{"id":"https://openalex.org/W2891597252","doi":"https://doi.org/10.1109/icassp.2018.8462011","title":"Human-Like Emotion Recognition: Multi-Label Learning from Noisy Labeled Audio-Visual Expressive Speech","display_name":"Human-Like Emotion Recognition: Multi-Label Learning from Noisy Labeled Audio-Visual Expressive Speech","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2891597252","doi":"https://doi.org/10.1109/icassp.2018.8462011","mag":"2891597252"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5070976231","display_name":"Yelin Kim","orcid":"https://orcid.org/0000-0002-6503-4637"},"institutions":[{"id":"https://openalex.org/I392282","display_name":"University at Albany, State University of New York","ror":"https://ror.org/012zs8222","country_code":"US","type":"education","lineage":["https://openalex.org/I392282"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yelin Kim","raw_affiliation_strings":["Electrical and Computer Engineering, University at Albany, USA"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, University at Albany, USA","institution_ids":["https://openalex.org/I392282"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055931401","display_name":"Jeesun Kim","orcid":"https://orcid.org/0000-0003-2651-1020"},"institutions":[{"id":"https://openalex.org/I63525965","display_name":"Western Sydney University","ror":"https://ror.org/03t52dk35","country_code":"AU","type":"education","lineage":["https://openalex.org/I63525965"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jeesun Kim","raw_affiliation_strings":["The MARCS Institute, Western Sydney University, Australia"],"affiliations":[{"raw_affiliation_string":"The MARCS Institute, Western Sydney University, Australia","institution_ids":["https://openalex.org/I63525965"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5070976231"],"corresponding_institution_ids":["https://openalex.org/I392282"],"apc_list":null,"apc_paid":null,"fwci":3.0729,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.91529313,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5104","last_page":"5108"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9937999844551086,"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/T11309","display_name":"Music and Audio Processing","score":0.9883000254631042,"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":0.6867538094520569},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6651894450187683},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5817013382911682},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.558078408241272},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5352044701576233},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.48000258207321167},{"id":"https://openalex.org/keywords/emotion-classification","display_name":"Emotion classification","score":0.45696821808815},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.44872090220451355},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3632270395755768},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35709208250045776},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.24881768226623535},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.18541410565376282}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6867538094520569},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6651894450187683},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5817013382911682},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.558078408241272},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5352044701576233},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.48000258207321167},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.45696821808815},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.44872090220451355},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3632270395755768},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35709208250045776},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24881768226623535},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.18541410565376282},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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":30,"referenced_works":["https://openalex.org/W1995794789","https://openalex.org/W2005418748","https://openalex.org/W2009059481","https://openalex.org/W2014399678","https://openalex.org/W2024221294","https://openalex.org/W2026131661","https://openalex.org/W2056403322","https://openalex.org/W2057563799","https://openalex.org/W2058787788","https://openalex.org/W2060470614","https://openalex.org/W2074788634","https://openalex.org/W2121971770","https://openalex.org/W2146334809","https://openalex.org/W2154024118","https://openalex.org/W2169166781","https://openalex.org/W2170876097","https://openalex.org/W2293946939","https://openalex.org/W2512795651","https://openalex.org/W2552810951","https://openalex.org/W2573267743","https://openalex.org/W2740109326","https://openalex.org/W2748702193","https://openalex.org/W2752818578","https://openalex.org/W2767087747","https://openalex.org/W6652578167","https://openalex.org/W6697009218","https://openalex.org/W6725674282","https://openalex.org/W6731942044","https://openalex.org/W6741652751","https://openalex.org/W6743825357"],"related_works":["https://openalex.org/W3126677997","https://openalex.org/W1610857240","https://openalex.org/W1550318927","https://openalex.org/W4305042383","https://openalex.org/W2546649374","https://openalex.org/W2773396412","https://openalex.org/W4380854332","https://openalex.org/W2184859701","https://openalex.org/W4386232293","https://openalex.org/W4380370144"],"abstract_inverted_index":{"To":[0],"capture":[1,105],"variation":[2],"in":[3,110,133],"categorical":[4,40],"emotion":[5,24,41,58,63,68,84,92,111,127,135],"recognition":[6,64,69,93,136],"by":[7,27],"human":[8,29,55,101],"perceivers,":[9],"we":[10],"propose":[11],"a":[12,74],"multi-label":[13,75],"learning":[14,45],"and":[15,46,56,82,113],"evaluation":[16],"method":[17],"that":[18,67,77,90],"can":[19,70,95],"employ":[20],"the":[21,34,87,98,106],"distribution":[22,99],"of":[23,100],"labels":[25],"generated":[26],"every":[28],"annotator.":[30],"In":[31],"contrast":[32],"to":[33,52],"traditional":[35],"accuracy-based":[36],"performance":[37],"measure":[38],"for":[39],"labels,":[42],"our":[43],"proposed":[44],"inference":[47],"algorithms":[48],"use":[49],"cross":[50],"entropy":[51],"directly":[53],"compare":[54],"machine":[57],"label":[59,108],"distributions.":[60],"Our":[61],"audiovisual":[62],"experiments":[65],"demonstrate":[66,89],"benefit":[71],"from":[72,124],"using":[73],"representation":[76],"fully":[78],"uses":[79],"both":[80],"clear":[81],"ambiguous":[83],"data.":[85],"Further,":[86],"results":[88],"this":[91],"system":[94],"(i)":[96],"learn":[97],"annotators":[102],"directly;":[103],"(ii)":[104],"humanlike":[107],"noise":[109],"perception;":[112],"(iii)":[114],"identify":[115],"infrequent":[116],"or":[117],"uncommon":[118],"emotional":[119],"expression":[120],"(such":[121],"as":[122],"frustration)":[123],"inconsistently":[125],"labeled":[126],"data,":[128],"which":[129],"were":[130],"often":[131],"ignored":[132],"previous":[134],"systems.":[137]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}