{"id":"https://openalex.org/W3093895424","doi":"https://doi.org/10.1145/3382507.3418813","title":"Speaker-Invariant Adversarial Domain Adaptation for Emotion Recognition","display_name":"Speaker-Invariant Adversarial Domain Adaptation for Emotion Recognition","publication_year":2020,"publication_date":"2020-10-21","ids":{"openalex":"https://openalex.org/W3093895424","doi":"https://doi.org/10.1145/3382507.3418813","mag":"3093895424"},"language":"en","primary_location":{"id":"doi:10.1145/3382507.3418813","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3382507.3418813","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 International Conference on Multimodal Interaction","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/A5028562848","display_name":"Yufeng Yin","orcid":"https://orcid.org/0000-0001-5558-2421"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yufeng Yin","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012209503","display_name":"Baiyu Huang","orcid":"https://orcid.org/0009-0000-7224-1987"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Baiyu Huang","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022847076","display_name":"Yizhen Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yizhen Wu","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024169758","display_name":"Mohammad Soleymani","orcid":"https://orcid.org/0000-0002-5873-1434"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Soleymani","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":3.451,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.94528188,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"481","last_page":"490"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9997000098228455,"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":0.9993000030517578,"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/discriminator","display_name":"Discriminator","score":0.8072192668914795},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7462079524993896},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6590891480445862},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5697486400604248},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5294541716575623},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5002350807189941},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4733704924583435},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.47227558493614197},{"id":"https://openalex.org/keywords/valence","display_name":"Valence (chemistry)","score":0.4666559398174286},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42782527208328247},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3920994997024536},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.13323450088500977}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.8072192668914795},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7462079524993896},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6590891480445862},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5697486400604248},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5294541716575623},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5002350807189941},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4733704924583435},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.47227558493614197},{"id":"https://openalex.org/C168900304","wikidata":"https://www.wikidata.org/wiki/Q171407","display_name":"Valence (chemistry)","level":2,"score":0.4666559398174286},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42782527208328247},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3920994997024536},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.13323450088500977},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"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:10.1145/3382507.3418813","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3382507.3418813","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 International Conference on Multimodal Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G486694964","display_name":null,"funder_award_id":"W911NF\u201020\u20102\u20100053","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W22861983","https://openalex.org/W1565327149","https://openalex.org/W1583837637","https://openalex.org/W1976066595","https://openalex.org/W2025905516","https://openalex.org/W2056403322","https://openalex.org/W2092206588","https://openalex.org/W2108598243","https://openalex.org/W2159408788","https://openalex.org/W2164186291","https://openalex.org/W2194775991","https://openalex.org/W2312004824","https://openalex.org/W2339343773","https://openalex.org/W2342475039","https://openalex.org/W2346454595","https://openalex.org/W2399733683","https://openalex.org/W2526050071","https://openalex.org/W2584009249","https://openalex.org/W2593116425","https://openalex.org/W2593768305","https://openalex.org/W2610961739","https://openalex.org/W2703895418","https://openalex.org/W2751214333","https://openalex.org/W2781528640","https://openalex.org/W2786808285","https://openalex.org/W2896591327","https://openalex.org/W2897444637","https://openalex.org/W2915606245","https://openalex.org/W2951670162","https://openalex.org/W2962687275","https://openalex.org/W2963130397","https://openalex.org/W2963341956","https://openalex.org/W2963777311","https://openalex.org/W2963826681","https://openalex.org/W2964109570","https://openalex.org/W2969556441","https://openalex.org/W2980980704","https://openalex.org/W2981648259","https://openalex.org/W2981677410","https://openalex.org/W3007708573","https://openalex.org/W3015308237","https://openalex.org/W3100133290"],"related_works":["https://openalex.org/W4293202849","https://openalex.org/W1980965563","https://openalex.org/W1489300767","https://openalex.org/W4380714744","https://openalex.org/W2387995142","https://openalex.org/W4319453655","https://openalex.org/W2089959425","https://openalex.org/W2964074194","https://openalex.org/W2995777218","https://openalex.org/W2129455854"],"abstract_inverted_index":{"Automatic":[0],"emotion":[1],"recognition":[2],"methods":[3],"are":[4,155],"sensitive":[5],"to":[6,31,67,87],"the":[7,36,42,46,70,74,80,110,115,129,134,143,146,152,156,163,167],"variations":[8],"across":[9,18],"different":[10],"datasets":[11],"and":[12,40,73,107,109,120,127],"their":[13],"performance":[14],"drops":[15],"when":[16],"evaluated":[17],"corpora.":[19],"We":[20],"can":[21,38],"apply":[22],"domain":[23,71,139],"adaptation":[24,140],"techniques":[25],"e.g.,":[26],"Domain-Adversarial":[27,63],"Neural":[28,64],"Network":[29,65],"(DANN)":[30],"mitigate":[32],"this":[33,58],"problem.":[34],"Though":[35],"DANN":[37,130],"detect":[39],"remove":[41],"bias":[43,47,72],"between":[44,48],"corpora,":[45],"speakers":[49],"still":[50],"remains":[51],"which":[52],"results":[53],"in":[54],"reduced":[55],"performance.":[56],"In":[57],"paper,":[59],"we":[60,82],"propose":[61],"Speaker-Invariant":[62],"(SIDANN)":[66],"reduce":[68],"both":[69],"speaker":[75,85],"bias.":[76],"Specifically,":[77],"based":[78],"on":[79,122],"DANN,":[81],"add":[83],"a":[84,95,137],"discriminator":[86],"unlearn":[88],"information":[89],"representing":[90],"speakers'":[91],"individual":[92],"characteristics":[93],"with":[94,102],"gradient":[96],"reversal":[97],"layer":[98],"(GRL).":[99],"Our":[100],"experiments":[101],"multimodal":[103],"data":[104],"(speech,":[105],"vision,":[106],"text)":[108],"cross-domain":[111],"evaluation":[112],"indicate":[113],"that":[114,133,151],"proposed":[116],"SIDANN":[117,135],"outperforms":[118],"(+5.6%":[119],"+2.8%":[121],"average":[123],"for":[124,159,169],"detecting":[125],"arousal":[126,160],"valence)":[128],"model,":[131],"suggesting":[132],"has":[136],"better":[138],"ability":[141],"than":[142],"DANN.":[144],"Besides,":[145],"modality":[147],"contribution":[148],"analysis":[149],"shows":[150],"acoustic":[153],"features":[154,165],"most":[157],"informative":[158],"detection":[161],"while":[162],"lexical":[164],"perform":[166],"best":[168],"valence":[170],"detection.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":8}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}