{"id":"https://openalex.org/W4392944059","doi":"https://doi.org/10.1109/iceic61013.2024.10457123","title":"SC-ERM: Speaker-Centric Learning for Speech Emotion Recognition","display_name":"SC-ERM: Speaker-Centric Learning for Speech Emotion Recognition","publication_year":2024,"publication_date":"2024-01-28","ids":{"openalex":"https://openalex.org/W4392944059","doi":"https://doi.org/10.1109/iceic61013.2024.10457123"},"language":"en","primary_location":{"id":"doi:10.1109/iceic61013.2024.10457123","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iceic61013.2024.10457123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Electronics, Information, and Communication (ICEIC)","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/A5102632168","display_name":"Juhwan Yoon","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Juhwan Yoon","raw_affiliation_strings":["Yonsei University,dept. of electrical and electronic engineering,Seoul,South Korea","dept. of electrical and electronic engineering, Yonsei University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Yonsei University,dept. of electrical and electronic engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I193775966"]},{"raw_affiliation_string":"dept. of electrical and electronic engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074612173","display_name":"Seyun Um","orcid":"https://orcid.org/0000-0002-2229-6741"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seyun Um","raw_affiliation_strings":["Yonsei University,dept. of electrical and electronic engineering,Seoul,South Korea","dept. of electrical and electronic engineering, Yonsei University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Yonsei University,dept. of electrical and electronic engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I193775966"]},{"raw_affiliation_string":"dept. of electrical and electronic engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017925728","display_name":"Woojin Chung","orcid":"https://orcid.org/0000-0003-2090-4851"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Woo-Jin Chung","raw_affiliation_strings":["Yonsei University,dept. of electrical and electronic engineering,Seoul,South Korea","dept. of electrical and electronic engineering, Yonsei University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Yonsei University,dept. of electrical and electronic engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I193775966"]},{"raw_affiliation_string":"dept. of electrical and electronic engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056128107","display_name":"Hong-Goo Kang","orcid":"https://orcid.org/0000-0002-6554-0783"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hong-Goo Kang","raw_affiliation_strings":["Yonsei University,dept. of electrical and electronic engineering,Seoul,South Korea","dept. of electrical and electronic engineering, Yonsei University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Yonsei University,dept. of electrical and electronic engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I193775966"]},{"raw_affiliation_string":"dept. of electrical and electronic engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102632168"],"corresponding_institution_ids":["https://openalex.org/I193775966"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.027079,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9664000272750854,"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":0.9664000272750854,"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":0.9569000005722046,"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":0.9399999976158142,"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/speech-recognition","display_name":"Speech recognition","score":0.7378488183021545},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7309580445289612},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7221421599388123},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6330961585044861},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4473775327205658}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7378488183021545},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7309580445289612},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7221421599388123},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6330961585044861},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4473775327205658}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iceic61013.2024.10457123","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iceic61013.2024.10457123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Electronics, Information, and Communication (ICEIC)","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":12,"referenced_works":["https://openalex.org/W2146334809","https://openalex.org/W2187089797","https://openalex.org/W2726515241","https://openalex.org/W2794506738","https://openalex.org/W2803193013","https://openalex.org/W3024869864","https://openalex.org/W3036601975","https://openalex.org/W4225635674","https://openalex.org/W4324348061","https://openalex.org/W4375869379","https://openalex.org/W4385245566","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W2144208207","https://openalex.org/W1813780412","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W2160753975","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"We":[0,69],"propose":[1],"a":[2,62,65,92,122],"novel":[3],"deep":[4],"learning-based":[5],"model":[6,18,33,113],"for":[7,105],"speech":[8],"emotion":[9,36,44,48],"recognition,":[10],"SC-ERM,":[11],"which":[12],"focuses":[13],"on":[14],"speaker-centric":[15,54],"learning.":[16],"This":[17],"effectively":[19],"estimates":[20],"emotions":[21,104,120],"and":[22,50,78],"demonstrates":[23,82,114],"the":[24,100,129],"ability":[25],"to":[26,28,99],"generalize":[27],"unseen":[29],"speakers.":[30],"Our":[31],"proposed":[32],"utilizes":[34],"speaker-specific":[35],"characteristics":[37],"in":[38,85,96,117],"two":[39],"steps:":[40],"first,":[41],"it":[42,52,81,90],"extracts":[43],"representations":[45],"using":[46,74],"an":[47,75],"encoder,":[49],"second,":[51],"employs":[53],"learning":[55],"by":[56],"incorporating":[57],"speaker":[58,66],"style":[59],"embeddings":[60],"as":[61],"condition":[63],"through":[64],"mask":[67],"generator.":[68],"evaluate":[70],"our":[71,112],"model's":[72],"performance":[73,84,116],"emotional":[76,87,125],"dataset":[77],"find":[79],"that":[80],"out-standing":[83],"recognizing":[86],"states.":[88],"Notably,":[89],"achieves":[91],"9.2%":[93],"relative":[94],"improvement":[95],"accuracy":[97],"compared":[98],"baseline":[101],"when":[102],"classifying":[103],"speakers":[106,130],"not":[107],"seen":[108],"during":[109],"training.":[110],"Overall,":[111],"promising":[115],"accurately":[118],"identifying":[119],"across":[121],"range":[123],"of":[124,128],"expressions,":[126],"irrespective":[127],"involved.":[131]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}