{"id":"https://openalex.org/W4221145199","doi":"https://doi.org/10.1109/tpami.2023.3263585","title":"Dawn of the Transformer Era in Speech Emotion Recognition: Closing the Valence Gap","display_name":"Dawn of the Transformer Era in Speech Emotion Recognition: Closing the Valence Gap","publication_year":2023,"publication_date":"2023-03-31","ids":{"openalex":"https://openalex.org/W4221145199","doi":"https://doi.org/10.1109/tpami.2023.3263585","pmid":"https://pubmed.ncbi.nlm.nih.gov/37015129"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2023.3263585","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3263585","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2203.07378","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060352345","display_name":"Johannes Wagner","orcid":"https://orcid.org/0000-0003-2389-410X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Johannes Wagner","raw_affiliation_strings":["audEERING GmbH, Gilching, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"audEERING GmbH, Gilching, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012240826","display_name":"Andreas Triantafyllopoulos","orcid":"https://orcid.org/0000-0001-8338-617X"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Triantafyllopoulos","raw_affiliation_strings":["Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Augsburg, Germany"],"raw_orcid":"https://orcid.org/0000-0001-8338-617X","affiliations":[{"raw_affiliation_string":"Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048480810","display_name":"Hagen Wierstorf","orcid":"https://orcid.org/0009-0009-2628-8261"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hagen Wierstorf","raw_affiliation_strings":["audEERING GmbH, Gilching, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"audEERING GmbH, Gilching, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019825395","display_name":"Maximilian Schmitt","orcid":"https://orcid.org/0000-0001-7453-5612"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maximilian Schmitt","raw_affiliation_strings":["audEERING GmbH, Gilching, Germany"],"raw_orcid":"https://orcid.org/0000-0001-7453-5612","affiliations":[{"raw_affiliation_string":"audEERING GmbH, Gilching, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019602951","display_name":"Felix Burkhardt","orcid":"https://orcid.org/0000-0002-2689-0545"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Felix Burkhardt","raw_affiliation_strings":["audEERING GmbH, Gilching, Germany"],"raw_orcid":"https://orcid.org/0000-0002-2689-0545","affiliations":[{"raw_affiliation_string":"audEERING GmbH, Gilching, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023264395","display_name":"Florian Eyben","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Florian Eyben","raw_affiliation_strings":["audEERING GmbH, Gilching, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"audEERING GmbH, Gilching, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn W. Schuller","raw_affiliation_strings":["audEERING GmbH, Gilching, Germany"],"raw_orcid":"https://orcid.org/0000-0002-6478-8699","affiliations":[{"raw_affiliation_string":"audEERING GmbH, Gilching, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1268,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.86497347,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"45","issue":"9","first_page":"10745","last_page":"10759"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9455000162124634,"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":0.9455000162124634,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.012900000438094139,"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/T11309","display_name":"Music and Audio Processing","score":0.010599999688565731,"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":0.6483219861984253},{"id":"https://openalex.org/keywords/valence","display_name":"Valence (chemistry)","score":0.6345716118812561},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5952818393707275},{"id":"https://openalex.org/keywords/concordance-correlation-coefficient","display_name":"Concordance correlation coefficient","score":0.5573077201843262},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.47143855690956116},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45131444931030273},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3896080255508423},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37231552600860596},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1460115611553192},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12406972050666809},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08193069696426392},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.08153939247131348}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6483219861984253},{"id":"https://openalex.org/C168900304","wikidata":"https://www.wikidata.org/wiki/Q171407","display_name":"Valence (chemistry)","level":2,"score":0.6345716118812561},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5952818393707275},{"id":"https://openalex.org/C2781059462","wikidata":"https://www.wikidata.org/wiki/Q5158906","display_name":"Concordance correlation coefficient","level":2,"score":0.5573077201843262},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.47143855690956116},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45131444931030273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3896080255508423},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37231552600860596},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1460115611553192},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12406972050666809},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08193069696426392},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08153939247131348},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004644","descriptor_name":"Emotions","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004644","descriptor_name":"Emotions","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004644","descriptor_name":"Emotions","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":6,"locations":[{"id":"doi:10.1109/tpami.2023.3263585","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3263585","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:37015129","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37015129","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:arXiv.org:2203.07378","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.07378","pdf_url":"https://arxiv.org/pdf/2203.07378","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:107403","is_oa":true,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-1074032","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/107403/107403.pdf","source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"doc-type:article"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1771671","is_oa":false,"landing_page_url":"https://mediatum.ub.tum.de/1771671","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.48550/arxiv.2203.07378","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2203.07378","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2203.07378","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.07378","pdf_url":"https://arxiv.org/pdf/2203.07378","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7189395530","display_name":null,"funder_award_id":"442218748","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1533303231","https://openalex.org/W1966797434","https://openalex.org/W2003653478","https://openalex.org/W2052666245","https://openalex.org/W2117645142","https://openalex.org/W2128837546","https://openalex.org/W2146334809","https://openalex.org/W2156503193","https://openalex.org/W2313339984","https://openalex.org/W2399733683","https://openalex.org/W2556418146","https://openalex.org/W2742542661","https://openalex.org/W2746763037","https://openalex.org/W2781692313","https://openalex.org/W2785722081","https://openalex.org/W2803098682","https://openalex.org/W2811466185","https://openalex.org/W2897444637","https://openalex.org/W2910165986","https://openalex.org/W2966384645","https://openalex.org/W2972372393","https://openalex.org/W2972852081","https://openalex.org/W2972935927","https://openalex.org/W2973034847","https://openalex.org/W2982223350","https://openalex.org/W3007157104","https://openalex.org/W3015988193","https://openalex.org/W3082167223","https://openalex.org/W3094550259","https://openalex.org/W3100511085","https://openalex.org/W3119308075","https://openalex.org/W3161663055","https://openalex.org/W3162811262","https://openalex.org/W3162890625","https://openalex.org/W3169022486","https://openalex.org/W3193714551","https://openalex.org/W3197580070","https://openalex.org/W3197642003","https://openalex.org/W3198771897","https://openalex.org/W3208152093","https://openalex.org/W3209059054","https://openalex.org/W3215440557","https://openalex.org/W4213019189","https://openalex.org/W4221089191","https://openalex.org/W4285111045","https://openalex.org/W4297841899","https://openalex.org/W4393695169","https://openalex.org/W6680300913","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6774314701","https://openalex.org/W6776129198","https://openalex.org/W6780218876","https://openalex.org/W6782436372","https://openalex.org/W6799856993","https://openalex.org/W6800751262","https://openalex.org/W6802103249","https://openalex.org/W6802301941","https://openalex.org/W6802546489","https://openalex.org/W6803378298","https://openalex.org/W6803979805","https://openalex.org/W6804030475","https://openalex.org/W6931421704"],"related_works":["https://openalex.org/W770098","https://openalex.org/W90294","https://openalex.org/W10658944","https://openalex.org/W2226195","https://openalex.org/W8895266","https://openalex.org/W2308727","https://openalex.org/W14656806","https://openalex.org/W676756","https://openalex.org/W153917","https://openalex.org/W16116878"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,8,23],"transformer-based":[3,134],"architectures":[4,18,135],"have":[5,19,34,49],"shown":[6,50],"promise":[7],"several":[9,70],"machine":[10],"learning":[11],"tasks.":[12],"In":[13],"the":[14,24,37,82,101,108,192,197],"audio":[15],"domain,":[16],"such":[17],"been":[20],"successfully":[21],"utilised":[22],"field":[25],"of":[26,39,66,73,88,103,116],"speech":[27],"emotion":[28],"recognition":[29],"(SER).":[30],"However,":[31],"existing":[32],"works":[33],"not":[35,152],"evaluated":[36],"influence":[38],"model":[40,195],"size":[41],"and":[42,48,57,76,86,94,144],"pre-training":[43],"data":[44],"on":[45,69,81,128,162,166],"downstream":[46],"performance,":[47],"limited":[51],"attention":[52],"to":[53,96,140,148,196],"generalisation,":[54],"robustness,":[55],"fairness,":[56],"efficiency.":[58],"The":[59],"present":[60],"contribution":[61],"conducts":[62],"a":[63,121,141],"thorough":[64],"analysis":[65],"these":[67],"aspects":[68],"pre-trained":[71],"variants":[72],"wav2vec":[74],"2.0":[75],"HuBERT":[77],"that":[78,133,159,180],"we":[79,106,157,190],"fine-tuned":[80],"dimensions":[83],"arousal,":[84],"dominance,":[85],"valence":[87,112,163],"MSP-Podcast,":[89],"while":[90],"additionally":[91],"using":[92],"IEMOCAP":[93],"MOSI":[95],"test":[97],"cross-corpus":[98],"generalisation.":[99],"To":[100,185],"best":[102,193],"our":[104,187],"knowledge,":[105],"obtain":[107],"top":[109],"performance":[110],"for":[111],"prediction":[113],"without":[114],"use":[115],"explicit":[117],"linguistic":[118,168],"information,":[119,169],"with":[120,146,176],"concordance":[122],"correlation":[123],"coefficient":[124],"(CCC)":[125],"of.":[126],"638":[127],"MSP-Podcast.":[129],"Our":[130],"investigations":[131],"reveal":[132],"are":[136],"more":[137],"robust":[138],"compared":[139],"CNN-based":[142],"baseline":[143],"fair":[145],"respect":[147],"gender":[149],"groups,":[150],"but":[151],"towards":[153],"individual":[154],"speakers.":[155],"Finally,":[156],"show":[158],"their":[160],"success":[161],"is":[164],"based":[165],"implicit":[167],"which":[170],"explains":[171],"why":[172],"they":[173],"perform":[174],"on-par":[175],"recent":[177],"multimodal":[178],"approaches":[179],"explicitly":[181],"utilise":[182],"textual":[183],"information.":[184],"make":[186],"findings":[188],"reproducible,":[189],"release":[191],"performing":[194],"community.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2022-04-03T00:00:00"}