{"id":"https://openalex.org/W3049723069","doi":"https://doi.org/10.21437/interspeech.2020-1212","title":"Jointly Fine-Tuning \u201cBERT-Like\u201d Self Supervised Models to Improve Multimodal Speech Emotion Recognition","display_name":"Jointly Fine-Tuning \u201cBERT-Like\u201d Self Supervised Models to Improve Multimodal Speech Emotion Recognition","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3049723069","doi":"https://doi.org/10.21437/interspeech.2020-1212","mag":"3049723069"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1212","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1212","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2008.06682","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072026088","display_name":"Shamane Siriwardhana","orcid":"https://orcid.org/0000-0003-0688-7901"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Shamane Siriwardhana","raw_affiliation_strings":["University of Auckland, Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Auckland, Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103934437","display_name":"Andrew Reis","orcid":null},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Andrew Reis","raw_affiliation_strings":["University of Auckland, Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Auckland, Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033966897","display_name":"Rivindu Weerasekera","orcid":"https://orcid.org/0000-0002-9630-2008"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rivindu Weerasekera","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5027647989","display_name":"Suranga Nanayakkara","orcid":"https://orcid.org/0000-0001-7441-5493"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Suranga Nanayakkara","raw_affiliation_strings":["University of Auckland, Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Auckland, Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3755","last_page":"3759"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994999766349792,"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/T12031","display_name":"Speech and dialogue systems","score":0.9980999827384949,"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":0.8268828392028809},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.807768702507019},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6802242398262024},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6255545020103455},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5424711108207703},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.532644510269165},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4797976315021515},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4311745762825012},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.42223963141441345}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8268828392028809},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.807768702507019},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6802242398262024},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6255545020103455},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5424711108207703},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.532644510269165},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4797976315021515},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4311745762825012},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.42223963141441345},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2020-1212","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1212","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2008.06682","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.06682","pdf_url":"https://arxiv.org/pdf/2008.06682","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":"mag:3049723069","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2008.06682","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2008.06682","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2008.06682","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2008.06682","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.06682","pdf_url":"https://arxiv.org/pdf/2008.06682","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":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3049723069.pdf"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2095176743","https://openalex.org/W2146334809","https://openalex.org/W2158419735","https://openalex.org/W2250539671","https://openalex.org/W2339343773","https://openalex.org/W2465534249","https://openalex.org/W2784665486","https://openalex.org/W2795642794","https://openalex.org/W2808359495","https://openalex.org/W2842511635","https://openalex.org/W2883409523","https://openalex.org/W2889325879","https://openalex.org/W2903538854","https://openalex.org/W2913939497","https://openalex.org/W2935542736","https://openalex.org/W2936173226","https://openalex.org/W2947476638","https://openalex.org/W2952509486","https://openalex.org/W2962686539","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963710346","https://openalex.org/W2963799213","https://openalex.org/W2965373594","https://openalex.org/W2970608575","https://openalex.org/W2971222961","https://openalex.org/W2971250720","https://openalex.org/W2972495317","https://openalex.org/W2973049979","https://openalex.org/W2980109192","https://openalex.org/W2985076077","https://openalex.org/W2985862548","https://openalex.org/W2988736778","https://openalex.org/W2996383576","https://openalex.org/W3007708573","https://openalex.org/W3015489952"],"related_works":["https://openalex.org/W3096690837","https://openalex.org/W2963341956","https://openalex.org/W3034266838","https://openalex.org/W2964051877","https://openalex.org/W3037572520","https://openalex.org/W2842511635","https://openalex.org/W2146334809","https://openalex.org/W2965373594","https://openalex.org/W2883409523","https://openalex.org/W2250539671","https://openalex.org/W1494198834","https://openalex.org/W3148757058","https://openalex.org/W3189296823","https://openalex.org/W3015988193","https://openalex.org/W3207222250","https://openalex.org/W2996383576","https://openalex.org/W2970608575","https://openalex.org/W2963403868","https://openalex.org/W2963288440","https://openalex.org/W2795497335"],"abstract_inverted_index":{"Multimodal":[0],"emotion":[1,58],"recognition":[2],"from":[3],"speech":[4,48,57,91],"is":[5,25],"an":[6],"important":[7],"area":[8],"in":[9],"affective":[10],"computing.":[11],"Fusing":[12],"multiple":[13],"data":[14,24],"modalities":[15,51,94],"and":[16,49,70,92,95],"learning":[17],"representations":[18],"with":[19],"limited":[20],"amounts":[21],"of":[22,36,55,89],"labeled":[23],"a":[26,98],"challenging":[27],"task.":[28],"In":[29],"this":[30],"paper,":[31],"we":[32,72],"explore":[33],"the":[34,53],"use":[35],"modality-specific":[37],"\"BERT-like\"":[38,77],"pretrained":[39],"Self":[40],"Supervised":[41],"Learning":[42],"(SSL)":[43],"architectures":[44,79],"to":[45,116],"represent":[46],"both":[47],"text":[50,93],"for":[52],"task":[54],"multimodal":[56],"recognition.":[59],"By":[60],"conducting":[61],"experiments":[62],"on":[63],"three":[64],"publicly":[65],"available":[66],"datasets":[67],"(IEMOCAP,":[68],"CMU-MOSEI,":[69],"CMU-MOSI),":[71],"show":[73,96],"that":[74,97,111],"jointly":[75],"fine-tuning":[76],"SSL":[78,109],"achieve":[80],"state-of-the-art":[81],"(SOTA)":[82],"results.":[83],"We":[84],"also":[85],"evaluate":[86],"two":[87],"methods":[88],"fusing":[90],"simple":[99],"fusion":[100],"mechanism":[101],"can":[102],"outperform":[103],"more":[104],"complex":[105],"ones":[106],"when":[107],"using":[108],"models":[110],"have":[112],"similar":[113],"architectural":[114],"properties":[115],"BERT.":[117]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}