{"id":"https://openalex.org/W4375868872","doi":"https://doi.org/10.1109/icassp49357.2023.10094888","title":"Zero-Shot Speech Emotion Recognition Using Generative Learning with Reconstructed Prototypes","display_name":"Zero-Shot Speech Emotion Recognition Using Generative Learning with Reconstructed Prototypes","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868872","doi":"https://doi.org/10.1109/icassp49357.2023.10094888"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094888","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094888","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5049684805","display_name":"Xinzhou Xu","orcid":"https://orcid.org/0000-0002-4017-5919"},"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/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","DE"],"is_corresponding":false,"raw_author_name":"Xinzhou Xu","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications,School of Internet of Things,P. R. China","Chair of Embedded Intelligence for Health Care & Wellbeing, University of Augsburg, Germany","School of Internet of Things, Nanjing University of Posts and Telecommunications, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications,School of Internet of Things,P. R. China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"Chair of Embedded Intelligence for Health Care & Wellbeing, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]},{"raw_affiliation_string":"School of Internet of Things, Nanjing University of Posts and Telecommunications, P. R. 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":[{"id":"https://openalex.org/I4210129668","display_name":"Agilent Technologies (Germany)","ror":"https://ror.org/0355p2e87","country_code":"DE","type":"company","lineage":["https://openalex.org/I138285227","https://openalex.org/I4210129668"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jun Deng","raw_affiliation_strings":["Agile Robots AG,Germany","Agile Robots AG, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Agile Robots AG,Germany","institution_ids":["https://openalex.org/I4210129668"]},{"raw_affiliation_string":"Agile Robots AG, Germany","institution_ids":["https://openalex.org/I4210129668"]}]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixing Zhang","raw_affiliation_strings":["Hunan University,College of Computer Science and Electronic Engineering,P. R. China","College of Computer Science and Electronic Engineering, Hunan University, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,College of Computer Science and Electronic Engineering,P. R. China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, P. R. China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047980942","display_name":"Zhen Yang","orcid":"https://orcid.org/0000-0002-4400-3823"},"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":"Zhen Yang","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications,School of Telecommunications and Information Engineering,P. R. China","School of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications,School of Telecommunications and Information Engineering,P. R. China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"School of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, P. R. China","institution_ids":["https://openalex.org/I41198531"]}]},{"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"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn W. Schuller","raw_affiliation_strings":["University of Augsburg,Chair of Embedded Intelligence for Health Care & Wellbeing,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Augsburg,Chair of Embedded Intelligence for Health Care & Wellbeing,Germany","institution_ids":["https://openalex.org/I179225836"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9333,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.88952671,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994000196456909,"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":0.9987000226974487,"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/paralanguage","display_name":"Paralanguage","score":0.860276997089386},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.700912356376648},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6618972420692444},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6083334684371948},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5336915254592896},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5160071849822998},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5098475813865662},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5040368437767029},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.44241416454315186},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33808717131614685},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.0780322253704071},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06475400924682617}],"concepts":[{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.860276997089386},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.700912356376648},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6618972420692444},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6083334684371948},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5336915254592896},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5160071849822998},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5098475813865662},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5040368437767029},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.44241416454315186},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33808717131614685},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0780322253704071},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06475400924682617},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094888","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094888","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6200000047683716}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320324852","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W652269744","https://openalex.org/W2177696193","https://openalex.org/W2239141610","https://openalex.org/W2289084343","https://openalex.org/W2334493732","https://openalex.org/W2493916176","https://openalex.org/W2589599921","https://openalex.org/W2598545578","https://openalex.org/W2761514455","https://openalex.org/W2788967885","https://openalex.org/W2792059711","https://openalex.org/W2886300652","https://openalex.org/W2888731576","https://openalex.org/W2910453440","https://openalex.org/W2915760784","https://openalex.org/W2937977583","https://openalex.org/W2962762077","https://openalex.org/W2963499153","https://openalex.org/W2963960318","https://openalex.org/W2964086552","https://openalex.org/W2964276171","https://openalex.org/W2972244714","https://openalex.org/W2972883999","https://openalex.org/W2979571231","https://openalex.org/W2980520956","https://openalex.org/W2981843773","https://openalex.org/W2982234480","https://openalex.org/W2989798836","https://openalex.org/W3089741414","https://openalex.org/W3094173182","https://openalex.org/W3099153556","https://openalex.org/W3102160429","https://openalex.org/W3129157062","https://openalex.org/W3158711590","https://openalex.org/W3164582967","https://openalex.org/W3169611941","https://openalex.org/W3196831814","https://openalex.org/W3212436340","https://openalex.org/W4205734456","https://openalex.org/W4294367149","https://openalex.org/W6621740533","https://openalex.org/W6747248625","https://openalex.org/W6759301235"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559","https://openalex.org/W4299831724"],"abstract_inverted_index":{"Zero-shot":[0],"Speech":[1],"Emotion":[2],"Recognition":[3],"(SER)":[4],"enables":[5],"machines":[6],"to":[7,79,87,95],"perceive":[8],"unseen-emotional":[9,45],"speech":[10],"without":[11],"knowing":[12],"any":[13],"samples":[14],"from":[15,76,91],"these":[16],"emotional":[17],"states,":[18],"which":[19],"is":[20,85],"helpful":[21],"in":[22,62],"audio-based":[23],"autonomous":[24],"affective":[25],"computing.":[26],"However,":[27],"existing":[28],"works":[29],"on":[30,101],"zero-shot":[31,53,99],"SER":[32,54],"directly":[33],"employ":[34],"original":[35],"prototypes":[36,61,72,94],"and":[37],"only":[38],"consider":[39],"inter-domain":[40],"knowledge":[41],"transfer":[42],"through":[43],"learning":[44,58,84],"classifiers.":[46],"In":[47],"this":[48,63],"regard,":[49],"we":[50,69],"propose":[51],"a":[52],"approach":[55,108],"using":[56,73],"generative":[57,83],"with":[59,113],"reconstructed":[60,93],"paper.":[64],"Within":[65],"the":[66,74,89,92,96,106,114],"proposed":[67,107],"approach,":[68],"first":[70],"reconstruct":[71],"alignment":[75],"paralinguistic":[77],"features":[78],"semantic":[80],"prototypes.":[81],"Then,":[82],"performed":[86],"build":[88],"connection":[90],"features.":[97],"Afterwards,":[98],"experiments":[100],"emotional-speech":[102],"data":[103],"demonstrate":[104],"that":[105],"achieves":[109],"better":[110],"performance":[111],"compared":[112],"state-of-the-art":[115],"approaches.":[116]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}