{"id":"https://openalex.org/W2962775980","doi":"https://doi.org/10.1609/aaai.v33i01.33011061","title":"Play as You Like: Timbre-Enhanced Multi-Modal Music Style Transfer","display_name":"Play as You Like: Timbre-Enhanced Multi-Modal Music Style Transfer","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2962775980","doi":"https://doi.org/10.1609/aaai.v33i01.33011061","mag":"2962775980"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33011061","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33011061","pdf_url":"https://aaai.org/ojs/index.php/AAAI/article/download/3897/3775","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/3897/3775","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109370301","display_name":"Chien-Yu Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chien-Yu Lu","raw_affiliation_strings":["National Tsing Hua University"],"affiliations":[{"raw_affiliation_string":"National Tsing Hua University","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002599997","display_name":"Min-Xin Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Min-Xin Xue","raw_affiliation_strings":["National Tsing Hua University"],"affiliations":[{"raw_affiliation_string":"National Tsing Hua University","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032190615","display_name":"Chia-Che Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chia-Che Chang","raw_affiliation_strings":["National Tsing Hua University"],"affiliations":[{"raw_affiliation_string":"National Tsing Hua University","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058589126","display_name":"Che\u2013Rung Lee","orcid":"https://orcid.org/0000-0003-3940-4478"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Che-Rung Lee","raw_affiliation_strings":["National Tsing Hua University"],"affiliations":[{"raw_affiliation_string":"National Tsing Hua University","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038264558","display_name":"Li Su","orcid":"https://orcid.org/0000-0003-4275-8832"},"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":"Li Su","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":5,"corresponding_author_ids":["https://openalex.org/A5109370301"],"corresponding_institution_ids":["https://openalex.org/I25846049"],"apc_list":null,"apc_paid":null,"fwci":6.1358,"has_fulltext":true,"cited_by_count":29,"citation_normalized_percentile":{"value":0.97368421,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"33","issue":"01","first_page":"1061","last_page":"1068"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9930999875068665,"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":0.9930999875068665,"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/T10860","display_name":"Speech and Audio Processing","score":0.9908999800682068,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9761999845504761,"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/timbre","display_name":"Timbre","score":0.8283659219741821},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7162226438522339},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5901187062263489},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.48893657326698303},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4858245849609375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4749172627925873},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.46660181879997253},{"id":"https://openalex.org/keywords/spectral-envelope","display_name":"Spectral envelope","score":0.4203811585903168},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35233888030052185},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.11875385046005249}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.8283659219741821},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7162226438522339},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5901187062263489},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.48893657326698303},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4858245849609375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4749172627925873},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.46660181879997253},{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.4203811585903168},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35233888030052185},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.11875385046005249},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v33i01.33011061","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33011061","pdf_url":"https://aaai.org/ojs/index.php/AAAI/article/download/3897/3775","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.v33i01.33011061","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33011061","pdf_url":"https://aaai.org/ojs/index.php/AAAI/article/download/3897/3775","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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2962775980.pdf","grobid_xml":"https://content.openalex.org/works/W2962775980.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W1556327471","https://openalex.org/W1590604789","https://openalex.org/W1986595194","https://openalex.org/W2008066450","https://openalex.org/W2028895660","https://openalex.org/W2071326872","https://openalex.org/W2135733734","https://openalex.org/W2140356304","https://openalex.org/W2294038178","https://openalex.org/W2308529009","https://openalex.org/W2326925005","https://openalex.org/W2328848613","https://openalex.org/W2405581548","https://openalex.org/W2475287302","https://openalex.org/W2519091744","https://openalex.org/W2523469089","https://openalex.org/W2593414223","https://openalex.org/W2605287558","https://openalex.org/W2611104282","https://openalex.org/W2619556892","https://openalex.org/W2630255117","https://openalex.org/W2768959015","https://openalex.org/W2786254735","https://openalex.org/W2793183272","https://openalex.org/W2797650215","https://openalex.org/W2798844427","https://openalex.org/W2810518847","https://openalex.org/W2849790107","https://openalex.org/W2962793481","https://openalex.org/W2962947361","https://openalex.org/W2963233633","https://openalex.org/W2963890275","https://openalex.org/W2964121592","https://openalex.org/W2964268978","https://openalex.org/W4292198620","https://openalex.org/W4298294608","https://openalex.org/W4301107988","https://openalex.org/W4320013936","https://openalex.org/W6633252260","https://openalex.org/W6657918666","https://openalex.org/W6680762372","https://openalex.org/W6701655646","https://openalex.org/W6734074887","https://openalex.org/W6734564793","https://openalex.org/W6737215374","https://openalex.org/W6745992979","https://openalex.org/W6747635987","https://openalex.org/W6749509193"],"related_works":["https://openalex.org/W2048127514","https://openalex.org/W2075905938","https://openalex.org/W2152591660","https://openalex.org/W2292954653","https://openalex.org/W1570824959","https://openalex.org/W3082502994","https://openalex.org/W2543693073","https://openalex.org/W2124515947","https://openalex.org/W1994414084","https://openalex.org/W1987096921"],"abstract_inverted_index":{"Style":[0],"transfer":[1,63,178,203],"of":[2,14,46,77,115,122,196],"polyphonic":[3],"music":[4,19,47,61,78,201],"recordings":[5],"is":[6,52,162],"a":[7,150],"challenging":[8],"task":[9],"when":[10],"considering":[11],"the":[12,22,66,74,82,90,101,113,119,125,146,194,197,214],"modeling":[13],"diverse,":[15],"imaginative,":[16],"and":[17,41,107,124,140,169,189,208],"reasonable":[18],"pieces":[20],"in":[21,48,89,127,200,209],"style":[23,62,177,202],"different":[24,182],"from":[25,100],"their":[26],"original":[27],"one.":[28],"To":[29],"achieve":[30,166],"this,":[31],"learning":[32],"stable":[33],"multi-modal":[34,75],"representations":[35],"for":[36,68],"both":[37],"domain-variant":[38],"(i.e.,":[39,43],"style)":[40],"domaininvariant":[42],"content)":[44],"information":[45],"an":[49,59],"unsupervised":[50,60],"manner":[51],"critical.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57,80],"propose":[58],"method":[64,199],"without":[65],"need":[67],"parallel":[69],"data.":[70],"Besides,":[71],"to":[72,96,110,165,212],"characterize":[73],"distribution":[76],"pieces,":[79],"employ":[81],"Multi-modal":[83],"Unsupervised":[84],"Image-to-Image":[85],"Translation":[86],"(MUNIT)":[87],"framework":[88],"proposed":[91,198],"system.":[92],"This":[93],"allows":[94],"one":[95],"generate":[97],"diverse":[98],"outputs":[99],"learned":[102],"latent":[103],"distributions":[104],"representing":[105],"contents":[106],"styles.":[108],"Moreover,":[109],"better":[111],"capture":[112],"granularity":[114],"sound,":[116],"such":[117],"as":[118],"perceptual":[120],"dimensions":[121],"timbre":[123],"nuance":[126],"instrument-specific":[128],"performance,":[129],"cognitively":[130],"plausible":[131],"features":[132],"including":[133],"mel-frequency":[134],"cepstral":[135],"coefficients":[136],"(MFCC),":[137],"spectral":[138,141],"difference,":[139],"envelope,":[142],"are":[143],"combined":[144],"with":[145,204],"widely-used":[147],"mel-spectrogram":[148],"into":[149],"timbreenhanced":[151],"multi-channel":[152],"input":[153],"representation.":[154],"The":[155],"Relativistic":[156],"average":[157],"Generative":[158],"Adversarial":[159],"Networks":[160],"(RaGAN)":[161],"also":[163],"utilized":[164],"fast":[167],"convergence":[168],"high":[170],"stability.":[171],"We":[172],"conduct":[173],"experiments":[174],"on":[175],"bilateral":[176],"tasks":[179],"among":[180],"three":[181],"genres,":[183],"namely":[184],"piano":[185],"solo,":[186,188],"guitar":[187],"string":[190],"quartet.":[191],"Results":[192],"demonstrate":[193],"advantages":[195],"improved":[205],"sound":[206],"quality":[207],"allowing":[210],"users":[211],"manipulate":[213],"output.":[215]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}