{"id":"https://openalex.org/W4225314403","doi":"https://doi.org/10.1109/icassp43922.2022.9746930","title":"Confidence Estimation for Speech Emotion Recognition Based on the Relationship Between Emotion Categories and Primitives","display_name":"Confidence Estimation for Speech Emotion Recognition Based on the Relationship Between Emotion Categories and Primitives","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225314403","doi":"https://doi.org/10.1109/icassp43922.2022.9746930"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746930","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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":"https://openalex.org/A5036554015","display_name":"Yang Li","orcid":"https://orcid.org/0000-0002-3912-5420"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Li","raw_affiliation_strings":["University of Rochester,Dept. of Electrical and Computer Engineering","Amazon Alexa","Dept. of Electrical and Computer Engineering, University of Rochester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester,Dept. of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I5388228"]},{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, University of Rochester","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076143510","display_name":"Constantinos Papayiannis","orcid":"https://orcid.org/0000-0001-6448-3767"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Constantinos Papayiannis","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091009689","display_name":"Viktor Rozgi\u0107","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Viktor Rozgic","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107174154","display_name":"Elizabeth Shriberg","orcid":"https://orcid.org/0009-0004-3779-4956"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elizabeth Shriberg","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100406950","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0002-1560-6182"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7383,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.67280979,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"7352","last_page":"7356"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7110772132873535},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.516604483127594},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5114749670028687},{"id":"https://openalex.org/keywords/centroid","display_name":"Centroid","score":0.4967556595802307},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4860828220844269},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.45073145627975464},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42150020599365234},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4165249764919281},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3230123519897461}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7110772132873535},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.516604483127594},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5114749670028687},{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.4967556595802307},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4860828220844269},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.45073145627975464},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42150020599365234},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4165249764919281},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3230123519897461},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations 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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746930","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W582134693","https://openalex.org/W1522301498","https://openalex.org/W1665214252","https://openalex.org/W2061068689","https://openalex.org/W2079359777","https://openalex.org/W2082927806","https://openalex.org/W2085662862","https://openalex.org/W2146334809","https://openalex.org/W2170876097","https://openalex.org/W2270192120","https://openalex.org/W2399125226","https://openalex.org/W2406566596","https://openalex.org/W2513507089","https://openalex.org/W2737498590","https://openalex.org/W2742542661","https://openalex.org/W2747172199","https://openalex.org/W2803098682","https://openalex.org/W2890076758","https://openalex.org/W2908048420","https://openalex.org/W2952307697","https://openalex.org/W2963873807","https://openalex.org/W2970565181","https://openalex.org/W2972711440","https://openalex.org/W2979585146","https://openalex.org/W3004449907","https://openalex.org/W3010072020","https://openalex.org/W3016039577","https://openalex.org/W3035059588","https://openalex.org/W3119221111","https://openalex.org/W3162811262","https://openalex.org/W6617145748","https://openalex.org/W6631190155","https://openalex.org/W6637242042","https://openalex.org/W6712977385","https://openalex.org/W6741590867","https://openalex.org/W6757818805","https://openalex.org/W6774612490","https://openalex.org/W6780663757"],"related_works":["https://openalex.org/W151193258","https://openalex.org/W1892467659","https://openalex.org/W2312116756","https://openalex.org/W4214733035","https://openalex.org/W3005023910","https://openalex.org/W2947809439","https://openalex.org/W4315700287","https://openalex.org/W2579805650","https://openalex.org/W2747298132","https://openalex.org/W4323520804"],"abstract_inverted_index":{"Confidence":[0],"estimation":[1,132],"for":[2,29],"Speech":[3],"Emotion":[4],"Recognition":[5],"(SER)":[6],"is":[7,112],"instrumental":[8],"in":[9,13,97],"improving":[10],"the":[11,14,33,54,59,72,77,98,108,118,125,135,148],"reliability":[12],"behavior":[15],"of":[16,74,94,107,151],"downstream":[17],"applications.":[18],"In":[19],"this":[20],"work":[21],"we":[22,84,146,157],"propose":[23],"(1)":[24],"a":[25,50,65,141,159],"novel":[26],"confidence":[27,61,116,131,153],"metric":[28],"SER":[30],"based":[31],"on":[32,134],"relationship":[34],"between":[35],"emotion":[36,44],"primitives:":[37],"arousal,":[38],"valence,":[39],"and":[40,43,63,76,101,137,162],"dominance":[41],"(AVD)":[42],"categories":[45],"(ECs),":[46],"(2)":[47],"EmoConfidNet":[48,75,111,128],"-":[49],"DNN":[51],"trained":[52,113],"alongside":[53],"EC":[55,78,96,103,126,143],"recognizer":[56],"to":[57,70,92,114,123],"predict":[58,115],"proposed":[60],"metric,":[62],"(3)":[64],"data":[66],"filtering":[67],"technique":[68],"used":[69,122],"enhance":[71],"training":[73,82],"recognizer.":[79,127],"For":[80,140],"each":[81,95],"sample,":[83],"calculate":[85],"distances":[86],"from":[87,117],"corresponding":[88],"AVD":[89,99],"annotation":[90],"vectors":[91],"centroids":[93],"space,":[100],"define":[102],"confidences":[104],"as":[105],"functions":[106],"evaluated":[109],"distances.":[110],"same":[119,149],"acoustic":[120],"representations":[121],"train":[124],"outperforms":[129],"state-of-the-art":[130],"methods":[133],"MSP-Podcast":[136],"IEMOCAP":[138],"datasets.":[139],"fixed":[142],"recognizer,":[144],"after":[145],"reject":[147],"number":[150],"low":[152],"predictions":[154],"using":[155,170],"EmoConfidNet,":[156],"achieve":[158],"higher":[160],"F1":[161],"unweighted":[163],"average":[164],"recall":[165],"(UAR)":[166],"than":[167],"when":[168],"rejecting":[169],"other":[171],"methods.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}