{"id":"https://openalex.org/W4403721999","doi":"https://doi.org/10.1109/taffc.2024.3486340","title":"An Efficient Bi-Modal Fusion Framework for Music Emotion Recognition","display_name":"An Efficient Bi-Modal Fusion Framework for Music Emotion Recognition","publication_year":2024,"publication_date":"2024-10-24","ids":{"openalex":"https://openalex.org/W4403721999","doi":"https://doi.org/10.1109/taffc.2024.3486340"},"language":"en","primary_location":{"id":"doi:10.1109/taffc.2024.3486340","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taffc.2024.3486340","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/A5030008357","display_name":"Yao Xiao","orcid":"https://orcid.org/0009-0000-8712-8071"},"institutions":[{"id":"https://openalex.org/I1297991670","display_name":"Southwest University of Science and Technology","ror":"https://ror.org/04d996474","country_code":"CN","type":"education","lineage":["https://openalex.org/I1297991670"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Xiao","raw_affiliation_strings":["School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, China","School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, Sichuan, China"],"raw_orcid":"https://orcid.org/0009-0000-8712-8071","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, China","institution_ids":["https://openalex.org/I1297991670"]},{"raw_affiliation_string":"School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, Sichuan, China","institution_ids":["https://openalex.org/I1297991670"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057903680","display_name":"Haoxin Ruan","orcid":"https://orcid.org/0000-0002-7093-4613"},"institutions":[{"id":"https://openalex.org/I1297991670","display_name":"Southwest University of Science and Technology","ror":"https://ror.org/04d996474","country_code":"CN","type":"education","lineage":["https://openalex.org/I1297991670"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoxin Ruan","raw_affiliation_strings":["School of Mathematics and Physics, Southwest University of Science and Technology, Mianyang, China","School of Mathematics and Physics, Southwest University of Science and Technology, Mianyang, Sichuan, China"],"raw_orcid":"https://orcid.org/0009-0005-7587-8306","affiliations":[{"raw_affiliation_string":"School of Mathematics and Physics, Southwest University of Science and Technology, Mianyang, China","institution_ids":["https://openalex.org/I1297991670"]},{"raw_affiliation_string":"School of Mathematics and Physics, Southwest University of Science and Technology, Mianyang, Sichuan, China","institution_ids":["https://openalex.org/I1297991670"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075393447","display_name":"Xujian Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I1297991670","display_name":"Southwest University of Science and Technology","ror":"https://ror.org/04d996474","country_code":"CN","type":"education","lineage":["https://openalex.org/I1297991670"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xujian Zhao","raw_affiliation_strings":["School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, China","School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, Sichuan, China"],"raw_orcid":"https://orcid.org/0000-0003-4717-9231","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, China","institution_ids":["https://openalex.org/I1297991670"]},{"raw_affiliation_string":"School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, Sichuan, China","institution_ids":["https://openalex.org/I1297991670"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087025546","display_name":"Peiquan Jin","orcid":"https://orcid.org/0000-0002-3871-0548"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peiquan Jin","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-3871-0548","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100739639","display_name":"Li Tian","orcid":"https://orcid.org/0000-0002-0873-4223"},"institutions":[{"id":"https://openalex.org/I1297991670","display_name":"Southwest University of Science and Technology","ror":"https://ror.org/04d996474","country_code":"CN","type":"education","lineage":["https://openalex.org/I1297991670"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Tian","raw_affiliation_strings":["School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, China","School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, Sichuan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, China","institution_ids":["https://openalex.org/I1297991670"]},{"raw_affiliation_string":"School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, Sichuan, China","institution_ids":["https://openalex.org/I1297991670"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024358983","display_name":"Zihan Wei","orcid":"https://orcid.org/0000-0002-4153-5314"},"institutions":[{"id":"https://openalex.org/I1297991670","display_name":"Southwest University of Science and Technology","ror":"https://ror.org/04d996474","country_code":"CN","type":"education","lineage":["https://openalex.org/I1297991670"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihan Wei","raw_affiliation_strings":["School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, China","School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, Sichuan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, China","institution_ids":["https://openalex.org/I1297991670"]},{"raw_affiliation_string":"School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, Sichuan, China","institution_ids":["https://openalex.org/I1297991670"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081022315","display_name":"Xuebo Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086059","display_name":"Sichuan University of Arts and Science","ror":"https://ror.org/00erq7915","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210086059"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuebo Cai","raw_affiliation_strings":["School of Music and Dance, Sichuan University of Culture and Arts, Mianyang, China","School of Music and Dance, Sichuan University of Culture and Arts, Mianyang, Sichuan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Music and Dance, Sichuan University of Culture and Arts, Mianyang, China","institution_ids":["https://openalex.org/I4210086059"]},{"raw_affiliation_string":"School of Music and Dance, Sichuan University of Culture and Arts, Mianyang, Sichuan, China","institution_ids":["https://openalex.org/I4210086059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083196327","display_name":"Yixin Wang","orcid":"https://orcid.org/0000-0002-3076-2140"},"institutions":[{"id":"https://openalex.org/I1297991670","display_name":"Southwest University of Science and Technology","ror":"https://ror.org/04d996474","country_code":"CN","type":"education","lineage":["https://openalex.org/I1297991670"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixin Wang","raw_affiliation_strings":["School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, China","School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, Sichuan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, China","institution_ids":["https://openalex.org/I1297991670"]},{"raw_affiliation_string":"School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, Sichuan, China","institution_ids":["https://openalex.org/I1297991670"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115594671","display_name":"Liang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I1297991670","display_name":"Southwest University of Science and Technology","ror":"https://ror.org/04d996474","country_code":"CN","type":"education","lineage":["https://openalex.org/I1297991670"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Liu","raw_affiliation_strings":["School of Economics and Management, Southwest University of Science and Technology, Mianyang, China","School of Economics and Management, Southwest University of Science and Technology, Mianyang, Sichuan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Economics and Management, Southwest University of Science and Technology, Mianyang, China","institution_ids":["https://openalex.org/I1297991670"]},{"raw_affiliation_string":"School of Economics and Management, Southwest University of Science and Technology, Mianyang, Sichuan, China","institution_ids":["https://openalex.org/I1297991670"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9172,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.74529652,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"16","issue":"2","first_page":"999","last_page":"1015"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9919999837875366,"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/T11309","display_name":"Music and Audio Processing","score":0.9919999837875366,"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/T10860","display_name":"Speech and Audio Processing","score":0.9581000208854675,"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":0.9495999813079834,"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/modal","display_name":"Modal","score":0.7412575483322144},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.7013733983039856},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.543808102607727},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5062779188156128},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4469435214996338},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36130642890930176},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3489748537540436},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15759769082069397},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.10282310843467712},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.09366592764854431}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7412575483322144},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.7013733983039856},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.543808102607727},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5062779188156128},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4469435214996338},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36130642890930176},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3489748537540436},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15759769082069397},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.10282310843467712},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.09366592764854431},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taffc.2024.3486340","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taffc.2024.3486340","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/G2045983733","display_name":null,"funder_award_id":"62072419","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":57,"referenced_works":["https://openalex.org/W1974758710","https://openalex.org/W2053101950","https://openalex.org/W2083488428","https://openalex.org/W2149628368","https://openalex.org/W2152491694","https://openalex.org/W2197620369","https://openalex.org/W2402288201","https://openalex.org/W2410860376","https://openalex.org/W2509286793","https://openalex.org/W2546875627","https://openalex.org/W2584561145","https://openalex.org/W2585432886","https://openalex.org/W2765291577","https://openalex.org/W2795014578","https://openalex.org/W2896249196","https://openalex.org/W2945956523","https://openalex.org/W2954802914","https://openalex.org/W2962960500","https://openalex.org/W2963408210","https://openalex.org/W2981851635","https://openalex.org/W3017343282","https://openalex.org/W3035493214","https://openalex.org/W3041508568","https://openalex.org/W3046491228","https://openalex.org/W3092879656","https://openalex.org/W3094138986","https://openalex.org/W3094144570","https://openalex.org/W3137028092","https://openalex.org/W3204266507","https://openalex.org/W3208743843","https://openalex.org/W3209211564","https://openalex.org/W3209419355","https://openalex.org/W4206908116","https://openalex.org/W4220829848","https://openalex.org/W4223606270","https://openalex.org/W4293518855","https://openalex.org/W4293817297","https://openalex.org/W4308478537","https://openalex.org/W4316664328","https://openalex.org/W4327852215","https://openalex.org/W4385245566","https://openalex.org/W4385392784","https://openalex.org/W6712564709","https://openalex.org/W6732221513","https://openalex.org/W6754646542","https://openalex.org/W6755182157","https://openalex.org/W6764408361","https://openalex.org/W6769955919","https://openalex.org/W6770160433","https://openalex.org/W6778572914","https://openalex.org/W6779779136","https://openalex.org/W6795512330","https://openalex.org/W6798288246","https://openalex.org/W6799448330","https://openalex.org/W6803752119","https://openalex.org/W6810054084","https://openalex.org/W6810443764"],"related_works":["https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W613940353","https://openalex.org/W2320915480","https://openalex.org/W2099421762","https://openalex.org/W2362990116","https://openalex.org/W3105646692","https://openalex.org/W4387914125","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Current":[0],"methods":[1],"for":[2,57,152,179],"Music":[3],"Emotion":[4],"Recognition":[5],"(MER)":[6],"face":[7],"challenges":[8],"in":[9,19,75,168],"effectively":[10],"extracting":[11],"features":[12,66,118],"sensitive":[13,70],"to":[14,41,71,99,121],"emotions,":[15],"especially":[16],"those":[17],"rich":[18,74],"temporal":[20,76],"detail.":[21],"Moreover,":[22],"the":[23,63,131,157,171],"narrow":[24],"scope":[25],"of":[26,65],"music-related":[27],"modalities":[28,38,87],"impedes":[29],"data":[30,81],"integration":[31],"from":[32,82,102,119],"multiple":[33,37],"sources,":[34],"while":[35,88],"including":[36],"often":[39],"leads":[40],"redundant":[42],"information,":[43],"which":[44,175],"can":[45],"degrade":[46],"performance.":[47],"To":[48],"address":[49],"these":[50],"issues,":[51],"we":[52,108],"propose":[53],"a":[54,110,165],"lightweight":[55],"framework":[56],"music":[58],"emotion":[59],"recognition":[60],"that":[61,67,79,116,137,143],"improves":[62],"extraction":[64],"are":[68,144],"both":[69,83],"emotions":[72],"and":[73,78,85,104,133,146,154],"information":[77,124],"integrates":[80,117],"audio":[84,103,155],"MIDI":[86,153],"minimizing":[89],"redundancy.":[90],"Our":[91],"approach":[92],"involves":[93],"developing":[94],"two":[95],"innovative":[96],"unimodal":[97,139],"encoders":[98],"learn":[100],"embeddings":[101],"MIDI-like":[105],"features.":[106],"Additionally,":[107],"introduce":[109],"Bi-modal":[111],"Fusion":[112],"Attention":[113],"Model":[114],"(BFAM)":[115],"low-level":[120],"high-level":[122],"semantic":[123],"across":[125],"different":[126],"modalities.":[127],"Experimental":[128],"evaluations":[129],"on":[130,156],"EMOPIA":[132,158],"VGMIDI":[134],"datasets":[135],"show":[136],"our":[138,162],"networks":[140],"achieve":[141],"accuracies":[142],"6.1%":[145],"4.4%":[147],"higher":[148],"than":[149],"baseline":[150],"algorithms":[151],"dataset,":[159],"respectively.":[160],"Furthermore,":[161],"BFAM":[163],"achieves":[164],"15.2%":[166],"improvement":[167],"accuracy":[169],"over":[170],"baseline,":[172],"reaching":[173],"82.2%,":[174],"underscores":[176],"its":[177],"effectiveness":[178],"bi-modal":[180],"MER":[181],"applications.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
