{"id":"https://openalex.org/W4285106979","doi":"https://doi.org/10.1109/taslp.2022.3171965","title":"ISNet: Individual Standardization Network for Speech Emotion Recognition","display_name":"ISNet: Individual Standardization Network for Speech Emotion Recognition","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4285106979","doi":"https://doi.org/10.1109/taslp.2022.3171965"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3171965","doi":"https://doi.org/10.1109/taslp.2022.3171965","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3171965","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-b","cwts-core","dongbi-a","norway-2","poland-140","russia-white-list-1"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"volume":null,"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/A5026460226","display_name":"Weiquan Fan","orcid":"https://orcid.org/0000-0002-8006-7947","observed_orcids":["https://orcid.org/0000-0002-8006-7947"]},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiquan Fan","raw_affiliation_strings":["School of Electronic and Information, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-8006-7947","affiliations":[{"raw_affiliation_string":"School of Electronic and Information, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007354180","display_name":"Xiangmin Xu","orcid":"https://orcid.org/0000-0003-4573-5820","observed_orcids":["https://orcid.org/0000-0003-4573-5820"]},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangmin Xu","raw_affiliation_strings":["School of Electronic and Information, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4573-5820","affiliations":[{"raw_affiliation_string":"School of Electronic and Information, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063210263","display_name":"Bolun Cai","orcid":"https://orcid.org/0000-0002-9394-7820","observed_orcids":["https://orcid.org/0000-0002-9394-7820"]},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bolun Cai","raw_affiliation_strings":["School of Electronic and Information, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036301580","display_name":"Xiaofen Xing","orcid":"https://orcid.org/0000-0002-0016-9055","observed_orcids":["https://orcid.org/0000-0002-0016-9055"]},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofen Xing","raw_affiliation_strings":["School of Electronic and Information, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0016-9055","affiliations":[{"raw_affiliation_string":"School of Electronic and Information, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":{"value":2195,"currency":"USD","value_usd":2195},"apc_paid":null,"fwci":11.4793,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.98965792,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":"30","issue":null,"first_page":"1803","last_page":"1814"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.00039999998989515007,"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/T10860","display_name":"Speech and Audio Processing","score":9.999999747378752e-05,"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/speech-emotion-recognition","display_name":"speech emotion recognition","score":1.0},{"id":"https://openalex.org/keywords/individual-differences","display_name":"individual differences","score":0.6769999861717224},{"id":"https://openalex.org/keywords/representation-learning","display_name":"representation learning","score":0.6100000143051147},{"id":"https://openalex.org/keywords/training-test-split","display_name":"training-test split","score":0.42500001192092896},{"id":"https://openalex.org/keywords/iemocap","display_name":"IEMOCAP","score":0.7689999938011169}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7468633651733398},{"id":"https://openalex.org/C188087704","wikidata":"https://www.wikidata.org/wiki/Q369577","display_name":"Standardization","level":2,"score":0.6824648380279541},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5683572888374329},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5002470016479492},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4867956340312958},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.45356249809265137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43130743503570557},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4261690676212311},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3913336992263794},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2022.3171965","doi":"https://doi.org/10.1109/taslp.2022.3171965","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3171965","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-b","cwts-core","dongbi-a","norway-2","poland-140","russia-white-list-1"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G420612141","display_name":null,"funder_award_id":"U1801262","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5451359984","display_name":null,"funder_award_id":"2022A1515011588","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W100428360","https://openalex.org/W175750906","https://openalex.org/W1141027450","https://openalex.org/W1542637018","https://openalex.org/W1981918162","https://openalex.org/W1987759408","https://openalex.org/W2096503735","https://openalex.org/W2104773730","https://openalex.org/W2111926505","https://openalex.org/W2131953535","https://openalex.org/W2146334809","https://openalex.org/W2152137767","https://openalex.org/W2168692779","https://openalex.org/W2181741066","https://openalex.org/W2574058222","https://openalex.org/W2625297138","https://openalex.org/W2747664154","https://openalex.org/W2761514455","https://openalex.org/W2766272105","https://openalex.org/W2798658180","https://openalex.org/W2806046733","https://openalex.org/W2888473984","https://openalex.org/W2889717020","https://openalex.org/W2894728917","https://openalex.org/W2895615590","https://openalex.org/W2936173226","https://openalex.org/W2963804252","https://openalex.org/W2972498864","https://openalex.org/W2972602947","https://openalex.org/W2972640480","https://openalex.org/W2989798836","https://openalex.org/W3009778738","https://openalex.org/W3015240477","https://openalex.org/W3015308237","https://openalex.org/W3015832261","https://openalex.org/W3038083940","https://openalex.org/W3093895424","https://openalex.org/W3096039514","https://openalex.org/W3096284638","https://openalex.org/W3096509145","https://openalex.org/W3096963953","https://openalex.org/W3120680448","https://openalex.org/W3141819983","https://openalex.org/W3160016036","https://openalex.org/W3161003523","https://openalex.org/W3161659450","https://openalex.org/W3162387328","https://openalex.org/W3162475537","https://openalex.org/W3162993161","https://openalex.org/W3198528147","https://openalex.org/W4390926572"],"related_works":["https://openalex.org/W4395046204","https://openalex.org/W4392908941","https://openalex.org/W4402112365","https://openalex.org/W4297841460","https://openalex.org/W4388110922","https://openalex.org/W4385807405","https://openalex.org/W4226419249","https://openalex.org/W2512449761","https://openalex.org/W4296068595","https://openalex.org/W4221162793"],"abstract_inverted_index":{"Speech":[0],"emotion":[1,81,89,122,152],"recognition":[2,39,82],"plays":[3],"an":[4,74],"essential":[5],"role":[6],"in":[7],"human-computer":[8],"interaction.":[9],"However,":[10],"cross-individual":[11],"representation":[12],"learning":[13],"and":[14,106,134,166,181,190,204],"individual-agnostic":[15,121],"systems":[16],"are":[17],"challenging":[18,149],"due":[19],"to":[20,40,56,83,126,146,169],"the":[21,34,85,112,118,163,186,191,198],"distribution":[22],"deviation":[23],"caused":[24,91],"by":[25,92],"individual":[26,42,63,75,93,98,109,127,171],"differences.":[27,43,94],"The":[28],"existing":[29],"related":[30],"approaches":[31],"mostly":[32],"use":[33],"auxiliary":[35],"task":[36],"of":[37,87,102,120,162,178,188],"speaker":[38],"eliminate":[41],"Unfortunately,":[44],"although":[45],"these":[46],"methods":[47],"can":[48],"reduce":[49],"interindividual":[50,58,88],"voiceprint":[51],"differences,":[52,128],"it":[53],"is":[54,195],"difficult":[55],"dissociate":[57],"expression":[59,67],"differences":[60],"since":[61],"each":[62],"has":[64],"its":[65],"unique":[66],"habits.":[68],"In":[69,124,139],"this":[70],"paper,":[71],"we":[72,96,129,141],"propose":[73,131,156],"standardization":[76,110],"network":[77],"(ISNet)":[78],"for":[79],"speech":[80,151],"alleviate":[84],"problem":[86],"confusion":[90],"Specifically,":[95],"model":[97],"benchmarks":[99],"as":[100],"representations":[101],"nonemotional":[103],"neutral":[104],"speech,":[105],"ISNet":[107],"realizes":[108],"using":[111],"automatically":[113],"generated":[114],"benchmark,":[115],"which":[116],"improves":[117],"robustness":[119],"representations.":[123],"response":[125],"also":[130],"more":[132,158],"comprehensive":[133],"meaningful":[135],"individual-level":[136],"evaluation":[137],"metrics.":[138],"addition,":[140],"continue":[142],"our":[143],"previous":[144],"work":[145],"construct":[147],"a":[148,157],"large-scale":[150],"dataset":[153],"(LSSED).":[154],"We":[155],"reasonable":[159],"division":[160],"method":[161],"training":[164],"set":[165,168],"testing":[167],"prevent":[170],"information":[172],"leakage.":[173],"Experimental":[174],"results":[175],"on":[176,202],"datasets":[177],"both":[179],"large":[180],"small":[182],"scales":[183],"have":[184],"proven":[185],"effectiveness":[187],"ISNet,":[189],"new":[192],"state-of-the-art":[193],"performance":[194],"achieved":[196],"under":[197],"same":[199],"experimental":[200],"conditions":[201],"IEMOCAP":[203],"LSSED.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":2}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2022-07-14T00:00:00"}