{"id":"https://openalex.org/W4416800071","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11248983","title":"MORTM: MoE-Optimized Rhythmic Transformer Model for Symbolic MIDI Generation","display_name":"MORTM: MoE-Optimized Rhythmic Transformer Model for Symbolic MIDI Generation","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416800071","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11248983"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11248983","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11248983","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-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/A5115717368","display_name":"Takaaki Nagoshi","orcid":null},"institutions":[{"id":"https://openalex.org/I104946051","display_name":"Nihon University","ror":"https://ror.org/05jk51a88","country_code":"JP","type":"education","lineage":["https://openalex.org/I104946051"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takaaki Nagoshi","raw_affiliation_strings":["Nihon University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nihon University,Japan","institution_ids":["https://openalex.org/I104946051"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108346747","display_name":"Tetsuro Kitahara","orcid":null},"institutions":[{"id":"https://openalex.org/I104946051","display_name":"Nihon University","ror":"https://ror.org/05jk51a88","country_code":"JP","type":"education","lineage":["https://openalex.org/I104946051"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuro Kitahara","raw_affiliation_strings":["Nihon University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nihon University,Japan","institution_ids":["https://openalex.org/I104946051"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I104946051"],"apc_list":null,"apc_paid":null,"fwci":0.8063,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78768844,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"258","last_page":"263"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9598000049591064,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9598000049591064,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11309","display_name":"Music and Audio Processing","score":0.014700000174343586,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.004699999932199717,"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/melody","display_name":"Melody","score":0.8716999888420105},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.7542999982833862},{"id":"https://openalex.org/keywords/midi","display_name":"MIDI","score":0.6082000136375427},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5758000016212463},{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.48649999499320984},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.3564999997615814},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.3346000015735626},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.32359999418258667}],"concepts":[{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.8716999888420105},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.7542999982833862},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.664900004863739},{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.6082000136375427},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5758000016212463},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5587000250816345},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.48649999499320984},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.3564999997615814},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3346000015735626},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2962000072002411},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C191287063","wikidata":"https://www.wikidata.org/wiki/Q543281","display_name":"Glitch","level":3,"score":0.2915000021457672},{"id":"https://openalex.org/C195818886","wikidata":"https://www.wikidata.org/wiki/Q5421724","display_name":"Expressive power","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.28760001063346863},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.28360000252723694},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.25270000100135803},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11248983","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11248983","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1498436455","https://openalex.org/W2064675550","https://openalex.org/W2150884987"],"related_works":[],"abstract_inverted_index":{"This":[0],"study":[1,132],"proposes":[2],"MORTM,":[3],"a":[4,27,35],"new":[5],"melody":[6],"generation":[7,164],"model":[8,71],"that":[9,51,106,153],"introduces":[10],"the":[11,19,61,70,81,107,136,140,145,154,159,163],"Mixture":[12],"of":[13,21,30,84,123,135,142,147,162],"Experts":[14],"(MoE)":[15],"architecture":[16,156],"to":[17,43,65,69,95,138,167],"address":[18],"challenges":[20],"conventional":[22],"Transformer-based":[23],"models":[24],"in":[25,37,117,144],"handling":[26],"diverse":[28],"array":[29],"musical":[31,46,169],"styles.":[32],"MoE":[33,55,143,155],"is":[34,133],"framework":[36],"which":[38],"specialized":[39],"subnetworks":[40],"(experts)":[41],"learn":[42],"handle":[44],"distinct":[45],"aspects.":[47],"Experimental":[48],"results":[49],"demonstrate":[50,139],"MORTM":[52],"equipped":[53],"with":[54,80,120],"significantly":[56,157],"improved":[57],"predictive":[58],"accuracy,":[59],"reducing":[60],"perplexity":[62],"from":[63,88],"4.92":[64],"2.04":[66],"when":[67],"compared":[68],"without":[72],"MoE.":[73],"It":[74],"also":[75],"enhanced":[76],"music":[77,149],"theoretical":[78],"consistency,":[79],"usage":[82],"rate":[83],"diatonic":[85],"notes":[86],"increasing":[87],"<tex":[89,96],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[90,97],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\text{7":[91],"6.":[92],"3":[93],"\\%}$</tex>":[94],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\text{8":[98],"1.":[99],"2":[100],"\\%}$</tex>.":[101],"Furthermore,":[102],"qualitative":[103],"analysis":[104],"implied":[105],"generated":[108],"melodies":[109],"were":[110],"more":[111],"natural":[112],"and":[113,125,171],"showed":[114],"greater":[115],"variability":[116],"melodic":[118],"features,":[119],"effective":[121],"use":[122],"triplets":[124],"rests.":[126],"Based":[127],"on":[128],"these":[129],"findings,":[130],"this":[131],"one":[134],"first":[137],"effectiveness":[141],"field":[146],"symbolic":[148],"generation.":[150],"We":[151],"conclude":[152],"enhances":[158],"expressive":[160],"power":[161],"model,":[165],"contributing":[166],"both":[168],"consistency":[170],"diversity.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-01T08:55:40.977307","created_date":"2025-11-28T00:00:00"}