{"id":"https://openalex.org/W2899724567","doi":"https://doi.org/10.1609/aaai.v33i01.33011174","title":"PerformanceNet: Score-to-Audio Music Generation with Multi-Band Convolutional Residual Network","display_name":"PerformanceNet: Score-to-Audio Music Generation with Multi-Band Convolutional Residual Network","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2899724567","doi":"https://doi.org/10.1609/aaai.v33i01.33011174","mag":"2899724567"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33011174","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33011174","pdf_url":"https://aaai.org/ojs/index.php/AAAI/article/download/3911/3789","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://aaai.org/ojs/index.php/AAAI/article/download/3911/3789","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101432451","display_name":"Bryan Wang","orcid":"https://orcid.org/0000-0001-9016-038X"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Bryan Wang","raw_affiliation_strings":["Academia Sinica"],"affiliations":[{"raw_affiliation_string":"Academia Sinica","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061291906","display_name":"Yi\u2010Hsuan Yang","orcid":"https://orcid.org/0000-0002-2724-6161"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Hsuan Yang","raw_affiliation_strings":["Academia Sinica"],"affiliations":[{"raw_affiliation_string":"Academia Sinica","institution_ids":["https://openalex.org/I84653119"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101432451"],"corresponding_institution_ids":["https://openalex.org/I84653119"],"apc_list":null,"apc_paid":null,"fwci":4.1118,"has_fulltext":true,"cited_by_count":28,"citation_normalized_percentile":{"value":0.95152355,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"33","issue":"01","first_page":"1174","last_page":"1181"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9991000294685364,"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/T10860","display_name":"Speech and Audio Processing","score":0.9854000210762024,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7485817670822144},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6600916981697083},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.6437009572982788},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.626322865486145},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.5254858136177063},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47273552417755127},{"id":"https://openalex.org/keywords/violin","display_name":"Violin","score":0.4356616735458374},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.4338444471359253},{"id":"https://openalex.org/keywords/melody","display_name":"Melody","score":0.43157249689102173},{"id":"https://openalex.org/keywords/pop-music-automation","display_name":"Pop music automation","score":0.4221068024635315},{"id":"https://openalex.org/keywords/pitch","display_name":"Pitch (Music)","score":0.4165031909942627},{"id":"https://openalex.org/keywords/musical-notation","display_name":"Musical notation","score":0.4133906662464142},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41188663244247437},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.392522394657135},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3510696589946747},{"id":"https://openalex.org/keywords/musical-composition","display_name":"Musical composition","score":0.2514941990375519},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.15552282333374023}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7485817670822144},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6600916981697083},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.6437009572982788},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.626322865486145},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.5254858136177063},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47273552417755127},{"id":"https://openalex.org/C129554576","wikidata":"https://www.wikidata.org/wiki/Q8355","display_name":"Violin","level":2,"score":0.4356616735458374},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.4338444471359253},{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.43157249689102173},{"id":"https://openalex.org/C73520026","wikidata":"https://www.wikidata.org/wiki/Q7229091","display_name":"Pop music automation","level":4,"score":0.4221068024635315},{"id":"https://openalex.org/C153405242","wikidata":"https://www.wikidata.org/wiki/Q118819","display_name":"Pitch (Music)","level":3,"score":0.4165031909942627},{"id":"https://openalex.org/C88639978","wikidata":"https://www.wikidata.org/wiki/Q233861","display_name":"Musical notation","level":3,"score":0.4133906662464142},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41188663244247437},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.392522394657135},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3510696589946747},{"id":"https://openalex.org/C109568592","wikidata":"https://www.wikidata.org/wiki/Q207628","display_name":"Musical composition","level":3,"score":0.2514941990375519},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.15552282333374023},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v33i01.33011174","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33011174","pdf_url":"https://aaai.org/ojs/index.php/AAAI/article/download/3911/3789","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"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33011174","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33011174","pdf_url":"https://aaai.org/ojs/index.php/AAAI/article/download/3911/3789","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":[{"score":0.47999998927116394,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2899724567.pdf","grobid_xml":"https://content.openalex.org/works/W2899724567.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W4126978","https://openalex.org/W54257720","https://openalex.org/W1901129140","https://openalex.org/W1959608418","https://openalex.org/W1994488211","https://openalex.org/W2120847449","https://openalex.org/W2127302078","https://openalex.org/W2136655611","https://openalex.org/W2157880479","https://openalex.org/W2164498268","https://openalex.org/W2173520492","https://openalex.org/W2191779130","https://openalex.org/W2194775991","https://openalex.org/W2475287302","https://openalex.org/W2486605727","https://openalex.org/W2519091744","https://openalex.org/W2523714292","https://openalex.org/W2529229741","https://openalex.org/W2559688696","https://openalex.org/W2560316200","https://openalex.org/W2572730214","https://openalex.org/W2606176153","https://openalex.org/W2726957814","https://openalex.org/W2754229890","https://openalex.org/W2766527293","https://openalex.org/W2774625825","https://openalex.org/W2777302760","https://openalex.org/W2786254735","https://openalex.org/W2792210438","https://openalex.org/W2805697608","https://openalex.org/W2811079561","https://openalex.org/W2849790107","https://openalex.org/W2884558435","https://openalex.org/W2885570506","https://openalex.org/W2887720658","https://openalex.org/W2902076983","https://openalex.org/W2950547518","https://openalex.org/W2962947361","https://openalex.org/W2963470893","https://openalex.org/W2963575853","https://openalex.org/W2963684088","https://openalex.org/W2963750251","https://openalex.org/W2963800363","https://openalex.org/W2964243274","https://openalex.org/W4294643831","https://openalex.org/W4297772864","https://openalex.org/W4320013936","https://openalex.org/W6640963894","https://openalex.org/W6687483927","https://openalex.org/W6730401039","https://openalex.org/W6734074887","https://openalex.org/W6751598888"],"related_works":["https://openalex.org/W327409203","https://openalex.org/W3108094971","https://openalex.org/W2071815022","https://openalex.org/W178932670","https://openalex.org/W3163568691","https://openalex.org/W3095436719","https://openalex.org/W2012356996","https://openalex.org/W1989409385","https://openalex.org/W2152591660","https://openalex.org/W2899724567"],"abstract_inverted_index":{"Music":[0],"creation":[1],"is":[2],"typically":[3],"composed":[4],"of":[5,136,145,153,196,208,217,225],"two":[6,154,249],"parts:":[7],"composing":[8],"the":[9,15,34,88,129,139,148,156,165,178,189,193,202,209,223],"musical":[10,54,71],"score,":[11],"and":[12,67,84,141,169,171,177,198,212,241,248],"then":[13],"performing":[14],"score":[16,237],"with":[17,59,214],"instruments":[18],"to":[19,42,65,163,172,187,204],"make":[20],"sounds.":[21,107],"While":[22],"recent":[23],"work":[24],"has":[25,104],"made":[26,41],"much":[27],"progress":[28],"in":[29,33,82,116,125,239],"automatic":[30],"music":[31,51,102,137,146,206],"generation":[32],"symbolic":[35,134],"domain,":[36],"few":[37],"attempts":[38],"have":[39],"been":[40],"build":[43,109],"an":[44,111,126,142,174],"AI":[45,112],"model":[46,122,151,203,232,247],"that":[47,123,229],"can":[48],"render":[49],"realistic":[50],"audio":[52,58,103,143],"from":[53],"scores.":[55],"Directly":[56],"synthesizing":[57],"sound":[60,91],"sample":[61],"libraries":[62],"often":[63],"leads":[64],"mechanical":[66],"deadpan":[68],"results,":[69],"since":[70,101],"scores":[72],"do":[73],"not":[74],"contain":[75],"performance-level":[76],"information,":[77],"such":[78,110],"as":[79],"subtle":[80],"changes":[81],"timing":[83],"dynamics.":[85],"Moreover,":[86],"while":[87],"task":[89],"may":[90],"like":[92],"a":[93,119,133,160,183,215,226,245],"text-to-speech":[94],"synthesis":[95],"problem,":[96],"there":[97],"are":[98],"fundamental":[99],"differences":[100],"rich":[105],"polyphonic":[106],"To":[108],"performer,":[113],"we":[114],"propose":[115],"this":[117],"paper":[118],"deep":[120],"convolutional":[121],"learns":[124],"end-to-end":[127],"manner":[128],"score-to-audio":[130],"mapping":[131],"between":[132,167],"representation":[135,144],"called":[138,147],"pianorolls":[140,168],"spectrograms.":[149],"The":[150],"consists":[152],"subnets:":[155],"ContourNet,":[157],"which":[158,180],"uses":[159,182],"U-Net":[161],"structure":[162],"learn":[164],"correspondence":[166],"spectrograms":[170],"give":[173],"initial":[175],"result;":[176],"TextureNet,":[179],"further":[181],"multi-band":[184],"residual":[185],"network":[186],"refine":[188],"result":[190,224],"by":[191],"adding":[192],"spectral":[194],"texture":[195],"overtones":[197],"timbre.":[199],"We":[200,220,252],"train":[201],"generate":[205],"clips":[207],"violin,":[210],"cello,":[211],"flute,":[213],"dataset":[216],"moderate":[218],"size.":[219],"also":[221],"present":[222],"user":[227],"study":[228],"shows":[230],"our":[231,254],"achieves":[233],"higher":[234],"mean":[235],"opinion":[236],"(MOS)":[238],"naturalness":[240],"emotional":[242],"expressivity":[243],"than":[244],"WaveNet-based":[246],"off-the-shelf":[250],"synthesizers.":[251],"open":[253],"source":[255],"code":[256],"at":[257],"https://github.com/bwang514/PerformanceNet":[258]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}
