{"id":"https://openalex.org/W4417073360","doi":"https://doi.org/10.1145/3743093.3771083","title":"Robust speech emotion recognition using conditional transformer-based architecture","display_name":"Robust speech emotion recognition using conditional transformer-based architecture","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W4417073360","doi":"https://doi.org/10.1145/3743093.3771083"},"language":null,"primary_location":{"id":"doi:10.1145/3743093.3771083","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3771083","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3771083","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3771083","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089600882","display_name":"Hanwook Chung","orcid":"https://orcid.org/0000-0002-4829-9799"},"institutions":[{"id":"https://openalex.org/I156918239","display_name":"Intertek (Canada)","ror":"https://ror.org/00yascf89","country_code":"CA","type":"company","lineage":["https://openalex.org/I156918239","https://openalex.org/I4210140224"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Hanwook Chung","raw_affiliation_strings":["Forvia Irystec Inc., Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"Forvia Irystec Inc., Montreal, Canada","institution_ids":["https://openalex.org/I156918239"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112457726","display_name":"H.D. Yoo","orcid":"https://orcid.org/0009-0008-5337-4475"},"institutions":[{"id":"https://openalex.org/I156918239","display_name":"Intertek (Canada)","ror":"https://ror.org/00yascf89","country_code":"CA","type":"company","lineage":["https://openalex.org/I156918239","https://openalex.org/I4210140224"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hyunjin Yoo","raw_affiliation_strings":["Forvia Irystec Inc., Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"Forvia Irystec Inc., Montreal, Canada","institution_ids":["https://openalex.org/I156918239"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5089600882"],"corresponding_institution_ids":["https://openalex.org/I156918239"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42434436,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9444000124931335,"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":0.9444000124931335,"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":0.01730000041425228,"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/T11309","display_name":"Music and Audio Processing","score":0.007000000216066837,"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/robustness","display_name":"Robustness (evolution)","score":0.7317000031471252},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4456000030040741},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.438400000333786},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4339999854564667},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.43140000104904175},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.39399999380111694},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3898000121116638},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37929999828338623}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7678999900817871},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7317000031471252},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7289999723434448},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4456000030040741},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.438400000333786},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4339999854564667},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.43140000104904175},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.39399999380111694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39329999685287476},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3898000121116638},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37929999828338623},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.3118000030517578},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3098999857902527},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2928999960422516},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3743093.3771083","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3771083","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3771083","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3743093.3771083","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3771083","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3771083","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417073360.pdf","grobid_xml":"https://content.openalex.org/works/W4417073360.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1968834101","https://openalex.org/W1974387177","https://openalex.org/W2146334809","https://openalex.org/W2806051338","https://openalex.org/W2885005742","https://openalex.org/W2898940603","https://openalex.org/W2940177920","https://openalex.org/W3015267357","https://openalex.org/W3015489952","https://openalex.org/W3131332223","https://openalex.org/W3144907487","https://openalex.org/W3161428216","https://openalex.org/W3204087964","https://openalex.org/W4224932526","https://openalex.org/W4285791551","https://openalex.org/W4379193822","https://openalex.org/W4381789033","https://openalex.org/W4382725773","https://openalex.org/W4387530839","https://openalex.org/W4388821018","https://openalex.org/W4390873774","https://openalex.org/W4392034510","https://openalex.org/W4400975545","https://openalex.org/W4402112491","https://openalex.org/W4404577030","https://openalex.org/W4405868887","https://openalex.org/W4410358460","https://openalex.org/W4412836922","https://openalex.org/W4415795657"],"related_works":[],"abstract_inverted_index":{"Robustness":[0],"remains":[1],"a":[2,19,27,38,56,60,67],"fundamental":[3],"challenge":[4],"in":[5,81,119],"real-world":[6],"speech":[7,21,61,68,85,110],"recognition,":[8],"particularly":[9],"under":[10,141],"adverse":[11,120],"acoustic":[12,43,121,144],"conditions.":[13],"In":[14],"this":[15],"paper,":[16],"we":[17],"introduce":[18],"robust":[20,140],"emotion":[22,69],"recognition":[23,70],"(SER)":[24],"approach":[25],"using":[26],"conditional":[28],"transformer-based":[29],"architecture,":[30],"specifically":[31],"designed":[32],"to":[33,96,112],"maintain":[34],"consistent":[35],"performance":[36],"across":[37],"wide":[39],"range":[40],"of":[41,52,101,116],"noisy":[42,84,109,143],"environments.":[44],"The":[45,73,105],"proposed":[46,137],"convolutional":[47],"transformer":[48],"(CTr)-based":[49],"architecture":[50,138],"consists":[51],"three":[53],"primary":[54],"modules:":[55],"noise-classification":[57],"module":[58,64,71],"(NCM),":[59],"feature":[62],"enhancement":[63],"(SFEM)":[65],"and":[66,94,123,146],"(SERM).":[72],"NCM":[74],"first":[75],"identifies":[76],"the":[77,82,92,99,114,117,125,128,136,151],"noise":[78,103],"type":[79],"presented":[80],"given":[83],"features,":[86],"producing":[87],"embeddings":[88],"that":[89,134,135],"condition":[90],"both":[91],"SFEM":[93,107],"SERM":[95,118,126],"better":[97,148],"capture":[98],"characteristics":[100],"different":[102],"types.":[104],"front-end":[106],"enhances":[108],"features":[111],"improve":[113],"robustness":[115],"conditions":[122],"finally,":[124],"predicts":[127],"emotional":[129],"states.":[130],"Experimental":[131],"results":[132,149],"show":[133],"performs":[139],"various":[142],"environment":[145],"provide":[147],"than":[150],"selected":[152],"benchmark":[153],"methods.":[154]},"counts_by_year":[],"updated_date":"2026-03-12T06:13:28.667946","created_date":"2025-12-06T00:00:00"}