{"id":"https://openalex.org/W4411019804","doi":"https://doi.org/10.1109/taffc.2025.3574178","title":"A Knowledge Distillation-Based Approach to Speech Emotion Recognition","display_name":"A Knowledge Distillation-Based Approach to Speech Emotion Recognition","publication_year":2025,"publication_date":"2025-06-04","ids":{"openalex":"https://openalex.org/W4411019804","doi":"https://doi.org/10.1109/taffc.2025.3574178"},"language":"en","primary_location":{"id":"doi:10.1109/taffc.2025.3574178","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taffc.2025.3574178","pdf_url":null,"source":{"id":"https://openalex.org/S104780363","display_name":"IEEE Transactions on Affective Computing","issn_l":"1949-3045","issn":["1949-3045","2371-9850"],"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 Affective Computing","raw_type":"journal-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/A5052655362","display_name":"Ziping Zhao","orcid":"https://orcid.org/0000-0002-8719-6389"},"institutions":[{"id":"https://openalex.org/I15062923","display_name":"Tianjin Normal University","ror":"https://ror.org/05x2td559","country_code":"CN","type":"education","lineage":["https://openalex.org/I15062923"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziping Zhao","raw_affiliation_strings":["College of Computer and Information Engineering, Tianjin Normal University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-8719-6389","affiliations":[{"raw_affiliation_string":"College of Computer and Information Engineering, Tianjin Normal University, Tianjin, China","institution_ids":["https://openalex.org/I15062923"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006317399","display_name":"J. Liu","orcid":"https://orcid.org/0009-0006-9749-7480"},"institutions":[{"id":"https://openalex.org/I15062923","display_name":"Tianjin Normal University","ror":"https://ror.org/05x2td559","country_code":"CN","type":"education","lineage":["https://openalex.org/I15062923"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jixin Liu","raw_affiliation_strings":["College of Computer and Information Engineering, Tianjin Normal University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0006-9749-7480","affiliations":[{"raw_affiliation_string":"College of Computer and Information Engineering, Tianjin Normal University, Tianjin, China","institution_ids":["https://openalex.org/I15062923"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047118636","display_name":"Haishuai Wang","orcid":"https://orcid.org/0000-0003-1617-0920"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haishuai Wang","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, China","College of Computer Science, Zhejiang University, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0003-1617-0920","affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062905153","display_name":"Danushka Bandara","orcid":"https://orcid.org/0000-0002-8885-622X"},"institutions":[{"id":"https://openalex.org/I126350171","display_name":"Fairfield University","ror":"https://ror.org/04z49n283","country_code":"US","type":"education","lineage":["https://openalex.org/I126350171"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Danushka Bandara","raw_affiliation_strings":["Department of Computer Science and Engineering, Fairfield University, Fairfield, CT, USA","Fairfield University, Department of Computer Science and Engineering, Fairfield, CT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Fairfield University, Fairfield, CT, USA","institution_ids":["https://openalex.org/I126350171"]},{"raw_affiliation_string":"Fairfield University, Department of Computer Science and Engineering, Fairfield, CT, USA","institution_ids":["https://openalex.org/I126350171"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9344-6428","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.188,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.93776579,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"16","issue":"3","first_page":"1307","last_page":"1317"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7850000262260437,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7850000262260437,"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":0.7799000144004822,"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":0.7682999968528748,"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/emotion-recognition","display_name":"Emotion recognition","score":0.7238904237747192},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.6649024486541748},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5757238268852234},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5716164112091064},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4225332736968994},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3900437653064728},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.333188533782959},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.06117510795593262}],"concepts":[{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.7238904237747192},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6649024486541748},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5757238268852234},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5716164112091064},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4225332736968994},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3900437653064728},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.333188533782959},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.06117510795593262},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taffc.2025.3574178","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taffc.2025.3574178","pdf_url":null,"source":{"id":"https://openalex.org/S104780363","display_name":"IEEE Transactions on Affective Computing","issn_l":"1949-3045","issn":["1949-3045","2371-9850"],"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 Affective Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2586592513","display_name":"\u591a\u6e90\u4fe1\u53f7\u878d\u5408\u7684\u6291\u90c1\u7a0b\u5ea6\u5206\u6790\u4e0e\u8ddf\u8e2a\u7814\u7a76","funder_award_id":"62071330","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5381013183","display_name":null,"funder_award_id":"61831022","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7272630985","display_name":null,"funder_award_id":"U21B2020","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W2119717200","https://openalex.org/W2747664154","https://openalex.org/W2770845466","https://openalex.org/W2889717020","https://openalex.org/W2892009249","https://openalex.org/W2936774411","https://openalex.org/W2936864631","https://openalex.org/W2963140444","https://openalex.org/W2963542740","https://openalex.org/W2973049979","https://openalex.org/W2982242214","https://openalex.org/W2986015886","https://openalex.org/W3030901202","https://openalex.org/W3035524453","https://openalex.org/W3101767455","https://openalex.org/W3105966348","https://openalex.org/W3109689953","https://openalex.org/W3132302778","https://openalex.org/W3158779859","https://openalex.org/W3161659450","https://openalex.org/W3163652268","https://openalex.org/W3173256823","https://openalex.org/W3197642003","https://openalex.org/W3198061281","https://openalex.org/W3198528147","https://openalex.org/W3204087964","https://openalex.org/W3205502670","https://openalex.org/W3209059054","https://openalex.org/W4221154966","https://openalex.org/W4221162872","https://openalex.org/W4221162874","https://openalex.org/W4223499953","https://openalex.org/W4226153164","https://openalex.org/W4285202066","https://openalex.org/W4296069133","https://openalex.org/W4312783726","https://openalex.org/W4313887688","https://openalex.org/W4372266717","https://openalex.org/W4372269797","https://openalex.org/W4372341110","https://openalex.org/W4382458595","https://openalex.org/W4385245566","https://openalex.org/W4385822446","https://openalex.org/W4385823310","https://openalex.org/W4411046783"],"related_works":["https://openalex.org/W3026162553","https://openalex.org/W2344382886","https://openalex.org/W19111321","https://openalex.org/W2412887479","https://openalex.org/W32245304","https://openalex.org/W2953684491","https://openalex.org/W4285338581","https://openalex.org/W2768175398","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Due":[0],"to":[1,19,22,61,115,138,152],"rapid":[2],"advancements":[3],"in":[4,12,53,71,192],"deep":[5],"learning,":[6],"Transformer-based":[7],"architectures":[8],"have":[9],"proven":[10],"effective":[11],"speech":[13,142],"emotion":[14],"recognition":[15],"(SER),":[16],"largely":[17],"due":[18],"their":[20],"ability":[21],"model":[23,114,165],"long-term":[24],"dependencies":[25],"more":[26],"effectively":[27],"than":[28],"recurrent":[29],"networks.":[30],"The":[31],"current":[32],"Transformer":[33,85],"architecture":[34],"is":[35,63,90],"not":[36],"well-suited":[37],"for":[38,88,118],"SER":[39,62,89,120],"because":[40,65],"its":[41,59],"large":[42],"parameter":[43],"number":[44],"demands":[45],"significant":[46],"computational":[47],"resources,":[48],"making":[49],"it":[50,117],"less":[51],"feasible":[52],"environments":[54],"with":[55,189],"limited":[56,64],"resources.":[57],"Furthermore,":[58],"application":[60],"human":[66],"emotions,":[67],"which":[68,135],"are":[69,77,136],"expressed":[70],"long":[72],"segments":[73],"of":[74],"continuous":[75],"speech,":[76],"inherently":[78],"complex":[79],"and":[80,106,149,169,181],"ambiguous.":[81],"Therefore,":[82],"designing":[83],"specialized":[84],"models":[86],"tailored":[87],"essential.":[91],"To":[92],"address":[93],"these":[94],"challenges,":[95],"we":[96,110,126,145,161],"propose":[97],"a":[98],"novel":[99],"knowledge":[100],"distillation":[101,172],"framework":[102],"that":[103,184],"combines":[104],"meta-knowledge":[105,168],"curriculum-based":[107,171],"distillation.":[108],"Specifically,":[109],"fine-tune":[111],"the":[112,119,123,140,154,163,170],"teacher":[113],"optimize":[116,162],"task.":[121],"For":[122],"student":[124,164],"model,":[125],"embed":[127],"individual":[128],"sequence":[129],"time":[130],"points":[131],"into":[132],"variable":[133],"tokens,":[134],"used":[137],"aggregate":[139],"global":[141],"representation.":[143],"Additionally,":[144],"combine":[146],"supervised":[147],"contrastive":[148],"cross-entropy":[150],"loss":[151],"increase":[153],"inter-class":[155],"distance":[156],"between":[157],"learnable":[158],"features.":[159],"Finally,":[160],"using":[166],"both":[167],"framework.":[173],"Experimental":[174],"results":[175],"on":[176],"two":[177],"benchmark":[178],"datasets,":[179],"IEMOCAP":[180],"MELD,":[182],"demonstrate":[183],"our":[185],"method":[186],"performs":[187],"competitively":[188],"state-of-the-art":[190],"approaches":[191],"SER.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}