{"id":"https://openalex.org/W4377719641","doi":"https://doi.org/10.1109/taslp.2023.3270726","title":"MuseMorphose: Full-Song and Fine-Grained Piano Music Style Transfer With One Transformer VAE","display_name":"MuseMorphose: Full-Song and Fine-Grained Piano Music Style Transfer With One Transformer VAE","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4377719641","doi":"https://doi.org/10.1109/taslp.2023.3270726","mag":"3163784447"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3270726","doi":"https://doi.org/10.1109/taslp.2023.3270726","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3270726","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-b","cwts-core","dongbi-a","norway-2","poland-140","russia-white-list-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2105.04090","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073482068","display_name":"Shih-Lun Wu","orcid":"https://orcid.org/0000-0002-8315-0762","observed_orcids":["https://orcid.org/0000-0002-8315-0762"]},"institutions":[{"id":"https://openalex.org/I4405259202","display_name":"Taiwan AI Labs","ror":"https://ror.org/01x6zrv65","country_code":"TW","type":"other","lineage":["https://openalex.org/I4405259202"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["TW","US"],"is_corresponding":false,"raw_author_name":"Shih-Lun Wu","raw_affiliation_strings":["Taiwan AI Labs, Taipei, Taiwan","Carnegie Mellon University, Pittsburgh, PA, USA; Taiwan AI Labs, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-8315-0762","affiliations":[{"raw_affiliation_string":"Taiwan AI Labs, Taipei, Taiwan","institution_ids":["https://openalex.org/I4405259202"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA; Taiwan AI Labs, Taipei, Taiwan","institution_ids":["https://openalex.org/I4405259202","https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061291906","display_name":"Yi\u2010Hsuan Yang","orcid":"https://orcid.org/0000-0002-2724-6161","observed_orcids":["https://orcid.org/0000-0002-2724-6161"]},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]},{"id":"https://openalex.org/I4405259202","display_name":"Taiwan AI Labs","ror":"https://ror.org/01x6zrv65","country_code":"TW","type":"other","lineage":["https://openalex.org/I4405259202"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Hsuan Yang","raw_affiliation_strings":["Taiwan AI Labs, Taipei, Taiwan","National Taiwan University, Taipei, Taiwan; Taiwan AI Labs, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-2724-6161","affiliations":[{"raw_affiliation_string":"Taiwan AI Labs, Taipei, Taiwan","institution_ids":["https://openalex.org/I4405259202"]},{"raw_affiliation_string":"National Taiwan University, Taipei, Taiwan; Taiwan AI Labs, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864","https://openalex.org/I4405259202"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2345,"currency":"USD","value_usd":2345},"apc_paid":null,"fwci":120.4262,"has_fulltext":true,"cited_by_count":97,"citation_normalized_percentile":{"value":0.99988033,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"31","issue":null,"first_page":"1953","last_page":"1967"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.5580999851226807,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.5580999851226807,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.41670000553131104,"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":0.008100000210106373,"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/midi-generation","display_name":"MIDI generation","score":0.6639999747276306},{"id":"https://openalex.org/keywords/polyphony","display_name":"polyphony","score":0.8730000257492065},{"id":"https://openalex.org/keywords/long-sequence-generation","display_name":"long sequence generation","score":0.5130000114440918}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.8083393573760986},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7637842893600464},{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.7315356731414795},{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.6618916988372803},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.6603357791900635},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6155892014503479},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5897579193115234},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5501103401184082},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.5420892834663391},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.43823105096817017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3753173351287842},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.36101996898651123},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1411784589290619},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.1211768090724945},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0817340612411499},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.07882183790206909},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07668742537498474},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/taslp.2023.3270726","doi":"https://doi.org/10.1109/taslp.2023.3270726","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3270726","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-b","cwts-core","dongbi-a","norway-2","poland-140","russia-white-list-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2105.04090","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.04090","pdf_url":"https://arxiv.org/pdf/2105.04090","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3163784447","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2105.04090.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2105.04090","doi":"https://doi.org/10.48550/arxiv.2105.04090","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2105.04090","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2105.04090","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.04090","pdf_url":"https://arxiv.org/pdf/2105.04090","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321041","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784"},{"id":"https://openalex.org/F4320323900","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4377719641.pdf","grobid_xml":"https://content.openalex.org/works/W4377719641.grobid-xml"},"referenced_works_count":90,"referenced_works":["https://openalex.org/W1501078361","https://openalex.org/W1522301498","https://openalex.org/W1710476689","https://openalex.org/W1816313093","https://openalex.org/W1959608418","https://openalex.org/W2008765103","https://openalex.org/W2064675550","https://openalex.org/W2074308058","https://openalex.org/W2100495367","https://openalex.org/W2111007352","https://openalex.org/W2149741699","https://openalex.org/W2163922914","https://openalex.org/W2194775991","https://openalex.org/W2210838531","https://openalex.org/W2399306074","https://openalex.org/W2405656250","https://openalex.org/W2525778437","https://openalex.org/W2560316200","https://openalex.org/W2587284713","https://openalex.org/W2626778328","https://openalex.org/W2736699890","https://openalex.org/W2753738274","https://openalex.org/W2766393356","https://openalex.org/W2772474126","https://openalex.org/W2789541106","https://openalex.org/W2792210438","https://openalex.org/W2795014578","https://openalex.org/W2798861951","https://openalex.org/W2805041018","https://openalex.org/W2884772108","https://openalex.org/W2885765530","https://openalex.org/W2885835225","https://openalex.org/W2892104732","https://openalex.org/W2896457183","https://openalex.org/W2898827701","https://openalex.org/W2914442349","https://openalex.org/W2919115771","https://openalex.org/W2919624000","https://openalex.org/W2920538220","https://openalex.org/W2924334974","https://openalex.org/W2938704169","https://openalex.org/W2950813464","https://openalex.org/W2951670304","https://openalex.org/W2952335829","https://openalex.org/W2952405182","https://openalex.org/W2953337107","https://openalex.org/W2959020461","https://openalex.org/W2962784628","https://openalex.org/W2963023793","https://openalex.org/W2963135265","https://openalex.org/W2963341956","https://openalex.org/W2963681776","https://openalex.org/W2963799213","https://openalex.org/W2964008635","https://openalex.org/W2964110616","https://openalex.org/W2964121744","https://openalex.org/W2964199361","https://openalex.org/W2964289981","https://openalex.org/W2964669873","https://openalex.org/W2973049837","https://openalex.org/W2995416527","https://openalex.org/W2996287690","https://openalex.org/W3003673875","https://openalex.org/W3034445277","https://openalex.org/W3034573343","https://openalex.org/W3034758887","https://openalex.org/W3037932933","https://openalex.org/W3045523713","https://openalex.org/W3047325651","https://openalex.org/W3047571292","https://openalex.org/W3049174246","https://openalex.org/W3091156754","https://openalex.org/W3092850823","https://openalex.org/W3094144570","https://openalex.org/W3096831136","https://openalex.org/W3098510582","https://openalex.org/W3098708719","https://openalex.org/W3099378280","https://openalex.org/W3111551570","https://openalex.org/W3121309507","https://openalex.org/W3122515622","https://openalex.org/W3124126546","https://openalex.org/W3125056032","https://openalex.org/W3125080906","https://openalex.org/W3129576130","https://openalex.org/W3163721282","https://openalex.org/W3173531154","https://openalex.org/W3175663427","https://openalex.org/W6931146026","https://openalex.org/W6950018155"],"related_works":["https://openalex.org/W3163784447","https://openalex.org/W2952405182","https://openalex.org/W7133227705","https://openalex.org/W3015625764","https://openalex.org/W2995416527","https://openalex.org/W2975687953","https://openalex.org/W3036376755","https://openalex.org/W7002463227","https://openalex.org/W7172488067","https://openalex.org/W4414956918"],"abstract_inverted_index":{"Transformers":[0],"and":[1,94,102,131],"variational":[2],"autoencoders":[3],"(VAE)":[4],"have":[5],"been":[6],"extensively":[7],"employed":[8],"for":[9,158],"symbolic":[10],"(e.g.,":[11,38],"MIDI)":[12],"domain":[13],"music":[14,42],"generation.":[15,88],"While":[16],"the":[17,27,41,54,79,92,104,109,140],"former":[18],"boast":[19],"an":[20],"impressive":[21],"capability":[22],"in":[23,52,121],"modeling":[24],"long":[25,117],"sequences,":[26],"latter":[28],"allow":[29],"users":[30,123],"to":[31,43,57,81,112,139],"willingly":[32],"exert":[33],"control":[34],"over":[35],"different":[36],"parts":[37],"bars)":[39],"of":[40,116],"be":[44],"generated.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49,74,90],"are":[50],"interested":[51],"bringing":[53],"two":[55,71],"together":[56],"construct":[58],"a":[59,99],"single":[60],"model":[61,107],"that":[62,145],"exhibits":[63],"both":[64],"strengths.":[65],"The":[66],"task":[67],"is":[68],"split":[69],"into":[70],"steps.":[72],"First,":[73],"equip":[75],"Transformer":[76,100],"decoders":[77],"with":[78,98,108],"ability":[80],"accept":[82],"segment-level,":[83],"time-varying":[84],"conditions":[85],"during":[86],"sequence":[87],"Subsequently,":[89],"combine":[91],"developed":[93],"tested":[95],"in-attention":[96],"decoder":[97],"encoder,":[101],"train":[103],"resulting":[105],"MuseMorphose":[106,146],"VAE":[110],"objective":[111],"achieve":[113],"style":[114,159],"transfer":[115,160],"pop":[118],"piano":[119],"pieces,":[120],"which":[122],"can":[124],"specify":[125],"musical":[126],"attributes":[127],"including":[128],"rhythmic":[129],"intensity":[130],"polyphony":[132],"(i.e.,":[133],"harmonic":[134],"fullness)":[135],"they":[136],"desire,":[137],"down":[138],"bar":[141],"level.":[142],"Experiments":[143],"show":[144],"outperforms":[147],"recurrent":[148],"neural":[149],"network":[150],"(RNN)":[151],"based":[152],"baselines":[153],"on":[154],"numerous":[155],"widely-used":[156],"metrics":[157],"tasks.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":21},{"year":2025,"cited_by_count":26},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":7}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2023-05-24T00:00:00"}
