{"id":"https://openalex.org/W4392903039","doi":"https://doi.org/10.1109/icassp48485.2024.10446645","title":"Enhancing Two-Stage Finetuning for Speech Emotion Recognition Using Adapters","display_name":"Enhancing Two-Stage Finetuning for Speech Emotion Recognition Using Adapters","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903039","doi":"https://doi.org/10.1109/icassp48485.2024.10446645"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446645","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446645","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":"conference-paper","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/A5055954787","display_name":"Yuan Gao","orcid":"https://orcid.org/0000-0002-3526-5856"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuan Gao","raw_affiliation_strings":["Kyoto University,Graduate School of Informatics,Kyoto,Japan","Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University,Graduate School of Informatics,Kyoto,Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101860389","display_name":"Hao Shi","orcid":"https://orcid.org/0000-0001-5979-2119"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hao Shi","raw_affiliation_strings":["Kyoto University,Graduate School of Informatics,Kyoto,Japan","Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University,Graduate School of Informatics,Kyoto,Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102757632","display_name":"Chenhui Chu","orcid":"https://orcid.org/0000-0001-9848-6384"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chenhui Chu","raw_affiliation_strings":["Kyoto University,Graduate School of Informatics,Kyoto,Japan","Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University,Graduate School of Informatics,Kyoto,Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["Kyoto University,Graduate School of Informatics,Kyoto,Japan","Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University,Graduate School of Informatics,Kyoto,Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11316","last_page":"11320"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9986000061035156,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8127501010894775},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.645852267742157},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6373231410980225},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5821769833564758},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4995131492614746},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4941902458667755},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48739224672317505},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4753008782863617},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46672406792640686},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.4251854121685028},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06414452195167542}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8127501010894775},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.645852267742157},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6373231410980225},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5821769833564758},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4995131492614746},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4941902458667755},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48739224672317505},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4753008782863617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46672406792640686},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.4251854121685028},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06414452195167542},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446645","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446645","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":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320338247","display_name":"Moonshot Research and Development Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2146334809","https://openalex.org/W2747172199","https://openalex.org/W2747664154","https://openalex.org/W2959546144","https://openalex.org/W2979826702","https://openalex.org/W3035390927","https://openalex.org/W3036601975","https://openalex.org/W3038993799","https://openalex.org/W3106539628","https://openalex.org/W3197642003","https://openalex.org/W3198528147","https://openalex.org/W3206189675","https://openalex.org/W3208480086","https://openalex.org/W4214825215","https://openalex.org/W4221162872","https://openalex.org/W4225319211","https://openalex.org/W4297841712","https://openalex.org/W4372267368","https://openalex.org/W4375869379","https://openalex.org/W4385822715","https://openalex.org/W4385822991","https://openalex.org/W4385823265","https://openalex.org/W6771876938","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W4288365749","https://openalex.org/W2936497627","https://openalex.org/W3013624417","https://openalex.org/W4287826556","https://openalex.org/W3098382480","https://openalex.org/W4287598411","https://openalex.org/W3100913109","https://openalex.org/W3198458223","https://openalex.org/W3126642501","https://openalex.org/W2964413124"],"abstract_inverted_index":{"This":[0],"study":[1],"investigates":[2],"the":[3,51,85,94,102,110,118,131,134,150,155,163],"effective":[4,47],"finetuning":[5,80],"of":[6,38,54,101,133],"a":[7,36,159],"pretrained":[8,103],"model":[9,104,119,137],"using":[10,149],"adapters":[11,115],"for":[12,48,75,91,105,120,139],"speech":[13,56],"emotion":[14,18],"recognition":[15,57,62,124],"(SER).":[16],"Since":[17,82],"is":[19,84],"related":[20],"with":[21],"linguistic":[22],"and":[23,26,33,59,88,107,122],"prosodic":[24],"information":[25],"also":[27,89],"other":[28,60],"attributes":[29],"such":[30],"as":[31],"gender":[32,121],"speaking":[34],"style,":[35],"framework":[37],"multi-task":[39],"learning":[40,52],"(MTL)":[41],"has":[42],"been":[43],"shown":[44],"to":[45,70,116,127],"be":[46],"SER.":[49,108],"However,":[50],"targets":[53],"automatic":[55],"(ASR)":[58],"attribute":[61],"are":[63],"apparently":[64],"in":[65,78,93,125],"conflict.":[66],"Therefore,":[67],"we":[68,97,113],"propose":[69],"employ":[71],"different":[72,76,146],"adaptation":[73,147],"methods":[74,148],"tasks":[77],"multiple":[79],"stages.":[81],"ASR":[83,106],"most":[86],"challenging":[87],"influential":[90],"SER,":[92],"first":[95],"stage,":[96,112],"finetune":[98,117],"all":[99],"parameters":[100,132],"In":[109],"second":[111],"incorporate":[114],"style":[123],"addition":[126],"SER":[128],"by":[129],"freezing":[130],"main":[135],"Transformer":[136],"tuned":[138],"ASR.":[140],"Experimental":[141],"evaluations":[142],"which":[143],"extensively":[144],"compare":[145],"IEMOCAP":[151],"dataset":[152],"demonstrate":[153],"that":[154],"proposed":[156],"approach":[157],"achieves":[158],"significant":[160],"improvement":[161],"from":[162],"simple":[164],"MTL.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}