{"id":"https://openalex.org/W4205734456","doi":"https://doi.org/10.1109/tcss.2021.3130401","title":"Rethinking Auditory Affective Descriptors Through Zero-Shot Emotion Recognition in Speech","display_name":"Rethinking Auditory Affective Descriptors Through Zero-Shot Emotion Recognition in Speech","publication_year":2021,"publication_date":"2021-12-10","ids":{"openalex":"https://openalex.org/W4205734456","doi":"https://doi.org/10.1109/tcss.2021.3130401"},"language":"en","primary_location":{"id":"doi:10.1109/tcss.2021.3130401","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcss.2021.3130401","pdf_url":null,"source":{"id":"https://openalex.org/S2490693980","display_name":"IEEE Transactions on Computational Social Systems","issn_l":"2329-924X","issn":["2329-924X","2373-7476"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Computational Social Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/91478/91478.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049684805","display_name":"Xinzhou Xu","orcid":"https://orcid.org/0000-0002-4017-5919"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinzhou Xu","raw_affiliation_strings":["School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-4017-5919","affiliations":[{"raw_affiliation_string":"School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100759486","display_name":"Jun Deng","orcid":"https://orcid.org/0000-0003-3196-8690"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Deng","raw_affiliation_strings":["Agile Robots AG, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0003-3196-8690","affiliations":[{"raw_affiliation_string":"Agile Robots AG, Munich, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036056631","display_name":"Zixing Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Zixing Zhang","raw_affiliation_strings":["Group on Language, Audio, and Music (GLAM), Imperial College London, London, U.K","HNU - Hunan University [Changsha] (Lushan Road (S), Yuelu District, Changsha, Hunan Province 410082 - China)"],"raw_orcid":"https://orcid.org/0000-0001-8487-0561","affiliations":[{"raw_affiliation_string":"Group on Language, Audio, and Music (GLAM), Imperial College London, London, U.K","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"HNU - Hunan University [Changsha] (Lushan Road (S), Yuelu District, Changsha, Hunan Province 410082 - China)","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029844690","display_name":"Xijian Fan","orcid":"https://orcid.org/0000-0002-7017-7667"},"institutions":[{"id":"https://openalex.org/I167027274","display_name":"Nanjing Forestry University","ror":"https://ror.org/03m96p165","country_code":"CN","type":"education","lineage":["https://openalex.org/I167027274"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xijian Fan","raw_affiliation_strings":["College of Information Science and Technology, Nanjing Forestry University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-7017-7667","affiliations":[{"raw_affiliation_string":"College of Information Science and Technology, Nanjing Forestry University, Nanjing, China","institution_ids":["https://openalex.org/I167027274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101872701","display_name":"Li Zhao","orcid":"https://orcid.org/0000-0002-7145-4718"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhao","raw_affiliation_strings":["School of Information Science and Engineering, Southeast University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002036844","display_name":"Laurence Devillers","orcid":"https://orcid.org/0000-0001-9894-172X"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4387152856","display_name":"Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique","ror":"https://ror.org/00rd81916","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4387152856"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Laurence Devillers","raw_affiliation_strings":["CNRS-LISN, Sorbonne University, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CNRS-LISN, Sorbonne University, Paris, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4387152856"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"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"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["DE","GB"],"is_corresponding":false,"raw_author_name":"Bjorn W. Schuller","raw_affiliation_strings":["Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Augsburg, Germany","Imperial College London (South Kensington Campus, London SW7 2AZ - United Kingdom)"],"raw_orcid":"https://orcid.org/0000-0002-6478-8699","affiliations":[{"raw_affiliation_string":"Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]},{"raw_affiliation_string":"Imperial College London (South Kensington Campus, London SW7 2AZ - United Kingdom)","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.671,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.8442293,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"9","issue":"5","first_page":"1530","last_page":"1541"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9991000294685364,"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/zero","display_name":"Zero (linguistics)","score":0.6178351640701294},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6028125882148743},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5413205027580261},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.4482437074184418},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.38437220454216003},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.3263322412967682},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16730910539627075}],"concepts":[{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6178351640701294},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6028125882148743},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5413205027580261},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4482437074184418},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.38437220454216003},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3263322412967682},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16730910539627075},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tcss.2021.3130401","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcss.2021.3130401","pdf_url":null,"source":{"id":"https://openalex.org/S2490693980","display_name":"IEEE Transactions on Computational Social Systems","issn_l":"2329-924X","issn":["2329-924X","2373-7476"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Computational Social Systems","raw_type":"journal-article"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:91478","is_oa":true,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/91478","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/91478/91478.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":"article"},{"id":"pmh:oai:HAL:hal-04423593v1","is_oa":false,"landing_page_url":"https://hal.science/hal-04423593","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Computational Social Systems, 2022, 9 (5), pp.1530-1541. ⟨10.1109/TCSS.2021.3130401⟩","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:uni-augsburg.opus-bayern.de:91478","is_oa":true,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/91478","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/91478/91478.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":"article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2535026932","display_name":"\u8bed\u97f3\u7684\u56fe\u4fe1\u53f7\u5904\u7406\u7406\u8bba\u4e0e\u6280\u672f\u7814\u7a76","funder_award_id":"62071242","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4023624630","display_name":null,"funder_award_id":"BK20180746","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G5250479028","display_name":null,"funder_award_id":"61801241","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7189395530","display_name":"Agentenbasierte, Interaktive, Tiefe 0shotlearningNetzwerke zur Optimierung von Ontologischem Klangverst\u00e4ndnis in Maschinen","funder_award_id":"442218748","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G7594417966","display_name":null,"funder_award_id":"61802206","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8192786398","display_name":null,"funder_award_id":"61902187","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4205734456.pdf","grobid_xml":"https://content.openalex.org/works/W4205734456.grobid-xml"},"referenced_works_count":76,"referenced_works":["https://openalex.org/W652269744","https://openalex.org/W1479771596","https://openalex.org/W1614298861","https://openalex.org/W1960364170","https://openalex.org/W1994997260","https://openalex.org/W2000436309","https://openalex.org/W2035348005","https://openalex.org/W2058787788","https://openalex.org/W2082927806","https://openalex.org/W2128532956","https://openalex.org/W2129007850","https://openalex.org/W2151942619","https://openalex.org/W2153020780","https://openalex.org/W2239141610","https://openalex.org/W2250539671","https://openalex.org/W2289084343","https://openalex.org/W2414501075","https://openalex.org/W2493916176","https://openalex.org/W2589599921","https://openalex.org/W2604268783","https://openalex.org/W2606705624","https://openalex.org/W2614874155","https://openalex.org/W2735297260","https://openalex.org/W2746978487","https://openalex.org/W2748075849","https://openalex.org/W2761514455","https://openalex.org/W2774054212","https://openalex.org/W2788967885","https://openalex.org/W2792059711","https://openalex.org/W2795014578","https://openalex.org/W2798357113","https://openalex.org/W2803098682","https://openalex.org/W2807795836","https://openalex.org/W2883743124","https://openalex.org/W2885005742","https://openalex.org/W2886300652","https://openalex.org/W2888731576","https://openalex.org/W2888786729","https://openalex.org/W2900917617","https://openalex.org/W2905054565","https://openalex.org/W2905841571","https://openalex.org/W2955931541","https://openalex.org/W2962762077","https://openalex.org/W2963499153","https://openalex.org/W2964276171","https://openalex.org/W2967182021","https://openalex.org/W2972244714","https://openalex.org/W2972883999","https://openalex.org/W2973037561","https://openalex.org/W2981437154","https://openalex.org/W3005283300","https://openalex.org/W3014201970","https://openalex.org/W3083752628","https://openalex.org/W3094173182","https://openalex.org/W3095881291","https://openalex.org/W3096164988","https://openalex.org/W3102160429","https://openalex.org/W3116201721","https://openalex.org/W3131643166","https://openalex.org/W3134816589","https://openalex.org/W3135148659","https://openalex.org/W3138794164","https://openalex.org/W3169611941","https://openalex.org/W3196508562","https://openalex.org/W3196831814","https://openalex.org/W3197438177","https://openalex.org/W4233923317","https://openalex.org/W4256441345","https://openalex.org/W6603820874","https://openalex.org/W6604278364","https://openalex.org/W6607872213","https://openalex.org/W6636510571","https://openalex.org/W6682222085","https://openalex.org/W6682691769","https://openalex.org/W6684770997","https://openalex.org/W6747248625"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2931662336","https://openalex.org/W2077865380","https://openalex.org/W4401768695","https://openalex.org/W2765597752","https://openalex.org/W2134894512","https://openalex.org/W2083375246","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Zero-shot":[0],"speech":[1,60,131,177],"emotion":[2,89],"recognition":[3,90],"(SER)":[4],"endows":[5],"machines":[6,169],"with":[7,17,182],"the":[8,26,62,108,128,183],"ability":[9],"of":[10,52,74,185],"sensing":[11],"unseen-emotional":[12,44],"states":[13,58],"in":[14,59,91,157,176],"speech,":[15],"compared":[16],"conventional":[18],"SER":[19,28,104],"endeavors":[20],"on":[21,71,107,127],"supervised":[22],"cases.":[23],"On":[24],"addressing":[25],"zero-shot":[27,88,103,158],"task,":[29],"auditory":[30],"affective":[31,39,174],"descriptors":[32],"(AADs)":[33],"are":[34],"typically":[35],"employed":[36],"to":[37,43,95,170],"transfer":[38],"knowledge":[40],"from":[41,110,148],"seen-":[42],"states.":[45],"However,":[46],"it":[47,165],"remains":[48],"unknown":[49],"which":[50],"types":[51,73],"AADs":[53,126],"can":[54,151],"well":[55],"describe":[56,173],"emotional":[57,130,155],"during":[61],"transfer.":[63],"In":[64],"this":[65],"regard,":[66],"we":[67],"define":[68],"and":[69,82,101,112,124,137,172],"research":[70],"three":[72],"AADs,":[75,86,114],"namely,":[76],"per-emotion":[77,79,111],"semantic-embedding,":[78],"manually":[80,84,153],"annotated,":[81],"per-sample":[83,113],"annotated":[85,154],"through":[87],"speech.":[92],"This":[93],"leads":[94],"a":[96],"systematic":[97],"design":[98],"including":[99],"prototype-":[100],"annotation-based":[102],"modules,":[105],"relying":[106],"input":[109],"respectively.":[115],"We":[116],"then":[117],"perform":[118],"extensive":[119],"experimental":[120,142],"comparisons":[121],"between":[122],"human":[123,180],"machines\u2019":[125],"French":[129],"corpus":[132],"CINEMO":[133],"for":[134,168],"positive-negative":[135],"(PN)":[136],"within-negative":[138],"(WN)":[139],"tasks.":[140],"The":[141,160],"results":[143,161],"indicate":[144],"that":[145,164],"semantic-embedding":[146],"prototypes":[147],"pretrained":[149,187],"models":[150],"outperform":[152],"dimensions":[156],"SER.":[159],"further":[162],"demonstrate":[163],"is":[166],"possible":[167],"understand":[171],"information":[175],"better":[178],"than":[179],"beings,":[181],"help":[184],"sufficient":[186],"models.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}