{"id":"https://openalex.org/W4375868941","doi":"https://doi.org/10.1109/icassp49357.2023.10096808","title":"Designing and Evaluating Speech Emotion Recognition Systems: A Reality Check Case Study with IEMOCAP","display_name":"Designing and Evaluating Speech Emotion Recognition Systems: A Reality Check Case Study with IEMOCAP","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868941","doi":"https://doi.org/10.1109/icassp49357.2023.10096808"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096808","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.1109/ICASSP49357.2023.10096808","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005132907","display_name":"N. G. Antoniou","orcid":"https://orcid.org/0000-0001-7180-7379"},"institutions":[{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]},{"id":"https://openalex.org/I4210129254","display_name":"Active Signal Technologies (United States)","ror":"https://ror.org/03q358129","country_code":"US","type":"company","lineage":["https://openalex.org/I4210129254"]}],"countries":["GR","US"],"is_corresponding":false,"raw_author_name":"Nikolaos Antoniou","raw_affiliation_strings":["Behavioral Signal Technologies,Los Angeles,CA,USA","Behavioral Signal Technologies, Los Angeles, CA, USA","Institute for Language and Speech Processing, Athena Research Center, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Behavioral Signal Technologies,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I4210129254"]},{"raw_affiliation_string":"Behavioral Signal Technologies, Los Angeles, CA, USA","institution_ids":[]},{"raw_affiliation_string":"Institute for Language and Speech Processing, Athena Research Center, Athens, Greece","institution_ids":["https://openalex.org/I4210098364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003869083","display_name":"Athanasios Katsamanis","orcid":"https://orcid.org/0000-0002-2642-2354"},"institutions":[{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]},{"id":"https://openalex.org/I4210129254","display_name":"Active Signal Technologies (United States)","ror":"https://ror.org/03q358129","country_code":"US","type":"company","lineage":["https://openalex.org/I4210129254"]}],"countries":["GR","US"],"is_corresponding":false,"raw_author_name":"Athanasios Katsamanis","raw_affiliation_strings":["Behavioral Signal Technologies,Los Angeles,CA,USA","Behavioral Signal Technologies, Los Angeles, CA, USA","Institute for Language and Speech Processing, Athena Research Center, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Behavioral Signal Technologies,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I4210129254"]},{"raw_affiliation_string":"Behavioral Signal Technologies, Los Angeles, CA, USA","institution_ids":[]},{"raw_affiliation_string":"Institute for Language and Speech Processing, Athena Research Center, Athens, Greece","institution_ids":["https://openalex.org/I4210098364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082928814","display_name":"Theodoros Giannakopoulos","orcid":null},"institutions":[{"id":"https://openalex.org/I4210129254","display_name":"Active Signal Technologies (United States)","ror":"https://ror.org/03q358129","country_code":"US","type":"company","lineage":["https://openalex.org/I4210129254"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Theodoros Giannakopoulos","raw_affiliation_strings":["Behavioral Signal Technologies,Los Angeles,CA,USA","Behavioral Signal Technologies, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Behavioral Signal Technologies,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I4210129254"]},{"raw_affiliation_string":"Behavioral Signal Technologies, Los Angeles, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I4210129254","display_name":"Active Signal Technologies (United States)","ror":"https://ror.org/03q358129","country_code":"US","type":"company","lineage":["https://openalex.org/I4210129254"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["Behavioral Signal Technologies,Los Angeles,CA,USA","Behavioral Signal Technologies, Los Angeles, CA, USA","SAIL-University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Behavioral Signal Technologies,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I4210129254"]},{"raw_affiliation_string":"Behavioral Signal Technologies, Los Angeles, CA, USA","institution_ids":[]},{"raw_affiliation_string":"SAIL-University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.1557,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.98254671,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9986000061035156,"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/computer-science","display_name":"Computer science","score":0.7932057976722717},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5127235651016235},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.509377121925354},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.4785202741622925},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4409372806549072},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.42003822326660156},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4150296747684479},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4137716293334961},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39055371284484863},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3766553997993469},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.36653172969818115},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36372944712638855},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.2797604501247406},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.26474910974502563},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10004445910453796}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7932057976722717},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5127235651016235},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.509377121925354},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.4785202741622925},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4409372806549072},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.42003822326660156},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4150296747684479},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4137716293334961},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39055371284484863},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3766553997993469},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.36653172969818115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36372944712638855},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.2797604501247406},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.26474910974502563},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10004445910453796},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096808","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:zenodo.org:8367342","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ICASSP49357.2023.10096808","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2023, 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"info:eu-repo/semantics/conferencePaper"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:8367342","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ICASSP49357.2023.10096808","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2023, 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"info:eu-repo/semantics/conferencePaper"},"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2057563799","https://openalex.org/W2146334809","https://openalex.org/W2170876097","https://openalex.org/W2583743457","https://openalex.org/W2742542661","https://openalex.org/W2972498864","https://openalex.org/W2972602947","https://openalex.org/W2972640480","https://openalex.org/W2973049979","https://openalex.org/W3006926732","https://openalex.org/W3011859875","https://openalex.org/W3036601975","https://openalex.org/W3096147072","https://openalex.org/W3097777922","https://openalex.org/W3109684201","https://openalex.org/W3162890625","https://openalex.org/W3163091219","https://openalex.org/W3163157357","https://openalex.org/W3197580070","https://openalex.org/W3197642003","https://openalex.org/W3197947674","https://openalex.org/W3198528147","https://openalex.org/W3198668286","https://openalex.org/W3198893858","https://openalex.org/W3204087964","https://openalex.org/W3206495532","https://openalex.org/W3209059054","https://openalex.org/W3211224152","https://openalex.org/W4221162793","https://openalex.org/W4221162872","https://openalex.org/W4223460604","https://openalex.org/W4296068413","https://openalex.org/W6733353833","https://openalex.org/W6780218876","https://openalex.org/W6801107960","https://openalex.org/W6803378298"],"related_works":["https://openalex.org/W2120447654","https://openalex.org/W2977179488","https://openalex.org/W2144453115","https://openalex.org/W2128223750","https://openalex.org/W2032233321","https://openalex.org/W4238532390","https://openalex.org/W2188872161","https://openalex.org/W2002978035","https://openalex.org/W2961779879","https://openalex.org/W797688974"],"abstract_inverted_index":{"There":[0],"is":[1],"an":[2,92],"imminent":[3],"need":[4],"for":[5,40,47],"guidelines":[6],"and":[7,14,44,57,65,101],"standard":[8],"test":[9,45],"sets":[10],"to":[11,42],"allow":[12],"direct":[13],"fair":[15],"comparisons":[16],"of":[17,55,72,94,109],"speech":[18],"emotion":[19],"recognition":[20],"(SER).":[21],"While":[22],"resources,":[23],"such":[24],"as":[25,36,80],"the":[26,73,81,95],"Interactive":[27],"Emotional":[28],"Dyadic":[29],"Motion":[30],"Capture":[31],"(IEMOCAP)":[32],"database,":[33],"have":[34],"emerged":[35],"widely-adopted":[37],"reference":[38],"corpora":[39],"researchers":[41],"develop":[43],"models":[46],"SER,":[48],"published":[49],"work":[50,85],"reveals":[51],"a":[52,69,107],"wide":[53],"range":[54],"assumptions":[56,99],"variety":[58],"in":[59,76,125],"its":[60],"use":[61,82],"that":[62],"challenge":[63],"reproducibility":[64,123],"generalization.":[66],"Based":[67],"on":[68,122],"critical":[70],"review":[71],"latest":[74],"advances":[75],"SER":[77,110],"using":[78,91,114],"IEMOCAP":[79],"case,":[83],"our":[84],"aims":[86],"at":[87],"two":[88],"contributions:":[89],"First,":[90],"analysis":[93],"recent":[96,115],"literature,":[97],"including":[98],"made":[100],"metrics":[102],"used":[103],"therein,":[104],"we":[105,120],"provide":[106],"set":[108],"evaluation":[111],"guidelines.":[112],"Second,":[113],"publications":[116],"with":[117],"open-sourced":[118],"implementations,":[119],"focus":[121],"assessment":[124],"SER.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2023-05-10T00:00:00"}