"11631","last_page":"11635"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983000159263611,"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/transformer","display_name":"Transformer","score":0.8257952332496643},{"id":"https://openalex.org/keywords/paralanguage","display_name":"Paralanguage","score":0.7642378807067871},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7633268237113953},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.5235657095909119},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5013842582702637},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4975614845752716},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4831342399120331},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4502505660057068},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4477066993713379},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3672332763671875},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34938186407089233},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.08533871173858643},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.08038750290870667},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06415364146232605},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.057016730308532715}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.8257952332496643},{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.7642378807067871},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7633268237113953},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.5235657095909119},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5013842582702637},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4975614845752716},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4831342399120331},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4502505660057068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4477066993713379},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3672332763671875},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34938186407089233},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.08533871173858643},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.08038750290870667},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06415364146232605},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.057016730308532715},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446997","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446997","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":47,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W2030931454","https://openalex.org/W2032254851","https://openalex.org/W2146334809","https://openalex.org/W2768783441","https://openalex.org/W2803193013","https://openalex.org/W2810556878","https://openalex.org/W2908510526","https://openalex.org/W2922711788","https://openalex.org/W2924116307","https://openalex.org/W2964128364","https://openalex.org/W2995181338","https://openalex.org/W3008554267","https://openalex.org/W3031325541","https://openalex.org/W3036601975","https://openalex.org/W3096615741","https://openalex.org/W3098571047","https://openalex.org/W3122100772","https://openalex.org/W3122349645","https://openalex.org/W3152037350","https://openalex.org/W3193714551","https://openalex.org/W3197580070","https://openalex.org/W3197642003","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3211224152","https://openalex.org/W4210505096","https://openalex.org/W4224918181","https://openalex.org/W4225302953","https://openalex.org/W4225694800","https://openalex.org/W4287728573","https://openalex.org/W4297841697","https://openalex.org/W4298201799","https://openalex.org/W4298201858","https://openalex.org/W4308521113","https://openalex.org/W4311000453","https://openalex.org/W4361994820","https://openalex.org/W4372341110","https://openalex.org/W4375869379","https://openalex.org/W4392172995","https://openalex.org/W6605703937","https://openalex.org/W6745840574","https://openalex.org/W6757817989","https://openalex.org/W6780218876","https://openalex.org/W6780233385","https://openalex.org/W6803378298","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W2064370490","https://openalex.org/W3166813893","https://openalex.org/W2910013580","https://openalex.org/W2391900574","https://openalex.org/W3200958703","https://openalex.org/W1990078780","https://openalex.org/W3108667266","https://openalex.org/W2376619307","https://openalex.org/W3118437876","https://openalex.org/W1527444722"],"abstract_inverted_index":{"Transformers":[0],"have":[1],"been":[2,30],"used":[3],"successfully":[4,136],"in":[5,23,42,78],"a":[6,47,60],"variety":[7,48],"of":[8,17,49,91,103],"settings,":[9],"including":[10,51],"Speech":[11],"Emotion":[12],"Recognition":[13],"(SER).":[14],"However,":[15],"use":[16],"the":[18,95,104],"latest":[19],"transformer":[20],"base":[21,62],"models":[22,119],"domain":[24],"generalization":[25],"(DG)":[26],"settings":[27],"has":[28],"mostly":[29],"unexplored":[31],"or":[32],"only":[33],"weakly":[34],"explored.":[35],"We":[36,68,100],"present":[37],"here":[38,121],"our":[39,71],"state-of-the-art":[40],"results":[41,77],"discrete":[43],"emotion":[44],"recognition":[45],"across":[46,94],"datasets,":[50,55],"acted":[52],"and":[53],"non-acted":[54],"showing":[56],"that":[57,70],"Whisper":[58,76],"is":[59],"powerful":[61],"Transformer":[63,113,118],"model":[64],"for":[65],"this":[66],"task.":[67],"show":[69,125],"approach":[72],"to":[73,111,128],"DG":[74],"with":[75,85,139],"accuracy":[79],"surpassing":[80],"all":[81,116],"previously":[82],"published":[83],"results,":[84],"an":[86,126],"Unweighted":[87],"Average":[88],"Recall":[89],"(UAR)":[90],"74.5%":[92],"averaged":[93],"6":[96],"distinct":[97],"datasets":[98],"used.":[99],"discuss":[101],"some":[102],"possible":[105],"reasons":[106],"behind":[107],"Whisper\u2019s":[108],"superior":[109],"performance":[110],"other":[112],"models,":[114],"though":[115],"3":[117],"evaluated":[120],"(HuBERT,":[122],"WavLM,":[123],"Whisper)":[124],"ability":[127],"generalize":[129],"as":[130,132],"well":[131],"learn":[133],"paralinguistic":[134],"information":[135],"through":[137],"fine-tuning":[138],"relatively":[140],"few":[141],"examples.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":4}],"updated_date":"2026-03-05T09:29:38.588285","created_date":"2025-10-10T00:00:00"}
