{"id":"https://openalex.org/W4225635674","doi":"https://doi.org/10.1109/icassp43922.2022.9747870","title":"Speech Emotion Recognition Using Self-Supervised Features","display_name":"Speech Emotion Recognition Using Self-Supervised Features","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225635674","doi":"https://doi.org/10.1109/icassp43922.2022.9747870"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747870","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747870","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":"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/A5079262240","display_name":"Edmilson Morais","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Edmilson Morais","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053864983","display_name":"Ron Hoory","orcid":"https://orcid.org/0009-0006-1327-5160"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ron Hoory","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100308092","display_name":"Weizhong Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weizhong Zhu","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028984453","display_name":"Itai Gat","orcid":"https://orcid.org/0000-0002-3467-9061"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Itai Gat","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014713995","display_name":"Matheus Damasceno","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matheus Damasceno","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021900623","display_name":"Hagai Aronowitz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hagai Aronowitz","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5079262240"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.5254,"has_fulltext":false,"cited_by_count":121,"citation_normalized_percentile":{"value":0.99199661,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6922","last_page":"6926"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9994999766349792,"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":0.9991000294685364,"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":0.803978681564331},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6060668230056763},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5647919774055481},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5428545475006104},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5036637187004089},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.48645827174186707},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.4729233384132385},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.42760586738586426},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4105324149131775},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.392444372177124},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33182960748672485},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2725374102592468}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.803978681564331},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6060668230056763},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5647919774055481},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5428545475006104},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5036637187004089},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.48645827174186707},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.4729233384132385},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.42760586738586426},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4105324149131775},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.392444372177124},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33182960748672485},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2725374102592468},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747870","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747870","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2146334809","https://openalex.org/W2584561145","https://openalex.org/W2795986449","https://openalex.org/W2796108585","https://openalex.org/W2896457183","https://openalex.org/W2937584914","https://openalex.org/W2963104701","https://openalex.org/W2973181312","https://openalex.org/W2982223350","https://openalex.org/W2997258743","https://openalex.org/W3015267357","https://openalex.org/W3015489952","https://openalex.org/W3015884429","https://openalex.org/W3022013598","https://openalex.org/W3024869864","https://openalex.org/W3036601975","https://openalex.org/W3041561163","https://openalex.org/W3096690837","https://openalex.org/W3096723250","https://openalex.org/W3104636952","https://openalex.org/W3167533889","https://openalex.org/W3197156295","https://openalex.org/W3197580070","https://openalex.org/W3197642003","https://openalex.org/W3198528147","https://openalex.org/W3198771897","https://openalex.org/W3209059054","https://openalex.org/W6755207826","https://openalex.org/W6780218876","https://openalex.org/W6782134137"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2333799855","https://openalex.org/W2351687372","https://openalex.org/W2004087835","https://openalex.org/W2314871050"],"abstract_inverted_index":{"Self-supervised":[0],"pre-trained":[1],"features":[2,88,91,121],"have":[3],"consistently":[4],"delivered":[5],"state-of-art":[6],"results":[7,124,128],"in":[8,19],"the":[9,20,70,112,127],"field":[10,21],"of":[11,22,54,58,81,86,114],"natural":[12],"language":[13],"processing":[14],"(NLP);":[15],"however,":[16],"their":[17],"merits":[18],"speech":[23],"emotion":[24,67],"recognition":[25],"(SER)":[26],"still":[27],"need":[28],"further":[29],"investigation.":[30],"In":[31],"this":[32],"paper":[33],"we":[34],"introduce":[35],"a":[36,55],"modular":[37],"End-to-End":[38],"(E2E)":[39],"SER":[40,62],"system":[41,101],"based":[42,100],"on":[43],"an":[44],"Upstream":[45],"+":[46],"Downstream":[47],"architecture":[48],"paradigm,":[49],"which":[50],"allows":[51],"easy":[52],"use/integration":[53],"large":[56],"variety":[57],"self-supervised":[59,82,119],"features.":[60],"Several":[61],"experiments":[63,76],"for":[64],"predicting":[65],"categorical":[66],"classes":[68],"from":[69],"IEMOCAP":[71],"dataset":[72],"are":[73],"performed.":[74],"These":[75],"investigate":[77],"interactions":[78],"among":[79],"fine-tuning":[80],"feature":[83],"models,":[84],"aggregation":[85],"frame-level":[87],"into":[89],"utterance-level":[90],"and":[92,116,137],"back-end":[93],"classification":[94],"networks.":[95],"The":[96],"proposed":[97],"monomodal":[98],"speech-only":[99],"not":[102],"only":[103],"achieves":[104],"SOTA":[105,131],"results,":[106],"but":[107],"also":[108],"brings":[109],"light":[110],"to":[111,126],"possibility":[113],"powerful":[115],"well":[117],"fine-tuned":[118],"acoustic":[120],"that":[122],"reach":[123],"similar":[125],"achieved":[129],"by":[130],"multimodal":[132],"systems":[133],"using":[134],"both":[135],"Speech":[136],"Text":[138],"modalities.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":34},{"year":2024,"cited_by_count":42},{"year":2023,"cited_by_count":37},{"year":2022,"cited_by_count":7}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}