{"id":"https://openalex.org/W4388820940","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317109","title":"Ensembling Multilingual Pre-Trained Models for Predicting Multi-Label Regression Emotion Share from Speech","display_name":"Ensembling Multilingual Pre-Trained Models for Predicting Multi-Label Regression Emotion Share from Speech","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388820940","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317109"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc58517.2023.10317109","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc58517.2023.10317109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":["National Institute of Advanced Industrial Science and Technology,Japan","National Institute of Advanced Industrial Science and Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology,Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology, 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":["National Institute of Advanced Industrial Science and Technology,Japan","National Institute of Advanced Industrial Science and Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology,Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology, 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":0.9452,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.77262699,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1026","last_page":"1029"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998000264167786,"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":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9952999949455261,"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/T10860","display_name":"Speech and Audio Processing","score":0.9951000213623047,"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":0.746069610118866},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6826503872871399},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6115332841873169},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5400403738021851},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5181230902671814},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.5079155564308167},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.48334023356437683},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4688756465911865},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.46510013937950134},{"id":"https://openalex.org/keywords/spearmans-rank-correlation-coefficient","display_name":"Spearman's rank correlation coefficient","score":0.46002641320228577},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4471820890903473},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.44157400727272034},{"id":"https://openalex.org/keywords/rank-correlation","display_name":"Rank correlation","score":0.4382568597793579},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.43701666593551636},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42932891845703125},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.42859748005867004},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.4262080192565918},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12104487419128418},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1060221791267395}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.746069610118866},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6826503872871399},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6115332841873169},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5400403738021851},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5181230902671814},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.5079155564308167},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.48334023356437683},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4688756465911865},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.46510013937950134},{"id":"https://openalex.org/C159744936","wikidata":"https://www.wikidata.org/wiki/Q1126730","display_name":"Spearman's rank correlation coefficient","level":2,"score":0.46002641320228577},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4471820890903473},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.44157400727272034},{"id":"https://openalex.org/C101601086","wikidata":"https://www.wikidata.org/wiki/Q3753228","display_name":"Rank correlation","level":2,"score":0.4382568597793579},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.43701666593551636},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42932891845703125},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.42859748005867004},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4262080192565918},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12104487419128418},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1060221791267395},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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":1,"locations":[{"id":"doi:10.1109/apsipaasc58517.2023.10317109","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc58517.2023.10317109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7300000190734863}],"awards":[],"funders":[{"id":"https://openalex.org/F4320337495","display_name":"Technology Development","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2090777335","https://openalex.org/W2144005487","https://openalex.org/W2573032414","https://openalex.org/W2637507649","https://openalex.org/W2746419079","https://openalex.org/W2897337310","https://openalex.org/W2905841571","https://openalex.org/W2963194800","https://openalex.org/W2963686995","https://openalex.org/W3028108576","https://openalex.org/W3036601975","https://openalex.org/W3114925916","https://openalex.org/W3115774049","https://openalex.org/W3134759918","https://openalex.org/W3213029956","https://openalex.org/W4311000453","https://openalex.org/W4361994820","https://openalex.org/W4372263897","https://openalex.org/W4378105483","https://openalex.org/W6640802321","https://openalex.org/W6670227514","https://openalex.org/W6746941363","https://openalex.org/W6760857467","https://openalex.org/W6780218876","https://openalex.org/W6847363464","https://openalex.org/W6852061275","https://openalex.org/W6852667952","https://openalex.org/W6852909395"],"related_works":["https://openalex.org/W2096962026","https://openalex.org/W2319525095","https://openalex.org/W4251214348","https://openalex.org/W2034896522","https://openalex.org/W2368363712","https://openalex.org/W2031235730","https://openalex.org/W2153289787","https://openalex.org/W2354721754","https://openalex.org/W2562018983","https://openalex.org/W1956723527"],"abstract_inverted_index":{"Speech":[0],"emotion":[1,13,35,54,76],"recognition":[2,14,55,78],"has":[3],"evolved":[4],"from":[5,15,79,89,116,174],"research":[6],"to":[7,41,51,69,85],"practical":[8],"applications.":[9],"Previous":[10],"studies":[11],"of":[12,29,34,72,103,145,170,180],"speech":[16,53],"have":[17],"focused":[18],"on":[19,22],"developing":[20],"models":[21,43,56,74,82],"certain":[23],"datasets":[24],"like":[25],"IEMOCAP.":[26],"The":[27,81,93,120],"lack":[28],"data":[30,88],"in":[31,44,59],"the":[32,45,101,104,112,117,125,131,150,155,158,167,183,188],"domain":[33],"modeling":[36],"emerges":[37],"as":[38,48,50],"a":[39,60,108,134,171],"challenge":[40],"evaluate":[42,52],"other":[46],"dataset,":[47],"well":[49],"that":[57,96],"work":[58],"multilingual":[61,87],"setting.":[62],"This":[63],"paper":[64],"proposes":[65],"an":[66],"ensemble":[67,97],"learning":[68,98],"fuse":[70],"results":[71,94],"pre-trained":[73],"for":[75,149,154,182,187],"share":[77],"speech.":[80],"were":[83],"chosen":[84],"accommodate":[86],"English":[90],"and":[91,111,185],"Spanish.":[92],"show":[95],"can":[99],"improve":[100],"performance":[102,121],"baseline":[105],"model":[106,110,115],"with":[107,137],"single":[109],"previous":[113,168],"best":[114],"late":[118],"fusion.":[119],"is":[122,133,147,160],"measured":[123],"using":[124],"Spearman":[126,141],"rank":[127,142],"correlation":[128,143],"coefficient":[129,144],"since":[130],"task":[132],"regression":[135],"problem":[136],"ranking":[138],"values.":[139],"A":[140],"0.537":[146],"reported":[148],"test":[151,184],"set,":[152,157],"while":[153],"development":[156],"score":[159],"0.524.":[161],"These":[162],"scores":[163,179],"are":[164],"higher":[165],"than":[166],"study":[169],"fusion":[172],"method":[173],"monolingual":[175],"data,":[176],"which":[177],"achieved":[178],"0.476":[181],"0.470":[186],"development.":[189]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}