{"id":"https://openalex.org/W7164584294","doi":"https://doi.org/10.1007/s11042-026-21719-3","title":"Music emotion recognition using tri-modal fusion of lyrics, vocals, and accompaniment with cross-attention","display_name":"Music emotion recognition using tri-modal fusion of lyrics, vocals, and accompaniment with cross-attention","publication_year":2026,"publication_date":"2026-06-12","ids":{"openalex":"https://openalex.org/W7164584294","doi":"https://doi.org/10.1007/s11042-026-21719-3"},"language":"en","primary_location":{"id":"doi:10.1007/s11042-026-21719-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11042-026-21719-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11042-026-21719-3.pdf","source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia Tools and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11042-026-21719-3.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100333961","display_name":"Wenfeng Li","orcid":"https://orcid.org/0000-0001-9491-6543"},"institutions":[{"id":"https://openalex.org/I4210166603","display_name":"Jinling Institute of Technology","ror":"https://ror.org/05em1gq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210166603"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenfeng Li","raw_affiliation_strings":["School of Software Engineering, Jinling Institute of Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Jinling Institute of Technology, Nanjing, China","institution_ids":["https://openalex.org/I4210166603"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138498943","display_name":"Yuehao Deng","orcid":"https://orcid.org/0009-0001-6023-7005"},"institutions":[{"id":"https://openalex.org/I4210166603","display_name":"Jinling Institute of Technology","ror":"https://ror.org/05em1gq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210166603"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuehao Deng","raw_affiliation_strings":["School of Software Engineering, Jinling Institute of Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0001-6023-7005","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Jinling Institute of Technology, Nanjing, China","institution_ids":["https://openalex.org/I4210166603"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138531019","display_name":"Shuli Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210166603","display_name":"Jinling Institute of Technology","ror":"https://ror.org/05em1gq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210166603"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuli Liao","raw_affiliation_strings":["School of Software Engineering, Jinling Institute of Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Jinling Institute of Technology, Nanjing, China","institution_ids":["https://openalex.org/I4210166603"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064478697","display_name":"C Li","orcid":"https://orcid.org/0009-0000-6857-1676"},"institutions":[{"id":"https://openalex.org/I4210166603","display_name":"Jinling Institute of Technology","ror":"https://ror.org/05em1gq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210166603"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunyang Li","raw_affiliation_strings":["School of Software Engineering, Jinling Institute of Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Jinling Institute of Technology, Nanjing, China","institution_ids":["https://openalex.org/I4210166603"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5138507377","display_name":"Qiqi Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210166603","display_name":"Jinling Institute of Technology","ror":"https://ror.org/05em1gq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210166603"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiqi Wang","raw_affiliation_strings":["School of Software Engineering, Jinling Institute of Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Jinling Institute of Technology, Nanjing, China","institution_ids":["https://openalex.org/I4210166603"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5138498943"],"corresponding_institution_ids":["https://openalex.org/I4210166603"],"apc_list":{"value":2890,"currency":"USD","value_usd":2890},"apc_paid":{"value":2890,"currency":"USD","value_usd":2890},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74563739,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"85","issue":"6","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.5206000208854675,"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":0.5206000208854675,"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/T11309","display_name":"Music and Audio Processing","score":0.2793999910354614,"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":0.014000000432133675,"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/emotion-recognition","display_name":"Emotion recognition","score":0.6862999796867371},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.45820000767707825},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.2639999985694885},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.24269999563694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8319000005722046},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6862999796867371},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6075000166893005},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.45820000767707825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3797000050544739},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26260000467300415},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25429999828338623},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2442999929189682},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.24269999563694}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11042-026-21719-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11042-026-21719-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11042-026-21719-3.pdf","source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia Tools and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11042-026-21719-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11042-026-21719-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11042-026-21719-3.pdf","source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia Tools and Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2860604785","display_name":null,"funder_award_id":"SJCX25_1300","funder_id":"https://openalex.org/F5515530138","funder_display_name":"High Level Innovation and Entrepreneurial Research Team Program in Jiangsu"},{"id":"https://openalex.org/G4684688371","display_name":null,"funder_award_id":"jit-b-2021-09","funder_id":"https://openalex.org/F4320327505","funder_display_name":"Jinling Institute of Technology"},{"id":"https://openalex.org/G4781053124","display_name":null,"funder_award_id":"BY2021086, BY20230682","funder_id":"https://openalex.org/F4320329853","funder_display_name":"International Science and Technology Cooperation Program of Jiangsu Province"}],"funders":[{"id":"https://openalex.org/F4320321605","display_name":"Government of Jiangsu Province","ror":"https://ror.org/004svx814"},{"id":"https://openalex.org/F4320327505","display_name":"Jinling Institute of Technology","ror":"https://ror.org/05em1gq62"},{"id":"https://openalex.org/F4320329853","display_name":"International Science and Technology Cooperation Program of Jiangsu Province","ror":null},{"id":"https://openalex.org/F5515530138","display_name":"High Level Innovation and Entrepreneurial Research Team Program in Jiangsu","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7164584294.pdf","grobid_xml":"https://content.openalex.org/works/W7164584294.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W200309034","https://openalex.org/W2016524684","https://openalex.org/W2144198023","https://openalex.org/W2171848217","https://openalex.org/W2923286899","https://openalex.org/W2951697207","https://openalex.org/W2970078867","https://openalex.org/W3015710625","https://openalex.org/W3037149862","https://openalex.org/W3157722160","https://openalex.org/W3203247751","https://openalex.org/W4221145109","https://openalex.org/W4224919533","https://openalex.org/W4312797616","https://openalex.org/W4379251869","https://openalex.org/W4400141361","https://openalex.org/W4400770765","https://openalex.org/W4403635995","https://openalex.org/W4414458967"],"related_works":[],"abstract_inverted_index":{"Music":[0],"emotion":[1,141],"recognition":[2],"(MER)":[3],"remains":[4],"challenging":[5],"due":[6],"to":[7],"the":[8,35,56,81,90,125,161,180,186],"complex":[9],"and":[10,28,41,61,63,97,129,166,185,194],"heterogeneous":[11],"nature":[12],"of":[13,39,182],"emotional":[14,37,204],"expression":[15],"in":[16,138,160,172,206],"music.":[17,207],"Existing":[18],"multimodal":[19],"approaches":[20],"typically":[21],"treat":[22],"audio":[23,57,183],"as":[24,196],"a":[25,49,71,104,115,167],"monolithic":[26],"modality":[27],"fuse":[29],"it":[30],"naively":[31],"with":[32,68],"lyrics,":[33],"neglecting":[34],"distinct":[36],"contributions":[38],"vocals":[40,60,193],"accompaniment.":[42],"To":[43],"address":[44],"this":[45],"limitation,":[46],"we":[47],"propose":[48],"tri-modal":[50],"MER":[51],"framework":[52],"that":[53,108,146,191],"explicitly":[54],"decouples":[55],"signal":[58],"into":[59],"accompaniment":[62,195],"jointly":[64],"models":[65],"their":[66],"interactions":[67],"lyrics":[69],"through":[70],"cross-attention":[72],"fusion":[73,106,188],"mechanism":[74],"termed":[75],"Tri-Modal":[76],"Cross-Attention":[77],"Fusion":[78],"(TCAF).":[79],"Specifically,":[80],"TCAF":[82],"module":[83],"establishes":[84],"six":[85],"bidirectional":[86],"attention":[87],"pathways":[88],"among":[89],"three":[91],"modalities,":[92],"enabling":[93],"fine-grained":[94],"cross-modal":[95],"alignment":[96],"context-aware":[98],"feature":[99],"enhancement.":[100],"We":[101,118],"further":[102],"introduce":[103],"gated":[105],"unit":[107],"dynamically":[109],"weights":[110],"each":[111],"modality\u2019s":[112],"contribution":[113],"on":[114,122,164,175],"per-sample":[116],"basis.":[117],"evaluate":[119],"our":[120,130,147],"method":[121],"two":[123],"benchmarks:":[124],"regression":[126],"dataset":[127,135],"PMEmo":[128,165],"newly":[131],"curated":[132],"six-class":[133,173],"classification":[134],"MCEmo,":[136],"grounded":[137],"Ekman\u2019s":[139],"basic":[140],"theory.":[142],"Experimental":[143],"results":[144],"show":[145],"approach":[148],"achieves":[149],"state-of-the-art":[150],"performance,":[151],"significantly":[152],"outperforming":[153],"strong":[154],"baselines\u2014yielding":[155],"an":[156],"8.2%":[157],"relative":[158],"improvement":[159],"average":[162],"$$R^2$$":[163],"3.6":[168],"percentage":[169],"points":[170],"gain":[171],"accuracy":[174],"MCEmo.":[176],"Ablation":[177],"studies":[178],"confirm":[179],"effectiveness":[181],"decoupling":[184],"proposed":[187],"strategy,":[189],"demonstrating":[190],"modeling":[192],"separate":[197],"modalities":[198],"is":[199],"crucial":[200],"for":[201],"capturing":[202],"nuanced":[203],"cues":[205]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-06-13T00:00:00"}
