{"id":"https://openalex.org/W7155405875","doi":"https://doi.org/10.1145/3797552.3797704","title":"Benchmarking Transformer Architectures for Speech Emotion Recognition","display_name":"Benchmarking Transformer Architectures for Speech Emotion Recognition","publication_year":2025,"publication_date":"2025-11-21","ids":{"openalex":"https://openalex.org/W7155405875","doi":"https://doi.org/10.1145/3797552.3797704"},"language":null,"primary_location":{"id":"doi:10.1145/3797552.3797704","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797552.3797704","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 4th International Conference on Artificial Intelligence and Education","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3797552.3797704","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Qichen Wang","orcid":"https://orcid.org/0009-0003-5638-1498"},"institutions":[{"id":"https://openalex.org/I106645853","display_name":"Changchun University of Science and Technology","ror":"https://ror.org/007mntk44","country_code":"CN","type":"education","lineage":["https://openalex.org/I106645853"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qichen Wang","raw_affiliation_strings":["Changchun University of Science and Technology, Changchun, Jilin, China,"],"raw_orcid":"https://orcid.org/0009-0003-5638-1498","affiliations":[{"raw_affiliation_string":"Changchun University of Science and Technology, Changchun, Jilin, China,","institution_ids":["https://openalex.org/I106645853"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I106645853"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.80614111,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"954","last_page":"960"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9911999702453613,"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":0.9911999702453613,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.0006000000284984708,"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/benchmarking","display_name":"Benchmarking","score":0.6622999906539917},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5891000032424927},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5580000281333923},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4765999913215637},{"id":"https://openalex.org/keywords/confusion-matrix","display_name":"Confusion matrix","score":0.47429999709129333},{"id":"https://openalex.org/keywords/confusion","display_name":"Confusion","score":0.4740000069141388},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4641999900341034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6654999852180481},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6622999906539917},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5979999899864197},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5891000032424927},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5580000281333923},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4765999913215637},{"id":"https://openalex.org/C138602881","wikidata":"https://www.wikidata.org/wiki/Q2709591","display_name":"Confusion matrix","level":2,"score":0.47429999709129333},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.4740000069141388},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4641999900341034},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46160000562667847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41359999775886536},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33379998803138733},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3303999900817871},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3206999897956848},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2563999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3797552.3797704","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797552.3797704","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 4th International Conference on Artificial Intelligence and Education","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3797552.3797704","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797552.3797704","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 4th International Conference on Artificial Intelligence and Education","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2060422862","https://openalex.org/W3025165719","https://openalex.org/W3036601975","https://openalex.org/W4361994820","https://openalex.org/W4367281761","https://openalex.org/W4372266023","https://openalex.org/W4382722605","https://openalex.org/W4382998827","https://openalex.org/W4386800155","https://openalex.org/W4392654280","https://openalex.org/W4393397422","https://openalex.org/W4400438927","https://openalex.org/W4402334360","https://openalex.org/W4403278133","https://openalex.org/W4403914130","https://openalex.org/W4404145938"],"related_works":[],"abstract_inverted_index":{"Speech":[0],"Emotion":[1],"Recognition":[2],"(SER)":[3],"has":[4],"gained":[5],"significant":[6],"attention":[7],"due":[8],"to":[9,76,80],"its":[10],"wide":[11],"applications":[12],"in":[13,156],"human\u2013computer":[14],"interaction,":[15],"healthcare,":[16],"and":[17,40,56,64,74,105,137,144,167,178,186,201],"intelligent":[18],"communication":[19],"systems.":[20],"However,":[21],"effectively":[22],"capturing":[23],"emotional":[24,82],"cues":[25],"from":[26,84],"speech":[27,198],"remains":[28],"a":[29,48,181,191],"challenging":[30],"task":[31],"because":[32],"of":[33,37,51,98,118,194],"the":[34,87,90,94,126],"complex":[35],"variability":[36],"acoustic":[38],"signals":[39],"contextual":[41],"dependencies.":[42],"In":[43],"this":[44],"study,":[45],"we":[46],"conduct":[47],"systematic":[49],"comparison":[50],"three":[52],"Transformer-based":[53,151],"architectures\u2014Conformer,":[54],"Squeezeformer,":[55],"Wav2Vec":[57,102,170],"2.0\u2014on":[58],"two":[59],"widely":[60],"used":[61],"datasets:":[62],"TESS":[63,88],"IEMOCAP.":[65],"The":[66,120],"models":[67,127,152],"are":[68],"evaluated":[69],"using":[70],"accuracy,":[71],"precision,":[72],"recall,":[73],"F1-score":[75],"assess":[77],"their":[78],"ability":[79],"distinguish":[81],"states":[83],"speech.":[85],"On":[86],"dataset,":[89],"Conformer":[91,114,159],"model":[92],"achieves":[93],"highest":[95],"overall":[96],"accuracy":[97,117],"99.58%,":[99],"followed":[100],"by":[101],"2.0":[103,171],"(\u224898%)":[104],"Squeezeformer":[106,111,179],"(97.86%),":[107],"while":[108],"on":[109],"IEMOCAP,":[110],"slightly":[112],"outperforms":[113],"with":[115,139,158],"an":[116],"99.35%.":[119],"confusion":[121,141],"matrix":[122],"analysis":[123],"reveals":[124],"that":[125,150],"achieve":[128],"near-perfect":[129],"recognition":[130,200],"for":[131,163,197,205,211],"emotions":[132],"such":[133],"as":[134],"fear,":[135],"neutral,":[136],"sad,":[138],"occasional":[140],"between":[142,184],"happy":[143],"pleasant":[145],"surprise.":[146],"These":[147],"results":[148],"demonstrate":[149],"exhibit":[153],"state-of-the-art":[154],"performance":[155],"SER,":[157],"showing":[160],"superior":[161],"capacity":[162],"modeling":[164],"both":[165],"local":[166],"global":[168],"dependencies,":[169],"providing":[172],"robust":[173],"generalization":[174],"through":[175],"self-supervised":[176],"learning,":[177],"offering":[180],"favorable":[182],"trade-off":[183],"efficiency":[185],"accuracy.":[187],"This":[188],"study":[189],"provides":[190],"comprehensive":[192],"benchmark":[193],"Transformer":[195],"architectures":[196],"emotion":[199],"offers":[202],"valuable":[203],"insights":[204],"developing":[206],"efficient,":[207],"high-performance":[208],"SER":[209],"systems":[210],"real-world":[212],"applications.":[213]},"counts_by_year":[],"updated_date":"2026-04-24T06:07:52.864757","created_date":"2026-04-24T00:00:00"}