{"id":"https://openalex.org/W4406461937","doi":"https://doi.org/10.1109/slt61566.2024.10832334","title":"Enhancing Domain Generalization in Speech Emotion Recognition by Combining Domain-Variant Representations and Domain-Invariant Classifiers","display_name":"Enhancing Domain Generalization in Speech Emotion Recognition by Combining Domain-Variant Representations and Domain-Invariant Classifiers","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461937","doi":"https://doi.org/10.1109/slt61566.2024.10832334"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5071262282","display_name":"Shi-wook Lee","orcid":"https://orcid.org/0000-0002-2377-6376"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Shi-Wook Lee","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology,Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology,Japan","institution_ids":["https://openalex.org/I73613424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5071262282"],"corresponding_institution_ids":["https://openalex.org/I73613424"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31706587,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"533","last_page":"539"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9987999796867371,"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/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"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":0.6749802827835083},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6167514324188232},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5972720980644226},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5649178624153137},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.545834481716156},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5318496227264404},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5279185771942139},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42411521077156067},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.364726722240448},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19032984972000122}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6749802827835083},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6167514324188232},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5972720980644226},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5649178624153137},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.545834481716156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5318496227264404},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5279185771942139},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42411521077156067},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.364726722240448},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19032984972000122},{"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/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1836465849","https://openalex.org/W2146334809","https://openalex.org/W2239141610","https://openalex.org/W2342475039","https://openalex.org/W2611652970","https://openalex.org/W3092928935","https://openalex.org/W3197580070","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4230277160","https://openalex.org/W4281492411","https://openalex.org/W4281644515","https://openalex.org/W4288287305","https://openalex.org/W4361994820","https://openalex.org/W4372269797","https://openalex.org/W4391454536","https://openalex.org/W4392019934","https://openalex.org/W6765285020","https://openalex.org/W6771898459","https://openalex.org/W6780218876","https://openalex.org/W6784247468","https://openalex.org/W6790960999","https://openalex.org/W6804364296","https://openalex.org/W6811172144","https://openalex.org/W6838905592","https://openalex.org/W6853925136","https://openalex.org/W6857843283","https://openalex.org/W6861561259","https://openalex.org/W7073743773"],"related_works":["https://openalex.org/W3162204513","https://openalex.org/W2371138613","https://openalex.org/W2048963458","https://openalex.org/W43109613","https://openalex.org/W2359952343","https://openalex.org/W2239445980","https://openalex.org/W2080152487","https://openalex.org/W3083152911","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Speech":[0],"emotion":[1,96,125],"recognition":[2,97],"often":[3],"suffers":[4],"from":[5,33],"domain-specific":[6],"correlations":[7,32],"in":[8,119,123],"training":[9,35],"datasets,":[10,115],"which":[11],"leads":[12],"to":[13,23,72],"compromised":[14],"generalization.":[15,75],"For":[16],"robust":[17],"out-of-domain":[18,113],"generalization,":[19],"it":[20],"is":[21,91],"crucial":[22],"eliminate":[24],"spurious":[25,49],"correlations.":[26,50],"Typically,":[27],"feature":[28],"representations":[29,43,59,78],"capture":[30,79],"all":[31],"the":[34],"dataset,":[36],"but":[37],"classifiers":[38,84],"should":[39],"focus":[40,85],"on":[41,86,112],"domain-invariant":[42,61,83],"and":[44,60,69,101],"ignore":[45],"domain-variant":[46,58,77],"ones":[47],"containing":[48],"We":[51],"propose":[52],"a":[53],"novel":[54],"method":[55,65,108],"that":[56,106],"combines":[57],"classifiers.":[62],"The":[63],"proposed":[64],"uses":[66],"multitask":[67],"learning":[68],"unsupervised":[70],"clustering":[71],"enhance":[73],"domain":[74,121],"Specifically,":[76],"diverse":[80],"features,":[81],"while":[82],"emotion-relevant":[87],"features.":[88],"Our":[89],"approach":[90],"evaluated":[92],"through":[93],"cross-language":[94],"speech":[95,124],"tasks":[98],"between":[99],"English":[100],"Japanese.":[102],"Experimental":[103],"results":[104],"demonstrate":[105],"our":[107],"significantly":[109],"improves":[110],"accuracy":[111],"test":[114],"highlighting":[116],"its":[117],"effectiveness":[118],"enhancing":[120],"generalization":[122],"recognition.":[126]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}