{"id":"https://openalex.org/W3202667537","doi":"https://doi.org/10.1109/icassp43922.2022.9747348","title":"SERAB: A Multi-Lingual Benchmark for Speech Emotion Recognition","display_name":"SERAB: A Multi-Lingual Benchmark for Speech Emotion Recognition","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3202667537","doi":"https://doi.org/10.1109/icassp43922.2022.9747348","mag":"3202667537"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747348","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747348","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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://infoscience.epfl.ch/handle/20.500.14299/193824","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055084920","display_name":"Neil Scheidwasser","orcid":"https://orcid.org/0000-0001-9922-0289"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Neil Scheidwasser-Clow","raw_affiliation_strings":["École Polytechnique Fédérale de Lausanne (EPFL),Lausanne,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"École Polytechnique Fédérale de Lausanne (EPFL),Lausanne,Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029632932","display_name":"Mikolaj Kegler","orcid":"https://orcid.org/0000-0003-3408-2588"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mikolaj Kegler","raw_affiliation_strings":["Imperial College London,London,United Kingdom","Imperial College London, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,London,United Kingdom","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012253790","display_name":"Pierre Beckmann","orcid":"https://orcid.org/0000-0001-9247-4841"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Pierre Beckmann","raw_affiliation_strings":["École Polytechnique Fédérale de Lausanne (EPFL),Lausanne,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"École Polytechnique Fédérale de Lausanne (EPFL),Lausanne,Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003558571","display_name":"Milo\u0161 Cer\u0148ak","orcid":"https://orcid.org/0000-0002-5569-9491"},"institutions":[{"id":"https://openalex.org/I4210148785","display_name":"Logitech (Switzerland)","ror":"https://ror.org/05pkpss54","country_code":"CH","type":"company","lineage":["https://openalex.org/I4210148785"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Milos Cernak","raw_affiliation_strings":["Logitech Europe S.A,Lausanne,Switzerland","Logitech Europe S.A, Lausanne, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Logitech Europe S.A,Lausanne,Switzerland","institution_ids":["https://openalex.org/I4210148785"]},{"raw_affiliation_string":"Logitech Europe S.A, Lausanne, Switzerland","institution_ids":["https://openalex.org/I4210148785"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7697","last_page":"7701"},"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":0.9993000030517578,"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/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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/computer-science","display_name":"Computer science","score":0.7975040078163147},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7220503091812134},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7104572653770447},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7103493213653564},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5949355959892273},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5658369660377502},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5169129371643066},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48628246784210205},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47863855957984924},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4535828232765198},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4341081976890564},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4157876670360565},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4141896963119507},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3445373475551605}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7975040078163147},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7220503091812134},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7104572653770447},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7103493213653564},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5949355959892273},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5658369660377502},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5169129371643066},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48628246784210205},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47863855957984924},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4535828232765198},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4341081976890564},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4157876670360565},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4141896963119507},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3445373475551605},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"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/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"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":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747348","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747348","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.epfl.ch:299305","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/193824","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"WoS","raw_type":"conference proceedings"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:299305","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/193824","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"WoS","raw_type":"conference proceedings"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W589698015","https://openalex.org/W1493923506","https://openalex.org/W1686810756","https://openalex.org/W2030931454","https://openalex.org/W2085662862","https://openalex.org/W2101234009","https://openalex.org/W2108598243","https://openalex.org/W2146334809","https://openalex.org/W2146885281","https://openalex.org/W2343758848","https://openalex.org/W2396589722","https://openalex.org/W2524365899","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2612445135","https://openalex.org/W2803193013","https://openalex.org/W2808331624","https://openalex.org/W2810556878","https://openalex.org/W2893507900","https://openalex.org/W2896596895","https://openalex.org/W2923014074","https://openalex.org/W2962835968","https://openalex.org/W2963310665","https://openalex.org/W2963614358","https://openalex.org/W3006926732","https://openalex.org/W3008526508","https://openalex.org/W3035060554","https://openalex.org/W3094502228","https://openalex.org/W3119786062","https://openalex.org/W3134945014","https://openalex.org/W3139773203","https://openalex.org/W3161003523","https://openalex.org/W3168953763","https://openalex.org/W3196831814","https://openalex.org/W3201143670","https://openalex.org/W4214493665","https://openalex.org/W4254718357","https://openalex.org/W4293571337","https://openalex.org/W4297775537","https://openalex.org/W4299980321","https://openalex.org/W6617505242","https://openalex.org/W6637373629","https://openalex.org/W6675354045","https://openalex.org/W6676297131","https://openalex.org/W6712588427","https://openalex.org/W6713639923","https://openalex.org/W6734260513","https://openalex.org/W6737664043","https://openalex.org/W6774908330","https://openalex.org/W6779326418","https://openalex.org/W6784333009","https://openalex.org/W6796491170","https://openalex.org/W7073743773"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2011676020","https://openalex.org/W2329895846"],"abstract_inverted_index":{"Recent":[0],"developments":[1],"in":[2,71,131,135],"speech":[3],"emotion":[4],"recognition":[5],"(SER)":[6],"often":[7,20],"leverage":[8],"deep":[9],"neural":[10],"networks":[11],"(DNNs).":[12],"Comparing":[13],"and":[14,30,53,80,115],"benchmarking":[15],"different":[16,28,57,78],"DNN":[17,117],"models":[18],"can":[19,133,144],"be":[21],"tedious":[22],"due":[23],"to":[24,106],"the":[25,35,40,51,75,85,93,103,128,141],"use":[26],"of":[27,56,66,82,96,110,127],"datasets":[29,68,76],"evaluation":[31],"protocols.":[32],"To":[33],"facilitate":[34],"process,":[36],"here,":[37],"we":[38],"present":[39],"Speech":[41],"Emotion":[42],"Recognition":[43],"Adaptation":[44],"Benchmark":[45],"(SERAB),":[46],"a":[47,108,125],"framework":[48,105],"for":[49,59,69,91],"evaluating":[50],"performance":[52],"generalization":[54,94],"capacity":[55,95],"approaches":[58],"utterance-level":[60],"SER.":[61],"The":[62,119],"benchmark":[63],"is":[64,88],"composed":[65],"nine":[67],"SER":[70],"six":[72],"languages.":[73],"Since":[74],"have":[77],"sizes":[79],"numbers":[81],"emotional":[83],"classes,":[84],"proposed":[86,104,142],"setup":[87],"particularly":[89],"suitable":[90],"estimating":[92],"pre-trained":[97],"DNN-based":[98],"feature":[99,113],"extractors.":[100],"We":[101],"used":[102],"evaluate":[107],"selection":[109],"standard":[111],"hand-crafted":[112],"sets":[114],"state-of-the-art":[116],"representations.":[118],"results":[120],"highlight":[121],"that":[122],"using":[123],"only":[124],"subset":[126],"data":[129],"included":[130],"SERAB":[132],"result":[134],"biased":[136],"evaluation,":[137],"while":[138],"compliance":[139],"with":[140],"protocol":[143],"circumvent":[145],"this":[146],"issue.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}