{"id":"https://openalex.org/W4409762694","doi":"https://doi.org/10.1109/acii63134.2024.00030","title":"RobuSER: A Robustness Benchmark for Speech Emotion Recognition","display_name":"RobuSER: A Robustness Benchmark for Speech Emotion Recognition","publication_year":2024,"publication_date":"2024-09-15","ids":{"openalex":"https://openalex.org/W4409762694","doi":"https://doi.org/10.1109/acii63134.2024.00030"},"language":"en","primary_location":{"id":"doi:10.1109/acii63134.2024.00030","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acii63134.2024.00030","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 12th International Conference on Affective Computing and Intelligent Interaction (ACII)","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/A5024447977","display_name":"Antonia Petrogianni","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Antonia Petrogianni","raw_affiliation_strings":["Behavioral Signal Technologies,Athens,Greece"],"affiliations":[{"raw_affiliation_string":"Behavioral Signal Technologies,Athens,Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092639641","display_name":"Lefteris Kapelonis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lefteris Kapelonis","raw_affiliation_strings":["Behavioral Signal Technologies,Athens,Greece"],"affiliations":[{"raw_affiliation_string":"Behavioral Signal Technologies,Athens,Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005132907","display_name":"N. G. Antoniou","orcid":"https://orcid.org/0000-0001-7180-7379"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikolaos Antoniou","raw_affiliation_strings":["Behavioral Signal Technologies,Athens,Greece"],"affiliations":[{"raw_affiliation_string":"Behavioral Signal Technologies,Athens,Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005816500","display_name":"Sofia Eleftheriou","orcid":"https://orcid.org/0000-0002-8322-176X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sofia Eleftheriou","raw_affiliation_strings":["Behavioral Signal Technologies,Athens,Greece"],"affiliations":[{"raw_affiliation_string":"Behavioral Signal Technologies,Athens,Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016128076","display_name":"Petros Mitseas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Petros Mitseas","raw_affiliation_strings":["Behavioral Signal Technologies,Athens,Greece"],"affiliations":[{"raw_affiliation_string":"Behavioral Signal Technologies,Athens,Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016108502","display_name":"Dimitris Sgouropoulos","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dimitris Sgouropoulos","raw_affiliation_strings":["Behavioral Signal Technologies,Athens,Greece"],"affiliations":[{"raw_affiliation_string":"Behavioral Signal Technologies,Athens,Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061662829","display_name":"Athanasios Katsamanis","orcid":null},"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"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Athanasios Katsamanis","raw_affiliation_strings":["Behavioral Signal Technologies, Institute for Language and Speech Processing, Athena R.C,Athens,Greece"],"affiliations":[{"raw_affiliation_string":"Behavioral Signal Technologies, Institute for Language and Speech Processing, Athena R.C,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/I203474044","display_name":"National Centre of Scientific Research \"Demokritos\"","ror":"https://ror.org/038jp4m40","country_code":"GR","type":"facility","lineage":["https://openalex.org/I203474044"]},{"id":"https://openalex.org/I4387152169","display_name":"Institute of Informatics & Telecommunications","ror":"https://ror.org/0396t6k89","country_code":null,"type":"facility","lineage":["https://openalex.org/I203474044","https://openalex.org/I4387152169"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Theodoros Giannakopoulos","raw_affiliation_strings":["Behavioral Signal Technologies, Institute of Informatics and Telecommunications, NCSR Demokritos,Athens,Greece"],"affiliations":[{"raw_affiliation_string":"Behavioral Signal Technologies, Institute of Informatics and Telecommunications, NCSR Demokritos,Athens,Greece","institution_ids":["https://openalex.org/I203474044","https://openalex.org/I4387152169"]}]},{"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["Behavioral Signal Technologies, SAIL, University of Southern California,Los Angeles,USA"],"affiliations":[{"raw_affiliation_string":"Behavioral Signal Technologies, SAIL, University of Southern California,Los Angeles,USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5024447977"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3292,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61038686,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"219","last_page":"227"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.963699996471405,"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":0.963699996471405,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9581000208854675,"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":0.9336000084877014,"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/robustness","display_name":"Robustness (evolution)","score":0.8191249370574951},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7813993692398071},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7803890109062195},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5403109192848206},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5336305499076843},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43885141611099243},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3647576570510864}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8191249370574951},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7813993692398071},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7803890109062195},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5403109192848206},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5336305499076843},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43885141611099243},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3647576570510864},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/acii63134.2024.00030","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acii63134.2024.00030","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 12th International Conference on Affective Computing and Intelligent Interaction (ACII)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W1974387177","https://openalex.org/W2030739378","https://openalex.org/W2030931454","https://openalex.org/W2038484192","https://openalex.org/W2108598243","https://openalex.org/W2140828385","https://openalex.org/W2146334809","https://openalex.org/W2151484683","https://openalex.org/W2194775991","https://openalex.org/W2289394825","https://openalex.org/W2593116425","https://openalex.org/W2742542661","https://openalex.org/W2944612567","https://openalex.org/W2963914279","https://openalex.org/W2967767914","https://openalex.org/W2972852081","https://openalex.org/W3015249983","https://openalex.org/W3097341095","https://openalex.org/W3111613338","https://openalex.org/W3136524425","https://openalex.org/W3196749180","https://openalex.org/W3198528147","https://openalex.org/W4221009324","https://openalex.org/W4224933371","https://openalex.org/W4293846201","https://openalex.org/W4375868941","https://openalex.org/W4386076667","https://openalex.org/W4389459413","https://openalex.org/W6637162671","https://openalex.org/W6687566353","https://openalex.org/W6688816777","https://openalex.org/W6746278845","https://openalex.org/W6757555829","https://openalex.org/W6780218876","https://openalex.org/W6847363464","https://openalex.org/W6869415701"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"The":[0,153],"recent":[1],"surge":[2],"in":[3,31,106,119,165,171,184],"deep":[4],"learning":[5],"has":[6],"improved":[7],"Speech":[8],"Emotion":[9],"Recognition":[10],"(SER)":[11],"model":[12,39,132,155],"performance;":[13],"however,":[14],"ensuring":[15],"robustness":[16,81],"across":[17],"diverse":[18,103],"scenarios":[19],"beyond":[20],"the":[21,53,80,126,141,144,179,193],"training":[22],"dataset":[23],"remains":[24],"a":[25,73,89,129,157],"problem.":[26],"This":[27,65],"challenge":[28],"becomes":[29],"pronounced":[30],"real-world":[32],"situations":[33],"characterized":[34],"by":[35,70],"noisy":[36],"conditions,":[37],"where":[38],"adaptability":[40],"to":[41,49,97,163],"unclean":[42],"data":[43],"is":[44,88,189],"crucial.":[45],"Despite":[46],"ongoing":[47],"efforts":[48],"develop":[50],"noise-robust":[51],"models,":[52],"lack":[54],"of":[55,82,122,128,143,161],"standardized":[56],"evaluation":[57,127],"protocols":[58],"hampers":[59],"fair":[60],"comparisons":[61],"among":[62],"different":[63,145],"models.":[64],"paper":[66],"tackles":[67],"this":[68,134,185],"issue":[69],"introducing":[71],"Robuser,":[72],"benchmarking":[74],"procedure":[75],"designed":[76],"specifically":[77],"for":[78,182],"evaluating":[79],"SER":[83,131],"models":[84],"under":[85],"noise.":[86],"Robuser":[87],"comprehensive":[90],"open-source":[91],"benchmark":[92],"that":[93],"can":[94],"be":[95],"applied":[96],"any":[98],"speech":[99],"dataset,":[100],"focusing":[101],"on":[102,151,175],"corruption":[104,146],"types":[105,147],"two":[107],"pivotal":[108],"dimensions:":[109],"additive":[110],"background":[111],"noise":[112],"and":[113,148,169],"various":[114],"signal":[115],"distortion":[116],"corruptions,":[117],"each":[118],"varying":[120],"levels":[121,150],"severity.":[123],"Furthermore,":[124],"through":[125],"state-of-the-art":[130],"against":[133],"benchmark,":[135],"we":[136],"offer":[137],"quantitative":[138],"insights":[139],"into":[140],"impact":[142],"severity":[149],"performance.":[152],"baseline":[154],"reveals":[156],"notable":[158],"performance":[159],"degradation":[160],"up":[162],"22.77%":[164],"Unweighted":[166],"Accuracy":[167,173],"(UA)":[168],"20.32%":[170],"Weighted":[172],"(WA)":[174],"corrupted":[176],"IEMOCAP,":[177],"underscoring":[178],"substantial":[180],"room":[181],"improvement":[183],"domain.":[186],"Our":[187],"code":[188],"openly":[190],"available":[191],"at":[192],"following":[194],"URL:":[195],"https://github.com/BehavioralSignalTechnologies/ser_robustness.git":[196]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}