{"id":"https://openalex.org/W4312951904","doi":"https://doi.org/10.1109/access.2022.3225198","title":"Evaluating Self-Supervised Speech Representations for Speech Emotion Recognition","display_name":"Evaluating Self-Supervised Speech Representations for Speech Emotion Recognition","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4312951904","doi":"https://doi.org/10.1109/access.2022.3225198"},"language":"en","primary_location":{"id":"doi:10.1109/access.2022.3225198","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3225198","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09964237.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09964237.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065879041","display_name":"Bagus Tris Atmaja","orcid":"https://orcid.org/0000-0003-1560-2824"},"institutions":[{"id":"https://openalex.org/I166843116","display_name":"Sepuluh Nopember Institute of Technology","ror":"https://ror.org/05kbmmt89","country_code":"ID","type":"education","lineage":["https://openalex.org/I166843116"]},{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["ID","JP"],"is_corresponding":false,"raw_author_name":"Bagus Tris Atmaja","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology, Tsukuba, Japan","Department of Engineering Physics, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia"],"raw_orcid":"https://orcid.org/0000-0003-1560-2824","affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology, Tsukuba, Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"Department of Engineering Physics, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia","institution_ids":["https://openalex.org/I166843116"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046057045","display_name":"Akira Sasou","orcid":"https://orcid.org/0000-0003-1700-0325"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akira Sasou","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology, Tsukuba, Japan"],"raw_orcid":"https://orcid.org/0000-0003-1700-0325","affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology, Tsukuba, Japan","institution_ids":["https://openalex.org/I73613424"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":5.0541,"has_fulltext":true,"cited_by_count":38,"citation_normalized_percentile":{"value":0.96273447,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"10","issue":null,"first_page":"124396","last_page":"124407"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9994999766349792,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9994000196456909,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7575821280479431},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6856818795204163},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5435492992401123},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5081138610839844},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.48963433504104614},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4895099401473999},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.46457892656326294},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44870486855506897},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4423363208770752},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4270259141921997},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.42196351289749146},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.2922671437263489},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06760203838348389}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7575821280479431},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6856818795204163},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5435492992401123},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5081138610839844},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.48963433504104614},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4895099401473999},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.46457892656326294},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44870486855506897},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4423363208770752},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4270259141921997},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.42196351289749146},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2922671437263489},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06760203838348389},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2022.3225198","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3225198","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09964237.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:b96d722eaec143edb7c26af3ac4ec8e7","is_oa":true,"landing_page_url":"https://doaj.org/article/b96d722eaec143edb7c26af3ac4ec8e7","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 10, Pp 124396-124407 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2022.3225198","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3225198","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09964237.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G6725152017","display_name":null,"funder_award_id":"JPNP20006","funder_id":"https://openalex.org/F4320321034","funder_display_name":"New Energy and Industrial Technology Development Organization"}],"funders":[{"id":"https://openalex.org/F4320321034","display_name":"New Energy and Industrial Technology Development Organization","ror":"https://ror.org/0055k7a87"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4312951904.pdf","grobid_xml":"https://content.openalex.org/works/W4312951904.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1565746575","https://openalex.org/W2037557484","https://openalex.org/W2146334809","https://openalex.org/W2342475039","https://openalex.org/W2526050071","https://openalex.org/W2611652970","https://openalex.org/W2648194195","https://openalex.org/W2742542661","https://openalex.org/W2883409523","https://openalex.org/W2971275122","https://openalex.org/W2972943112","https://openalex.org/W2982223350","https://openalex.org/W3006926732","https://openalex.org/W3015356564","https://openalex.org/W3015707499","https://openalex.org/W3041561163","https://openalex.org/W3097286738","https://openalex.org/W3097488938","https://openalex.org/W3101133634","https://openalex.org/W3122349645","https://openalex.org/W3166353905","https://openalex.org/W3196876847","https://openalex.org/W3197580070","https://openalex.org/W3197994565","https://openalex.org/W3198528147","https://openalex.org/W3198858531","https://openalex.org/W3203140070","https://openalex.org/W3204696009","https://openalex.org/W3206252155","https://openalex.org/W3209984917","https://openalex.org/W4212956106","https://openalex.org/W4221089191","https://openalex.org/W4307482387","https://openalex.org/W6785591002","https://openalex.org/W6799344719"],"related_works":["https://openalex.org/W4298261218","https://openalex.org/W4388820305","https://openalex.org/W3151376046","https://openalex.org/W4388404911","https://openalex.org/W430347950","https://openalex.org/W2992378684","https://openalex.org/W3169479349","https://openalex.org/W1987021544","https://openalex.org/W2147998355","https://openalex.org/W2105439218"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1,190],"has":[2],"recently":[3],"been":[4],"implemented":[5],"widely":[6],"in":[7,141],"speech":[8,28,39,52,65,75,90,131,156,192],"processing":[9,29],"areas,":[10],"replacing":[11],"conventional":[12],"acoustic":[13,58,70],"feature":[14,71],"extraction":[15],"to":[16,31,55,92,102,148],"extract":[17,32],"meaningful":[18],"information":[19,34],"from":[20,35,99,167],"speech.":[21],"One":[22],"of":[23,27,50,96,144,155,188],"the":[24,48,56,80,85,94,100,103,127,142,152,164],"challenging":[25],"applications":[26],"is":[30,45,139],"affective":[33],"speech,":[36],"commonly":[37],"called":[38],"emotion":[40,76,160,180,193],"recognition.":[41],"Until":[42],"now,":[43],"it":[44],"not":[46],"clear":[47],"position":[49],"these":[51],"representations":[53,66,91,157],"compared":[54],"classical":[57,69],"feature.":[59],"This":[60],"paper":[61],"evaluates":[62],"nineteen":[63],"self-supervised":[64,130,189],"and":[67,114,176,205],"one":[68],"for":[72,136,158,191],"five":[73,177],"distinct":[74],"recognition":[77,194],"datasets":[78],"on":[79,163,199,202,207],"same":[81],"classifier.":[82],"We":[83],"calculate":[84],"effect":[86,119],"size":[87],"among":[88,121,129],"twenty":[89],"show":[93],"magnitude":[95],"relative":[97],"differences":[98],"top":[101,107],"lowest":[104],"performance.":[105],"The":[106,123,133],"three":[108],"are":[109],"WavLM":[110],"Large,":[111,113,116],"UniSpeech-SAT":[112],"HuBERT":[115],"with":[117],"negligible":[118],"sizes":[120],"them.":[122],"significance":[124],"test":[125],"supports":[126],"difference":[128],"representations.":[132],"best":[134,153],"prediction":[135],"each":[137,159],"dataset":[138],"shown":[140],"form":[143],"a":[145],"confusion":[146],"matrix":[147],"gain":[149],"insights":[150],"into":[151],"performance":[154],"category":[161],"based":[162],"training":[165],"data":[166,204],"balanced":[168],"vs.":[169,173,178],"unbalanced":[170,208],"datasets,":[171],"English":[172],"Japanese":[174],"corpus,":[175],"six":[179],"categories.":[181],"Despite":[182],"showing":[183],"their":[184,197],"competitiveness,":[185],"this":[186],"exploration":[187],"also":[195],"shows":[196],"limitations":[198],"models":[200],"pre-trained":[201],"small":[203],"trained":[206],"datasets.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":9}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}