{"id":"https://openalex.org/W4286905321","doi":"https://doi.org/10.1109/icassp49357.2023.10095036","title":"Exploring Wav2vec 2.0 Fine Tuning for Improved Speech Emotion Recognition","display_name":"Exploring Wav2vec 2.0 Fine Tuning for Improved Speech Emotion Recognition","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4286905321","doi":"https://doi.org/10.1109/icassp49357.2023.10095036"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095036","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095036","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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":null,"display_name":"Li-Wei Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li-Wei Chen","raw_affiliation_strings":["Carnegie Mellon University,Language Technologies Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Language Technologies Institute","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040668817","display_name":"Alexander I. Rudnicky","orcid":"https://orcid.org/0000-0003-2044-8446"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Rudnicky","raw_affiliation_strings":["Carnegie Mellon University,Language Technologies Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Language Technologies Institute","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13497","display_name":"Hermeneutics and Narrative Identity","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/1211","display_name":"Philosophy"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13497","display_name":"Hermeneutics and Narrative Identity","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/1211","display_name":"Philosophy"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13695","display_name":"Aging, Elder Care, and Social Issues","score":0.9749000072479248,"subfield":{"id":"https://openalex.org/subfields/3600","display_name":"General Health Professions"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13099","display_name":"Health, Medicine and Society","score":0.95660001039505,"subfield":{"id":"https://openalex.org/subfields/3600","display_name":"General Health Professions"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7637569904327393},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6768560409545898},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"Fine-tuning","score":0.6266376972198486},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5718501806259155},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5714349746704102},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.48806893825531006},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4147166609764099},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40932294726371765},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3675362467765808},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07938766479492188},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07888820767402649}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7637569904327393},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6768560409545898},{"id":"https://openalex.org/C157524613","wikidata":"https://www.wikidata.org/wiki/Q2828883","display_name":"Fine-tuning","level":2,"score":0.6266376972198486},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5718501806259155},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5714349746704102},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.48806893825531006},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4147166609764099},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40932294726371765},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3675362467765808},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07938766479492188},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07888820767402649},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095036","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095036","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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":26,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2001540534","https://openalex.org/W2146334809","https://openalex.org/W2150593711","https://openalex.org/W2602034649","https://openalex.org/W2803193013","https://openalex.org/W2806051338","https://openalex.org/W3197156295","https://openalex.org/W3197642003","https://openalex.org/W3197947674","https://openalex.org/W3198275944","https://openalex.org/W3198712976","https://openalex.org/W3198771897","https://openalex.org/W3209059054","https://openalex.org/W6631190155","https://openalex.org/W6697498398","https://openalex.org/W6753000030","https://openalex.org/W6755207826","https://openalex.org/W6761176036","https://openalex.org/W6761305474","https://openalex.org/W6764265052","https://openalex.org/W6768021236","https://openalex.org/W6780218876","https://openalex.org/W6781920495","https://openalex.org/W6782524110","https://openalex.org/W6784497057"],"related_works":["https://openalex.org/W2899263","https://openalex.org/W1226999","https://openalex.org/W14230040","https://openalex.org/W11798771","https://openalex.org/W12768380","https://openalex.org/W13743179","https://openalex.org/W10910819","https://openalex.org/W12256131","https://openalex.org/W11209375","https://openalex.org/W4244564"],"abstract_inverted_index":{"While":[0],"Wav2Vec":[1],"2.0":[2],"has":[3],"been":[4],"proposed":[5],"for":[6,15],"speech":[7,16],"recognition":[8,18],"(ASR),":[9],"it":[10],"can":[11,22],"also":[12,71],"be":[13,23],"used":[14],"emotion":[17,87],"(SER);":[19],"its":[20],"performance":[21,67,123],"significantly":[24],"improved":[25],"using":[26],"different":[27],"fine-tuning":[28,34,62,75],"strategies.":[29],"Two":[30],"baseline":[31],"methods,":[32],"vanilla":[33],"(V-FT)":[35],"and":[36],"task":[37],"adaptive":[38],"pretraining":[39],"(TAPT)":[40],"are":[41],"first":[42],"presented.":[43],"We":[44,70],"show":[45,90],"that":[46,91],"V-FT":[47],"is":[48,128],"able":[49],"to":[50,84,102],"outperform":[51],"state-of-the-art":[52,122],"models":[53],"on":[54,68,124],"the":[55,66,81,121],"IEMOCAP":[56],"dataset.":[57],"TAPT,":[58,96],"an":[59],"existing":[60],"NLP":[61],"strategy,":[63],"further":[64],"improves":[65],"SER.":[69],"introduce":[72],"a":[73,112],"novel":[74],"method":[76],"termed":[77],"P-TAPT,":[78],"which":[79],"modifies":[80],"TAPT":[82],"objective":[83],"learn":[85],"contextualized":[86],"representations.":[88],"Experiments":[89],"P-TAPT":[92],"performs":[93],"better":[94],"than":[95],"especially":[97],"under":[98],"low-resource":[99],"settings.":[100],"Compared":[101],"prior":[103],"works":[104],"in":[105,116],"this":[106],"literature,":[107],"our":[108],"top-line":[109],"system":[110],"achieved":[111],"7.4%":[113],"absolute":[114],"improvement":[115],"unweighted":[117],"accuracy":[118],"(UA)":[119],"over":[120],"IEMOCAP.":[125],"Our":[126],"code":[127],"publicly":[129],"available.":[130],"<sup":[131],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[132],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[133]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2022-07-25T00:00:00"}