{"id":"https://openalex.org/W4416799068","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11248990","title":"Speech Emotion Recognition Via Entropy-Aware Score Selection","display_name":"Speech Emotion Recognition Via Entropy-Aware Score Selection","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799068","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11248990"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11248990","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11248990","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5090967603","display_name":"ChenYi Chua","orcid":null},"institutions":[{"id":"https://openalex.org/I168639165","display_name":"Singapore Institute of Technology","ror":"https://ror.org/01v2c2791","country_code":"SG","type":"education","lineage":["https://openalex.org/I168639165"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"ChenYi Chua","raw_affiliation_strings":["Singapore Institute of Technology,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Institute of Technology,Singapore","institution_ids":["https://openalex.org/I168639165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108964852","display_name":"JunKai Wong","orcid":null},"institutions":[{"id":"https://openalex.org/I168639165","display_name":"Singapore Institute of Technology","ror":"https://ror.org/01v2c2791","country_code":"SG","type":"education","lineage":["https://openalex.org/I168639165"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"JunKai Wong","raw_affiliation_strings":["Singapore Institute of Technology,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Institute of Technology,Singapore","institution_ids":["https://openalex.org/I168639165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064139325","display_name":"Chengxin Chen","orcid":"https://orcid.org/0000-0003-4510-3313"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengxin Chen","raw_affiliation_strings":["Institute Of Acoustics, Chinese Academy Of Sciences,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute Of Acoustics, Chinese Academy Of Sciences,China","institution_ids":["https://openalex.org/I4210099069"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102018159","display_name":"Xiaoxiao Miao","orcid":"https://orcid.org/0000-0002-6645-6524"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoxiao Miao","raw_affiliation_strings":["Duke Kunshan University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke Kunshan University,China","institution_ids":["https://openalex.org/I4210159968"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4954,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.8709312,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"724","last_page":"729"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9187999963760376,"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":0.9187999963760376,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.05570000037550926,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.002400000113993883,"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/pipeline","display_name":"Pipeline (software)","score":0.6399000287055969},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.631600022315979},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5023000240325928},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.38999998569488525},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.38029998540878296},{"id":"https://openalex.org/keywords/christian-ministry","display_name":"Christian ministry","score":0.3797000050544739},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.35920000076293945},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.3111000061035156}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7361000180244446},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6399000287055969},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.631600022315979},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5547999739646912},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5479999780654907},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5023000240325928},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41179999709129333},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.38999998569488525},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.38029998540878296},{"id":"https://openalex.org/C521751864","wikidata":"https://www.wikidata.org/wiki/Q1729207","display_name":"Christian ministry","level":2,"score":0.3797000050544739},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.35920000076293945},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32820001244544983},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3111000061035156},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.30399999022483826},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.2732999920845032},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2678000032901764},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11248990","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11248990","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320751","display_name":"Ministry of Education - Singapore","ror":"https://ror.org/01kcva023"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1518556865","https://openalex.org/W2146334809","https://openalex.org/W2342475039","https://openalex.org/W2619383789","https://openalex.org/W2707551695","https://openalex.org/W2888241804","https://openalex.org/W2963023579","https://openalex.org/W2963104701","https://openalex.org/W2963873807","https://openalex.org/W2964010806","https://openalex.org/W2969889150","https://openalex.org/W3015489952","https://openalex.org/W3035390927","https://openalex.org/W3128376221","https://openalex.org/W3160799772","https://openalex.org/W3209984917","https://openalex.org/W4372268605","https://openalex.org/W4390751814","https://openalex.org/W4404102681"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1,159],"paper,":[2],"we":[3],"propose":[4,57],"multimodal":[5,95],"framework":[6],"for":[7],"speech":[8,18],"emotion":[9,89],"recognition":[10],"that":[11,29,42,106],"leverages":[12],"entropy-aware":[13],"score":[14,60],"selection":[15],"to":[16,69],"combine":[17],"and":[19,38,66,102,113,145,158],"textual":[20],"predictions.":[21,77,96],"The":[22,97],"proposed":[23,108],"method":[24,109],"integrates":[25],"a":[26,39,45,58,111],"primary":[27,75],"pipeline":[28,41,76],"consists":[30,43],"of":[31,44,74,94,135],"an":[32],"acoustic":[33],"model":[34,48],"based":[35,63],"on":[36,64,99],"wav2vec2.0":[37],"secondary":[40],"sentiment":[46,79,84],"analysis":[47],"using":[49],"RoBERTaXLM,":[50],"with":[51],"transcriptions":[52],"generated":[53],"via":[54],"Whisper-large-v3.":[55],"We":[56],"late":[59],"fusion":[61],"approach":[62],"entropy":[65],"varentropy":[67],"thresholds":[68],"overcome":[70],"the":[71,100,107,155],"confidence":[72],"constraints":[73],"A":[78],"mapping":[80],"strategy":[81],"translates":[82],"three":[83],"categories":[85],"into":[86],"four":[87],"target":[88],"classes,":[90],"enabling":[91],"coherent":[92],"integration":[93],"results":[98],"IEMOCAP":[101],"MSP-IMPROV":[103],"datasets":[104],"show":[105],"offers":[110],"practical":[112],"reliable":[114],"enhancement":[115],"over":[116],"traditional":[117],"single-modality":[118],"systems<sup":[119],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[120,122],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup><sup":[121],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>Code":[123],"can":[124],"be":[125],"found":[126],"at":[127,166],"https://github.com/ExpiredTapWater/Emotion-Recognition.":[128],"This":[129],"study":[130],"is":[131,154],"supported":[132],"by":[133],"Ministry":[134],"Education,":[136],"Singapore,":[137],"under":[138],"its":[139,146],"Academic":[140],"Research":[141],"Tier":[142],"1":[143],"(R-R13-A405-0005)":[144],"SIT's":[147],"Ignition":[148],"grant":[149],"(STEM)":[150],"(R-IE3-A405-0005).":[151],"Xiaoxiao":[152],"Miao":[153],"corresponding":[156],"author":[157],"work":[160],"was":[161,165],"conducted":[162],"while":[163],"she":[164],"SIT..":[167]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}