{"id":"https://openalex.org/W4414140891","doi":"https://doi.org/10.1109/icmew68306.2025.11152218","title":"M6(GPT)3: Generating Multitrack Modifiable Multi-Minute MIDI Music from Text using Genetic Algorithms, Probabilistic Methods and GPT Models in any Progression and Time Signature","display_name":"M6(GPT)3: Generating Multitrack Modifiable Multi-Minute MIDI Music from Text using Genetic Algorithms, Probabilistic Methods and GPT Models in any Progression and Time Signature","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4414140891","doi":"https://doi.org/10.1109/icmew68306.2025.11152218"},"language":"en","primary_location":{"id":"doi:10.1109/icmew68306.2025.11152218","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew68306.2025.11152218","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","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/A5114400367","display_name":"Jakub Po\u0107wiardowski","orcid":null},"institutions":[{"id":"https://openalex.org/I108403487","display_name":"Warsaw University of Technology","ror":"https://ror.org/00y0xnp53","country_code":"PL","type":"education","lineage":["https://openalex.org/I108403487"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Jakub Po\u0107wiardowski","raw_affiliation_strings":["Institute of Computer Science Warsaw University of Technology,Warsaw,Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Science Warsaw University of Technology,Warsaw,Poland","institution_ids":["https://openalex.org/I108403487"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076000935","display_name":"Mateusz Modrzejewski","orcid":"https://orcid.org/0000-0002-6363-8584"},"institutions":[{"id":"https://openalex.org/I108403487","display_name":"Warsaw University of Technology","ror":"https://ror.org/00y0xnp53","country_code":"PL","type":"education","lineage":["https://openalex.org/I108403487"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Mateusz Modrzejewski","raw_affiliation_strings":["Institute of Computer Science Warsaw University of Technology,Warsaw,Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Science Warsaw University of Technology,Warsaw,Poland","institution_ids":["https://openalex.org/I108403487"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036916864","display_name":"Marek S. Tatara","orcid":"https://orcid.org/0000-0001-9753-8429"},"institutions":[{"id":"https://openalex.org/I134353371","display_name":"SK Group (South Korea)","ror":"https://ror.org/03696td91","country_code":"KR","type":"company","lineage":["https://openalex.org/I134353371"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Marek S. Tatara","raw_affiliation_strings":["Gdańsk University of Technology,Department of Robotics and Decision Systems,Gdańsk,Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gdańsk University of Technology,Department of Robotics and Decision Systems,Gdańsk,Poland","institution_ids":["https://openalex.org/I134353371"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27840017,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9998999834060669,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.9976999759674072,"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/midi","display_name":"MIDI","score":0.71670001745224},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6322000026702881},{"id":"https://openalex.org/keywords/chord","display_name":"Chord (peer-to-peer)","score":0.5841000080108643},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5217999815940857},{"id":"https://openalex.org/keywords/melody","display_name":"Melody","score":0.4343999922275543},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3846000134944916},{"id":"https://openalex.org/keywords/signature","display_name":"Signature (topology)","score":0.3598000109195709},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.34470000863075256},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32919999957084656},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.3257000148296356}],"concepts":[{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.71670001745224},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6901999711990356},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6322000026702881},{"id":"https://openalex.org/C194147245","wikidata":"https://www.wikidata.org/wiki/Q1076368","display_name":"Chord (peer-to-peer)","level":2,"score":0.5841000080108643},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5710999965667725},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5565000176429749},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5217999815940857},{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.4343999922275543},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3846000134944916},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36039999127388},{"id":"https://openalex.org/C2779696439","wikidata":"https://www.wikidata.org/wiki/Q7512811","display_name":"Signature (topology)","level":2,"score":0.3598000109195709},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.34470000863075256},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3215999901294708},{"id":"https://openalex.org/C2780416260","wikidata":"https://www.wikidata.org/wiki/Q2063","display_name":"JSON","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3086000084877014},{"id":"https://openalex.org/C176066374","wikidata":"https://www.wikidata.org/wiki/Q629118","display_name":"Fitness function","level":3,"score":0.3025999963283539},{"id":"https://openalex.org/C88639978","wikidata":"https://www.wikidata.org/wiki/Q233861","display_name":"Musical notation","level":3,"score":0.30250000953674316},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.29510000348091125},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C8880873","wikidata":"https://www.wikidata.org/wiki/Q187787","display_name":"Genetic algorithm","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C167927819","wikidata":"https://www.wikidata.org/wiki/Q1930567","display_name":"Shuffling","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C81687914","wikidata":"https://www.wikidata.org/wiki/Q1501797","display_name":"Percussion","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.25609999895095825}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmew68306.2025.11152218","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew68306.2025.11152218","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","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":21,"referenced_works":["https://openalex.org/W149236175","https://openalex.org/W398859631","https://openalex.org/W1590874898","https://openalex.org/W1965906514","https://openalex.org/W1966910303","https://openalex.org/W2338312508","https://openalex.org/W2621868418","https://openalex.org/W2772474126","https://openalex.org/W3049272330","https://openalex.org/W3092879656","https://openalex.org/W3114948430","https://openalex.org/W3127633281","https://openalex.org/W4221148975","https://openalex.org/W4246278590","https://openalex.org/W4287802874","https://openalex.org/W4318351475","https://openalex.org/W4372259826","https://openalex.org/W4379251846","https://openalex.org/W4380136719","https://openalex.org/W4396819664","https://openalex.org/W4399418334"],"related_works":["https://openalex.org/W3133630535","https://openalex.org/W2398084541","https://openalex.org/W4242364395","https://openalex.org/W2386555541","https://openalex.org/W3042962886","https://openalex.org/W2920621887","https://openalex.org/W2187442448","https://openalex.org/W889314198","https://openalex.org/W4285031015","https://openalex.org/W2580099843"],"abstract_inverted_index":{"This":[0],"work":[1],"introduces":[2],"the":[3,22,79],"M6(GPT)3":[4],"composer":[5],"system,":[6],"capable":[7],"of":[8,81],"generating":[9,119],"complete,":[10],"multi-minute":[11],"musical":[12,89,101],"compositions":[13],"with":[14,88],"complex":[15],"structures":[16],"in":[17,21,28,47,121],"any":[18,122],"time":[19,54,123],"signature,":[20,55],"MIDI":[23],"domain":[24],"from":[25,62],"input":[26],"descriptions":[27],"natural":[29,41],"language.":[30],"The":[31,50,84,104,116],"system":[32,117],"utilizes":[33],"an":[34],"autoregressive":[35],"transformer":[36],"language":[37,42],"model":[38],"to":[39,44,155],"map":[40],"prompts":[43],"composition":[45],"parameters":[46,111],"JSON":[48],"format.":[49],"defined":[51],"structure":[52],"includes":[53],"scales,":[56],"chord":[57],"progressions,":[58],"and":[59,68,91,99,112,134],"valence-arousal":[60],"values,":[61],"which":[63],"accompaniment,":[64],"melody,":[65],"bass,":[66],"motif,":[67],"percussion":[69,120],"tracks":[70],"are":[71],"created.":[72],"We":[73],"propose":[74],"a":[75,92,152],"genetic":[76],"algorithm":[77,85],"for":[78,118],"generation":[80,142],"melodic":[82],"elements.":[83],"incorporates":[86],"mutations":[87],"significance":[90],"fitness":[93],"function":[94],"based":[95],"on":[96,146],"normal":[97],"distribution":[98],"predefined":[100],"feature":[102],"values.":[103],"values":[105],"adaptively":[106],"evolve,":[107],"influenced":[108],"by":[109],"emotional":[110],"distinct":[113],"playing":[114],"styles.":[115],"signature":[124],"utilises":[125],"probabilistic":[126],"methods,":[127],"including":[128],"Markov":[129],"chains.":[130],"Through":[131],"both":[132],"human":[133],"objective":[135],"evaluations,":[136],"we":[137],"demonstrate":[138],"that":[139],"our":[140],"music":[141],"approach":[143],"outperforms":[144],"baselines":[145],"specific,":[147],"musically":[148],"meaningful":[149],"metrics,":[150],"offering":[151],"viable":[153],"alternative":[154],"purely":[156],"neural":[157],"network-based":[158],"systems.":[159]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}