{"id":"https://openalex.org/W4409019678","doi":"https://doi.org/10.1109/bigcomp64353.2025.00047","title":"Enhancing Speech Emotion Recognition through Segmental Average Pooling of Self-supervised Learning Features","display_name":"Enhancing Speech Emotion Recognition through Segmental Average Pooling of Self-supervised Learning Features","publication_year":2025,"publication_date":"2025-02-09","ids":{"openalex":"https://openalex.org/W4409019678","doi":"https://doi.org/10.1109/bigcomp64353.2025.00047"},"language":"en","primary_location":{"id":"doi:10.1109/bigcomp64353.2025.00047","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigcomp64353.2025.00047","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Big Data and Smart Computing (BigComp)","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/A5005505009","display_name":"Jonghwan Hyeon","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jonghwan Hyeon","raw_affiliation_strings":["KAIST,School of Computing,Daejeon,South Korea"],"affiliations":[{"raw_affiliation_string":"KAIST,School of Computing,Daejeon,South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113670378","display_name":"Yung-Hwan Oh","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yung-Hwan Oh","raw_affiliation_strings":["KAIST,School of Computing,Daejeon,South Korea"],"affiliations":[{"raw_affiliation_string":"KAIST,School of Computing,Daejeon,South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100738829","display_name":"Youngjun Lee","orcid":"https://orcid.org/0000-0002-6705-7883"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Young-Jun Lee","raw_affiliation_strings":["KAIST,School of Computing,Daejeon,South Korea"],"affiliations":[{"raw_affiliation_string":"KAIST,School of Computing,Daejeon,South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015094039","display_name":"Ho\u2010Jin Choi","orcid":"https://orcid.org/0000-0002-3398-9543"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ho-Jin Choi","raw_affiliation_strings":["KAIST,School of Computing,Daejeon,South Korea"],"affiliations":[{"raw_affiliation_string":"KAIST,School of Computing,Daejeon,South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5005505009"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":2.5565,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.87761057,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"191","last_page":"198"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.8001999855041504,"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/T10860","display_name":"Speech and Audio Processing","score":0.8001999855041504,"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":0.7242000102996826,"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":0.7114999890327454,"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/pooling","display_name":"Pooling","score":0.8127862215042114},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7518300414085388},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7376259565353394},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6210811138153076},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5089612007141113},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.376120388507843},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36620694398880005}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.8127862215042114},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7518300414085388},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7376259565353394},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6210811138153076},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5089612007141113},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.376120388507843},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36620694398880005}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigcomp64353.2025.00047","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigcomp64353.2025.00047","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Big Data and Smart Computing (BigComp)","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":26,"referenced_works":["https://openalex.org/W2062391442","https://openalex.org/W2101724615","https://openalex.org/W2102953093","https://openalex.org/W2143350951","https://openalex.org/W2146334809","https://openalex.org/W2512885694","https://openalex.org/W2892071465","https://openalex.org/W2937584914","https://openalex.org/W2940259008","https://openalex.org/W2962770129","https://openalex.org/W2979826702","https://openalex.org/W3015427680","https://openalex.org/W3132553907","https://openalex.org/W3160039712","https://openalex.org/W3163091219","https://openalex.org/W3197580070","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4296068765","https://openalex.org/W4385153942","https://openalex.org/W4385822446","https://openalex.org/W6729220966","https://openalex.org/W6755207826","https://openalex.org/W6766673545","https://openalex.org/W6766978945","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W147410782","https://openalex.org/W2900413183","https://openalex.org/W3022252430","https://openalex.org/W4390975304","https://openalex.org/W4287804464","https://openalex.org/W3103989898","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Speech":[0],"Emotion":[1],"Recognition":[2],"(SER)":[3],"involves":[4],"analyzing":[5],"human":[6],"emotions":[7],"conveyed":[8],"through":[9],"vocal":[10],"expressions.":[11],"Recently,":[12],"self-supervised":[13],"learning":[14],"(SSL)":[15],"has":[16],"emerged":[17],"as":[18,69,164],"a":[19,55,104,148],"powerful":[20],"tool":[21],"for":[22,40,125,177,186],"SER":[23,46,162],"by":[24,83,166],"enabling":[25],"the":[26,38,77,89,92,134,174,183],"extraction":[27],"of":[28,79,91,151,190],"meaningful":[29],"representations":[30],"from":[31,137,144],"large-scale":[32],"unlabeled":[33],"audio":[34,57],"datasets,":[35],"significantly":[36],"reducing":[37],"need":[39],"manual":[41],"labeling.":[42],"However,":[43],"most":[44],"SSLbased":[45],"methods":[47],"employ":[48],"Global":[49],"Average":[50,101],"Pooling":[51,102],"(GAP)":[52],"to":[53,109,132,158],"derive":[54],"single":[56],"representation,":[58],"which":[59,169],"unintentionally":[60],"treats":[61],"all":[62],"segments,":[63,86],"including":[64],"both":[65,121,191],"verbal":[66,113],"and":[67,123,179,193],"non-verbal,":[68],"equally":[70],"important.":[71],"This":[72,154],"approach":[73],"can":[74],"result":[75],"in":[76,161,188],"dilution":[78],"crucial":[80],"emotional":[81,152],"cues":[82],"irrelevant":[84],"non-verbal":[85,117],"thereby":[87,146],"limiting":[88],"effectiveness":[90],"model.":[93],"To":[94],"address":[95],"this":[96],"challenge,":[97],"we":[98],"introduce":[99],"Segmental":[100],"(SAP),":[103],"novel":[105],"pooling":[106],"technique":[107],"designed":[108],"selectively":[110],"emphasize":[111],"informative":[112],"segments":[114],"while":[115],"disregarding":[116],"parts.":[118],"By":[119],"combining":[120],"GAP":[122,138],"SAP":[124],"SSL":[126],"features,":[127],"our":[128,167],"method":[129],"is":[130],"able":[131],"integrate":[133],"overall":[135],"context":[136],"with":[139],"more":[140],"focused":[141],"segmental":[142],"information":[143],"SAP,":[145],"capturing":[147],"richer":[149],"representation":[150],"cues.":[153],"dual-pooling":[155],"strategy":[156],"leads":[157],"significant":[159],"improvements":[160],"performance,":[163],"demonstrated":[165],"experiments,":[168],"achieved":[170],"state-of-the-art":[171],"results":[172],"on":[173,182],"IEMOCAP":[175],"dataset":[176,185],"English,":[178],"superior":[180],"performance":[181],"KEMDy19":[184],"Korean,":[187],"terms":[189],"unweighted":[192],"weighted":[194],"accuracies.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}