{"id":"https://openalex.org/W4406461629","doi":"https://doi.org/10.1109/slt61566.2024.10832339","title":"GMP-TL: Gender-Augmented Multi-Scale Pseudo-Label Enhanced Transfer Learning For Speech Emotion Recognition","display_name":"GMP-TL: Gender-Augmented Multi-Scale Pseudo-Label Enhanced Transfer Learning For Speech Emotion Recognition","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461629","doi":"https://doi.org/10.1109/slt61566.2024.10832339"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5028107330","display_name":"Yu Pan","orcid":"https://orcid.org/0009-0000-4995-0689"},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yu Pan","raw_affiliation_strings":["Kyushu University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyushu University,Japan","institution_ids":["https://openalex.org/I135598925"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100402382","display_name":"Yuguang Yang","orcid":"https://orcid.org/0000-0003-1353-1815"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuguang Yang","raw_affiliation_strings":["Ximalaya Inc,ShangHai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ximalaya Inc,ShangHai,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101684274","display_name":"Yuheng Huang","orcid":"https://orcid.org/0000-0002-5358-4826"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuheng Huang","raw_affiliation_strings":["University of Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043098310","display_name":"Tiancheng Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tiancheng Jin","raw_affiliation_strings":["Kyushu University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyushu University,Japan","institution_ids":["https://openalex.org/I135598925"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004857861","display_name":"Jingjing Yin","orcid":"https://orcid.org/0000-0003-4843-613X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingjing Yin","raw_affiliation_strings":["Ximalaya Inc,ShangHai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ximalaya Inc,ShangHai,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101250603","display_name":"Yanni Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanni Hu","raw_affiliation_strings":["Ximalaya Inc,ShangHai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ximalaya Inc,ShangHai,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100618443","display_name":"Heng Lu","orcid":"https://orcid.org/0009-0009-9236-8825"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heng Lu","raw_affiliation_strings":["Ximalaya Inc,ShangHai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ximalaya Inc,ShangHai,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101468661","display_name":"Lei Ma","orcid":"https://orcid.org/0000-0002-8621-2420"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Lei Ma","raw_affiliation_strings":["University of Alberta,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta,Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065190767","display_name":"Jianjun Zhao","orcid":"https://orcid.org/0000-0001-8083-4352"},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jianjun Zhao","raw_affiliation_strings":["Kyushu University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyushu University,Japan","institution_ids":["https://openalex.org/I135598925"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4171,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.62420773,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"496","last_page":"501"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6696522235870361},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6565266847610474},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6503746509552002},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6417611837387085},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.569841206073761},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3900122344493866},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38886845111846924},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.053133219480514526}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6696522235870361},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6565266847610474},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6503746509552002},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6417611837387085},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.569841206073761},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3900122344493866},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38886845111846924},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.053133219480514526},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2140801466","https://openalex.org/W2146334809","https://openalex.org/W2168465881","https://openalex.org/W2602034649","https://openalex.org/W2766272105","https://openalex.org/W2784163702","https://openalex.org/W2964128364","https://openalex.org/W2972602947","https://openalex.org/W3015240477","https://openalex.org/W3036601975","https://openalex.org/W3103152812","https://openalex.org/W3197156295","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221161839","https://openalex.org/W4221161909","https://openalex.org/W4221162793","https://openalex.org/W4225319211","https://openalex.org/W4288391450","https://openalex.org/W4372260395","https://openalex.org/W4372269797","https://openalex.org/W4375869379","https://openalex.org/W4385714625","https://openalex.org/W4385822510","https://openalex.org/W4385822991","https://openalex.org/W4385823159","https://openalex.org/W4386158972","https://openalex.org/W4387814642","https://openalex.org/W4393216695","https://openalex.org/W4393969054","https://openalex.org/W6780218876","https://openalex.org/W6854730886","https://openalex.org/W6863379155"],"related_works":["https://openalex.org/W3201126466","https://openalex.org/W4282827391","https://openalex.org/W4405541655","https://openalex.org/W4386828785","https://openalex.org/W3165580226","https://openalex.org/W3135401135","https://openalex.org/W2886688859","https://openalex.org/W3133164560","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"The":[0],"continuous":[1],"evolution":[2],"of":[3,27,106,111],"pre-trained":[4,61],"speech":[5],"models":[6],"has":[7],"greatly":[8],"advanced":[9],"Speech":[10],"Emotion":[11],"Recognition":[12],"(SER).":[13],"However,":[14],"current":[15],"research":[16],"typically":[17],"relies":[18],"on":[19,97],"utterance-level":[20,82],"emotion":[21,83],"labels,":[22,84],"inadequately":[23],"capturing":[24],"the":[25,60],"complexity":[26],"emotions":[28],"within":[29],"a":[30,39,85,104],"single":[31],"utterance.":[32],"In":[33],"this":[34,54],"paper,":[35],"we":[36],"introduce":[37],"GMP-TL,":[38],"novel":[40],"SER":[41,120,129],"framework":[42],"that":[43,100],"employs":[44],"gender-augmented":[45],"multi-scale":[46,67],"pseudo-label":[47],"(GMP)":[48],"based":[49],"transfer":[50],"learning":[51,65],"to":[52,71,76,92,117,127],"mitigate":[53],"gap.":[55],"Specifically,":[56],"GMPTL":[57],"initially":[58],"uses":[59],"HuBERT,":[62],"implementing":[63],"multi-task":[64],"and":[66,81,108],"k":[68],"-means":[69],"clustering":[70],"acquire":[72],"frame-level":[73,79],"GMPs.":[74],"Subsequently,":[75],"fully":[77],"leverage":[78],"GMPs":[80],"two-stage":[86],"model":[87],"fine-tuning":[88],"approach":[89],"is":[90],"presented":[91],"further":[93],"optimize":[94],"GMP-TL.":[95],"Experiments":[96],"IEMOCAP":[98],"show":[99],"our":[101],"GMP-TL":[102],"attains":[103],"WAR":[105],"80.0%":[107],"an":[109],"UAR":[110],"82.0%,":[112],"achieving":[113],"superior":[114],"performance":[115],"compared":[116],"state-of-the-art":[118],"unimodal":[119],"methods":[121],"while":[122],"also":[123],"yielding":[124],"comparable":[125],"results":[126],"multimodal":[128],"approaches.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}