{"id":"https://openalex.org/W7127096767","doi":"https://doi.org/10.31449/inf.v50i5.10631","title":"GAN-Based Model for Multi-Instrument Collaborative Music Generation Using Deep Learning","display_name":"GAN-Based Model for Multi-Instrument Collaborative Music Generation Using Deep Learning","publication_year":2026,"publication_date":"2026-02-02","ids":{"openalex":"https://openalex.org/W7127096767","doi":"https://doi.org/10.31449/inf.v50i5.10631"},"language":null,"primary_location":{"id":"doi:10.31449/inf.v50i5.10631","is_oa":true,"landing_page_url":"https://doi.org/10.31449/inf.v50i5.10631","pdf_url":"https://www.informatica.si/index.php/informatica/article/download/10631/6443","source":{"id":"https://openalex.org/S4210173311","display_name":"Informatica","issn_l":"0350-5596","issn":["0350-5596","1854-3871"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310314525","host_organization_name":"Slovenian Society Informatika","host_organization_lineage":["https://openalex.org/P4310314525"],"host_organization_lineage_names":["Slovenian Society Informatika"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Informatica","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.informatica.si/index.php/informatica/article/download/10631/6443","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124863816","display_name":"Yuanhang Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117337","display_name":"Neijiang Normal University","ror":"https://ror.org/02bc8tz70","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210117337"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuanhang Lin","raw_affiliation_strings":["School of Music, Neijiang Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Music, Neijiang Normal University","institution_ids":["https://openalex.org/I4210117337"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5124863816"],"corresponding_institution_ids":["https://openalex.org/I4210117337"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1079023,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"50","issue":"5","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9480000138282776,"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":0.9480000138282776,"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":0.024800000712275505,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.004100000020116568,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.7720999717712402},{"id":"https://openalex.org/keywords/chord","display_name":"Chord (peer-to-peer)","score":0.6470000147819519},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.5547000169754028},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.46889999508857727},{"id":"https://openalex.org/keywords/midi","display_name":"MIDI","score":0.42100000381469727},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.3968000113964081},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.38119998574256897},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3682999908924103},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.3589000105857849},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.33709999918937683}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.7720999717712402},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7278000116348267},{"id":"https://openalex.org/C194147245","wikidata":"https://www.wikidata.org/wiki/Q1076368","display_name":"Chord (peer-to-peer)","level":2,"score":0.6470000147819519},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5853000283241272},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5841000080108643},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.5547000169754028},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.46889999508857727},{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.42100000381469727},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.3968000113964081},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.38119998574256897},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3682999908924103},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3589000105857849},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.3370000123977661},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.334199994802475},{"id":"https://openalex.org/C2983311337","wikidata":"https://www.wikidata.org/wiki/Q34379","display_name":"Musical instrument","level":2,"score":0.3215999901294708},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.2946000099182129},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.29440000653266907},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.28769999742507935},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.2833000123500824},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2752000093460083},{"id":"https://openalex.org/C81687914","wikidata":"https://www.wikidata.org/wiki/Q1501797","display_name":"Percussion","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27079999446868896},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.2669000029563904},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.2574000060558319},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.25220000743865967},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.25200000405311584},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.31449/inf.v50i5.10631","is_oa":true,"landing_page_url":"https://doi.org/10.31449/inf.v50i5.10631","pdf_url":"https://www.informatica.si/index.php/informatica/article/download/10631/6443","source":{"id":"https://openalex.org/S4210173311","display_name":"Informatica","issn_l":"0350-5596","issn":["0350-5596","1854-3871"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310314525","host_organization_name":"Slovenian Society Informatika","host_organization_lineage":["https://openalex.org/P4310314525"],"host_organization_lineage_names":["Slovenian Society Informatika"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Informatica","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.31449/inf.v50i5.10631","is_oa":true,"landing_page_url":"https://doi.org/10.31449/inf.v50i5.10631","pdf_url":"https://www.informatica.si/index.php/informatica/article/download/10631/6443","source":{"id":"https://openalex.org/S4210173311","display_name":"Informatica","issn_l":"0350-5596","issn":["0350-5596","1854-3871"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310314525","host_organization_name":"Slovenian Society Informatika","host_organization_lineage":["https://openalex.org/P4310314525"],"host_organization_lineage_names":["Slovenian Society Informatika"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Informatica","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5991315841674805}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7127096767.pdf","grobid_xml":"https://content.openalex.org/works/W7127096767.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,44,112,230],"intelligent":[1],"development":[2],"of":[3,9,51,179,186,193,215,308],"music":[4,23,54,311],"creation":[5],"promotes":[6],"the":[7,170,305],"application":[8,306],"artificial":[10],"intelligence":[11],"in":[12,235,266,273],"multi-instrument":[13,22,53,310],"collaborative":[14,254],"composition.":[15],"In":[16],"this":[17],"study,":[18],"we":[19],"propose":[20],"a":[21,28,49,63,78,88,115,131,154,174,182,189],"generation":[24,295],"model":[25,45,172,231],"based":[26],"on":[27,48,122],"conditional":[29],"Generative":[30],"Adversarial":[31],"Network":[32],"(cGAN)":[33],"that":[34,92,169,293],"explicitly":[35],"learns":[36],"different":[37,258],"instrument":[38,123,197,228],"performance":[39,255],"patterns":[40],"and":[41,62,71,81,85,109,118,142,164,188,202,224,244,249,272,284,297],"their":[42],"coordination.":[43,229],"is":[46,75,299],"trained":[47],"dataset":[50],"19,000":[52],"excerpts":[55],"collected":[56],"from":[57],"Muse":[58],"Score,":[59],"Magenta,":[60],"Spottily":[61],"self-built":[64],"corpus,":[65],"covering":[66],"classical,":[67],"pop,":[68],"jazz,":[69],"electronic":[70,275],"orchestral":[72],"styles.":[73],"Audio":[74],"converted":[76],"to":[77,104,125,160],"unified":[79],"format":[80],"sampling":[82],"rate,":[83],"denoised,":[84],"represented":[86],"by":[87],"fused":[89],"feature":[90],"set":[91],"combines":[93],"short-time":[94],"Fourier":[95],"transform":[96],"(STFT)":[97],"spectrograms":[98],"with":[99,153,207,278],"Mel-frequency":[100],"cepstral":[101],"coefficients":[102],"(MFCCs)":[103],"capture":[105],"both":[106],"harmonic":[107],"structure":[108],"timbral":[110],"characteristics.":[111],"generator":[113],"adopts":[114],"multi-layer":[116],"convolutional":[117],"transposed-convolutional":[119],"architecture":[120],"conditioned":[121],"labels":[124],"synthesize":[126],"multi-track":[127],"audio":[128,165],"segments,":[129],"while":[130],"multi-branch":[132],"discriminator":[133],"jointly":[134],"evaluates":[135],"global":[136],"musical":[137],"coherence,":[138],"instrument-wise":[139],"timbre":[140,222],"consistency":[141],"style":[143],"conformity.":[144],"Model":[145],"parameters":[146],"are":[147],"optimized":[148],"using":[149],"gradient-based":[150],"training":[151,162,285],"combined":[152],"genetic":[155],"search":[156],"over":[157],"key":[158],"hyperparameters":[159],"enhance":[161],"stability":[163,286],"realism.Quantitative":[166],"experiments":[167],"show":[168],"proposed":[171],"achieves":[173],"mean":[175],"pitch":[176],"prediction":[177],"error":[178],"0.42":[180],"semitones,":[181],"chord":[183,242,270],"recognition":[184],"accuracy":[185],"92.3%,":[187],"rhythm":[190],"synchronization":[191],"rate":[192],"95.1%":[194],"across":[195],"common":[196],"combinations":[198],"such":[199],"as":[200],"piano\u2013violin":[201],"guitar\u2013bass.":[203],"Subjective":[204],"listening":[205],"tests":[206],"20":[208],"experienced":[209],"musicians":[210],"report":[211],"an":[212,300],"average":[213],"score":[214],"4.3/5":[216],"for":[217,221,226,264,303],"melody":[218],"fluency,":[219],"4.2/5":[220],"matching":[223],"4.1/5":[225],"perceived":[227],"performs":[232],"particularly":[233],"well":[234],"generating":[236],"melodically":[237],"fluent":[238],"lines,":[239],"harmonically":[240],"consistent":[241],"progressions":[243],"rhythmically":[245],"stable":[246],"ensemble":[247],"parts,":[248],"can":[250],"more":[251],"accurately":[252],"simulate":[253],"effects":[256],"among":[257],"instruments.":[259,280],"However,":[260],"there":[261],"remains":[262],"room":[263],"improvement":[265],"handling":[267],"highly":[268],"complex":[269],"transformations":[271],"integrating":[274],"synthesizer":[276],"timbres":[277],"traditional":[279],"Moreover,":[281],"computational":[282],"cost":[283],"still":[287],"constrain":[288],"large-scale":[289],"practical":[290],"deployment,":[291],"indicating":[292],"improving":[294],"efficiency":[296],"robustness":[298],"important":[301],"direction":[302],"enhancing":[304],"value":[307],"AI-based":[309],"composition":[312],"models.":[313]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-02-03T00:00:00"}