{"id":"https://openalex.org/W7137905910","doi":"https://doi.org/10.1609/aaai.v40i3.37201","title":"Let the Model Learn to Feel: Mode-Guided Tonality Injection for Symbolic Music Emotion Recognition","display_name":"Let the Model Learn to Feel: Mode-Guided Tonality Injection for Symbolic Music Emotion Recognition","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137905910","doi":"https://doi.org/10.1609/aaai.v40i3.37201"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i3.37201","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i3.37201","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37201/41163","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37201/41163","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129687187","display_name":"Haiying Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiying Xia","raw_affiliation_strings":["Guangxi Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangxi Normal University","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129645402","display_name":"Zhongyi Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongyi Huang","raw_affiliation_strings":["Guangxi Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangxi Normal University","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103202581","display_name":"Yumei Tan","orcid":"https://orcid.org/0000-0001-8758-4704"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yumei Tan","raw_affiliation_strings":["Guangxi Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangxi Normal University","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129742714","display_name":"Shuxiang Song","orcid":null},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuxiang Song","raw_affiliation_strings":["Guangxi Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangxi Normal University","institution_ids":["https://openalex.org/I29739308"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I29739308"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"3","first_page":"2182","last_page":"2190"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9553999900817871,"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":0.9553999900817871,"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":0.0142000000923872,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.01209999993443489,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/tonality","display_name":"Tonality","score":0.6259999871253967},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5837000012397766},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.5576000213623047},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5527999997138977},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5512999892234802},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5024999976158142},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.4934999942779541},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4763999879360199},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4648999869823456}],"concepts":[{"id":"https://openalex.org/C2776275044","wikidata":"https://www.wikidata.org/wiki/Q192822","display_name":"Tonality","level":3,"score":0.6259999871253967},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5837000012397766},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.5576000213623047},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5527999997138977},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5512999892234802},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5435000061988831},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5024999976158142},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.4934999942779541},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4763999879360199},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4648999869823456},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.4569999873638153},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3986999988555908},{"id":"https://openalex.org/C10864753","wikidata":"https://www.wikidata.org/wiki/Q4353948","display_name":"Music and emotion","level":4,"score":0.3828999996185303},{"id":"https://openalex.org/C146902061","wikidata":"https://www.wikidata.org/wiki/Q476590","display_name":"Music psychology","level":3,"score":0.3808000087738037},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3612000048160553},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.3564999997615814},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3465000092983246},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3368000090122223},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3084000051021576},{"id":"https://openalex.org/C2776095079","wikidata":"https://www.wikidata.org/wiki/Q489538","display_name":"The Symbolic","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.28929999470710754},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C2780583480","wikidata":"https://www.wikidata.org/wiki/Q1366327","display_name":"Tone (literature)","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.25949999690055847},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i3.37201","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i3.37201","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37201/41163","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37201","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37201","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i3.37201","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i3.37201","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37201/41163","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1384081518","display_name":null,"funder_award_id":"DHKL2417","funder_id":"https://openalex.org/F4320330175","funder_display_name":"Guangxi Provincial Key Laboratory of Precision Navigation Technology and Application, Guilin University of Technology"},{"id":"https://openalex.org/G7320996038","display_name":null,"funder_award_id":"62366005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8525241642","display_name":null,"funder_award_id":"62366006","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"},{"id":"https://openalex.org/F4320322768","display_name":"Natural Science Foundation of Guangxi Province","ror":null},{"id":"https://openalex.org/F4320325559","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65"},{"id":"https://openalex.org/F4320327297","display_name":"Education Department of Guangxi Zhuang Autonomous Region","ror":"https://ror.org/00kx48s25"},{"id":"https://openalex.org/F4320330175","display_name":"Guangxi Provincial Key Laboratory of Precision Navigation Technology and Application, Guilin University of Technology","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137905910.pdf","grobid_xml":"https://content.openalex.org/works/W7137905910.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Music":[0],"emotion":[1,136,199],"recognition":[2],"is":[3],"a":[4,25,56,90,108,140],"key":[5],"task":[6],"in":[7,27,59,80,158,196],"symbolic":[8,28,197],"music":[9,29,64,198],"understanding":[10],"(SMER).":[11],"Recent":[12],"approaches":[13],"have":[14],"shown":[15],"promising":[16],"results":[17,189],"by":[18,123],"fine-tuning":[19],"large-scale":[20],"pre-trained":[21],"models":[22,40],"(e.g.,":[23],"MIDIBERT,":[24],"benchmark":[26],"understanding)":[30],"to":[31,35,63,117,148],"map":[32],"musical":[33,44,52],"semantics":[34],"emotional":[36,60,159],"labels.":[37],"While":[38],"these":[39],"effectively":[41,118],"capture":[42],"distributional":[43],"semantics,":[45],"they":[46],"often":[47],"overlook":[48],"tonal":[49],"structures,":[50],"particularly":[51],"modes,":[53],"which":[54,112],"play":[55],"critical":[57],"role":[58],"perception":[61],"according":[62],"psychology.":[65],"In":[66],"this":[67,86,124],"paper,":[68],"we":[69,88,105,126],"investigate":[70],"the":[71,102,129,134,155,166,191],"representational":[72],"capacity":[73],"of":[74,183,193],"MIDIBERT":[75,115,130],"and":[76,138,161,168,185],"identify":[77,128],"its":[78],"limitations":[79],"capturing":[81],"mode-emotion":[82],"associations.":[83],"To":[84],"address":[85],"issue,":[87],"propose":[89],"Mode-Guided":[91],"Enhancement":[92],"(MoGE)":[93],"strategy":[94,176],"that":[95,114,132,172],"incorporates":[96],"psychological":[97],"insights":[98],"on":[99,165],"mode":[100,109,151,174],"into":[101],"model.":[103],"Specifically,":[104],"first":[106],"conduct":[107],"augmentation":[110],"analysis,":[111],"reveals":[113],"fails":[116],"encode":[119],"emotion-mode":[120],"correlations.":[121],"Motivated":[122],"observation,":[125],"further":[127],"layer":[131],"shows":[133],"weakest":[135],"relevance":[137],"introduce":[139],"Mode-guided":[141],"Feature-wise":[142],"linear":[143],"modulation":[144],"injection":[145,175],"(MoFi)":[146],"framework":[147],"inject":[149],"explicit":[150],"features,":[152],"thereby":[153],"enhancing":[154],"model's":[156],"capability":[157],"representation":[160],"inference.":[162],"Extensive":[163],"experiments":[164],"EMOPIA":[167],"VGMIDI":[169],"datasets":[170],"demonstrate":[171],"our":[173],"significantly":[177],"improves":[178],"SMER":[179],"performance,":[180],"achieving":[181],"accuracies":[182],"75.2%":[184],"59.1%,":[186],"respectively.":[187],"These":[188],"validate":[190],"effectiveness":[192],"mode-guided":[194],"modeling":[195],"recognition.":[200]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}