{"id":"https://openalex.org/W4408258400","doi":"https://doi.org/10.1109/tencon61640.2024.10903112","title":"Multi-Label Emotion Share Regression from Speech Using Pre-Trained Self-Supervised Learning Models","display_name":"Multi-Label Emotion Share Regression from Speech Using Pre-Trained Self-Supervised Learning Models","publication_year":2024,"publication_date":"2024-12-01","ids":{"openalex":"https://openalex.org/W4408258400","doi":"https://doi.org/10.1109/tencon61640.2024.10903112"},"language":"en","primary_location":{"id":"doi:10.1109/tencon61640.2024.10903112","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tencon61640.2024.10903112","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"TENCON 2024 - 2024 IEEE Region 10 Conference (TENCON)","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/A5065879041","display_name":"Bagus Tris Atmaja","orcid":"https://orcid.org/0000-0003-1560-2824"},"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":"Bagus Tris Atmaja","raw_affiliation_strings":["AIST,Tsukuba,Japan"],"raw_orcid":"https://orcid.org/0000-0003-1560-2824","affiliations":[{"raw_affiliation_string":"AIST,Tsukuba,Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"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":["AIST,Tsukuba,Japan"],"raw_orcid":"https://orcid.org/0000-0003-1700-0325","affiliations":[{"raw_affiliation_string":"AIST,Tsukuba,Japan","institution_ids":["https://openalex.org/I73613424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3055,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.69028881,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"339","last_page":"342"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9925000071525574,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9925000071525574,"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":0.9846000075340271,"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":0.9843000173568726,"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/computer-science","display_name":"Computer science","score":0.7192907929420471},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6149042844772339},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5615639686584473},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.5550727844238281},{"id":"https://openalex.org/keywords/regression-analysis","display_name":"Regression analysis","score":0.5180413722991943},{"id":"https://openalex.org/keywords/multi-label-classification","display_name":"Multi-label classification","score":0.4495502710342407},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4259330630302429},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40704771876335144},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.19496792554855347},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14778932929039001}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7192907929420471},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6149042844772339},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5615639686584473},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.5550727844238281},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.5180413722991943},{"id":"https://openalex.org/C2776482837","wikidata":"https://www.wikidata.org/wiki/Q3553958","display_name":"Multi-label classification","level":2,"score":0.4495502710342407},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4259330630302429},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40704771876335144},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.19496792554855347},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14778932929039001}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tencon61640.2024.10903112","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tencon61640.2024.10903112","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"TENCON 2024 - 2024 IEEE Region 10 Conference (TENCON)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1995562189","https://openalex.org/W2090777335","https://openalex.org/W2144005487","https://openalex.org/W2486380366","https://openalex.org/W2746419079","https://openalex.org/W2803098682","https://openalex.org/W2963194800","https://openalex.org/W3036601975","https://openalex.org/W3112736871","https://openalex.org/W3114925916","https://openalex.org/W3197580070","https://openalex.org/W3206252155","https://openalex.org/W3206495532","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3213029956","https://openalex.org/W4285251897","https://openalex.org/W4312951904","https://openalex.org/W4361994820","https://openalex.org/W4372267510","https://openalex.org/W4387968410","https://openalex.org/W4388820940","https://openalex.org/W6746941363","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W31220157","https://openalex.org/W2312753042","https://openalex.org/W4289356671","https://openalex.org/W2389155397","https://openalex.org/W2165884543","https://openalex.org/W3186837933","https://openalex.org/W2368989808","https://openalex.org/W1969346022","https://openalex.org/W2034959125","https://openalex.org/W2355687852"],"abstract_inverted_index":{"Speech":[0],"emotion":[1,18,35,46,65,83,96,137],"recognition":[2,98,139],"(SER)":[3],"has":[4],"been":[5],"enabling":[6],"natural":[7],"human-machine":[8],"interaction.":[9],"Previous":[10],"SER":[11],"only":[12],"focused":[13],"on":[14,72],"predicting":[15],"a":[16,38,127],"single":[17],"from":[19,24,37,60],"humans'":[20],"voices,":[21],"whereas":[22],"emotions":[23],"voices":[25],"might":[26],"have":[27],"multiple":[28],"categories.":[29,84],"This":[30],"study":[31],"aims":[32],"to":[33,101],"predict":[34],"share":[36,66,97,138],"voice,":[39],"i.e.,":[40],"the":[41,44,50,73,87,102,120,134],"proportion":[42],"of":[43,80,90,123,131,136],"different":[45,82],"categories":[47],"expressed":[48],"in":[49,99],"speech.":[51],"We":[52,85],"evaluated":[53,71,113],"eight":[54],"pretrained":[55,114],"self-supervised":[56],"learning":[57],"(SSL)":[58],"models":[59,69],"major":[61],"companies":[62],"for":[63,94,116],"multilingual":[64,95],"recognition.":[67],"The":[68,110],"were":[70],"Hume-Prosody":[74],"dataset,":[75],"which":[76,125],"contains":[77],"51,881":[78],"samples":[79],"nine":[81],"observed":[86],"important":[88],"factor":[89],"wider":[91],"window":[92,104],"size":[93,105],"contrast":[100],"narrow":[103],"used":[106],"(around":[107],"5.5":[108],"s).":[109],"most":[111],"effective":[112],"model":[115],"this":[117],"case":[118],"is":[119],"large":[121],"version":[122],"HuBERT,":[124],"achieved":[126],"Spearman":[128],"correlation":[129],"score":[130],"0.579,":[132],"showing":[133],"feasibility":[135],"using":[140],"SSL.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}