{"id":"https://openalex.org/W4392903309","doi":"https://doi.org/10.1109/icassp48485.2024.10447678","title":"Generalization of Self-Supervised Learning-Based Representations for Cross-Domain Speech Emotion Recognition","display_name":"Generalization of Self-Supervised Learning-Based Representations for Cross-Domain Speech Emotion Recognition","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903309","doi":"https://doi.org/10.1109/icassp48485.2024.10447678"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447678","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447678","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5021565289","display_name":"Abinay Reddy Naini","orcid":null},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Abinay Reddy Naini","raw_affiliation_strings":["The University of Texas at Dallas,Department of Electrical and Computer Engineering","Department of Electrical and Computer Engineering, The University of Texas at Dallas"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, The University of Texas at Dallas","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076716803","display_name":"M.A. Kohler","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mary A. Kohler","raw_affiliation_strings":["North Carolina State University,Laboratory for Analytic Sciences","Laboratory for Analytic Sciences, North Carolina State University"],"affiliations":[{"raw_affiliation_string":"North Carolina State University,Laboratory for Analytic Sciences","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"Laboratory for Analytic Sciences, North Carolina State University","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079483985","display_name":"Elizabeth Richerson","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elizabeth Richerson","raw_affiliation_strings":["North Carolina State University,Laboratory for Analytic Sciences","Laboratory for Analytic Sciences, North Carolina State University"],"affiliations":[{"raw_affiliation_string":"North Carolina State University,Laboratory for Analytic Sciences","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"Laboratory for Analytic Sciences, North Carolina State University","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017291461","display_name":"Donita L. Robinson","orcid":"https://orcid.org/0000-0001-7540-3363"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Donita Robinson","raw_affiliation_strings":["North Carolina State University,Laboratory for Analytic Sciences","Laboratory for Analytic Sciences, North Carolina State University"],"affiliations":[{"raw_affiliation_string":"North Carolina State University,Laboratory for Analytic Sciences","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"Laboratory for Analytic Sciences, North Carolina State University","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040793194","display_name":"Carlos Busso","orcid":"https://orcid.org/0000-0002-4075-4072"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carlos Busso","raw_affiliation_strings":["The University of Texas at Dallas,Department of Electrical and Computer Engineering","Department of Electrical and Computer Engineering, The University of Texas at Dallas"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, The University of Texas at Dallas","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5021565289"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":3.3927,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.92910091,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"12031","last_page":"12035"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9987999796867371,"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/T10860","display_name":"Speech and Audio Processing","score":0.9970999956130981,"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/paralanguage","display_name":"Paralanguage","score":0.8402836918830872},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.750518798828125},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7083863615989685},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5724928975105286},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5470160841941833},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5384044647216797},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5126211047172546},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49075254797935486},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4836934208869934},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4624045491218567},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.44744378328323364},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10754421353340149},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.09365126490592957},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08252227306365967}],"concepts":[{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.8402836918830872},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.750518798828125},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7083863615989685},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5724928975105286},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5470160841941833},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5384044647216797},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5126211047172546},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49075254797935486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4836934208869934},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4624045491218567},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.44744378328323364},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10754421353340149},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.09365126490592957},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08252227306365967},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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},{"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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447678","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447678","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W830076066","https://openalex.org/W1731081199","https://openalex.org/W2032254851","https://openalex.org/W2158630797","https://openalex.org/W2342475039","https://openalex.org/W2595840341","https://openalex.org/W2742542661","https://openalex.org/W2963447013","https://openalex.org/W2979826702","https://openalex.org/W3036601975","https://openalex.org/W3041561163","https://openalex.org/W3086923691","https://openalex.org/W3162840325","https://openalex.org/W3196749180","https://openalex.org/W3198771897","https://openalex.org/W3205644108","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3211224152","https://openalex.org/W4226033575","https://openalex.org/W4230277160","https://openalex.org/W4293793697","https://openalex.org/W4361994820","https://openalex.org/W4372189490","https://openalex.org/W4372267458","https://openalex.org/W4385823042","https://openalex.org/W6631190155","https://openalex.org/W6637618735","https://openalex.org/W6755207826","https://openalex.org/W6780218876","https://openalex.org/W6803378298","https://openalex.org/W6810007534","https://openalex.org/W7027429494"],"related_works":["https://openalex.org/W2064370490","https://openalex.org/W3166813893","https://openalex.org/W2910013580","https://openalex.org/W2391900574","https://openalex.org/W3200958703","https://openalex.org/W1990078780","https://openalex.org/W3108667266","https://openalex.org/W2376619307","https://openalex.org/W3118437876","https://openalex.org/W1527444722"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1],"(SSL)":[2],"from":[3],"unlabelled":[4],"speech":[5,9,25,45,62,93],"data":[6],"has":[7],"revolutionized":[8],"representation":[10],"learning.":[11],"Among":[12],"them,":[13],"wavLM,":[14],"wav2vec2,":[15],"HuBERT,":[16],"and":[17,68,101,128],"Data2vec":[18],"have":[19,30],"produced":[20],"benchmark":[21],"performances":[22],"on":[23,41],"automatic":[24],"recognition.":[26,49],"However,":[27],"few":[28],"studies":[29],"explored":[31],"the":[32,53,112,116,119,123,126,135,153],"generalization":[33,54],"of":[34,55,155],"SSL-based":[35],"representations":[36,81,117,157],"to":[37,75,114,151],"different":[38,71,106,156],"tasks":[39],"based":[40],"paralinguistic":[42],"information":[43],"in":[44,70,97,145,161],"such":[46],"as":[47],"emotion":[48,63],"This":[50],"paper":[51],"explores":[52],"all":[56],"four":[57],"popular":[58],"SSL":[59,80],"models":[60],"for":[61,118,158],"recognition":[64],"(SER)":[65],"when":[66,83],"trained":[67],"tested":[69],"domains.":[72,108],"We":[73],"aim":[74],"understand":[76,152],"how":[77],"adaptable":[78],"these":[79],"are":[82,140],"using":[84],"simple":[85],"domain":[86,130,137,159],"adaptation":[87,138,160],"techniques.":[88],"The":[89,109,143],"evaluation":[90],"considers":[91],"emotional":[92,102],"databases":[94],"that":[95,134],"deviate":[96],"language,":[98],"recording":[99],"conditions,":[100],"distribution,":[103],"providing":[104],"very":[105],"target":[107,129],"results":[110],"reveal":[111],"necessity":[113],"fine-tune":[115],"SER":[120],"downstream.":[121],"As":[122],"differences":[124],"between":[125],"source":[127],"increase,":[131],"we":[132],"observe":[133],"unsupervised":[136],"techniques":[139],"more":[141],"effective.":[142],"analysis":[144],"this":[146],"study":[147],"provides":[148],"useful":[149],"insights":[150],"advantages":[154],"SER.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}