{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T06:00:33Z","timestamp":1782280833551,"version":"3.54.5"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100010665","name":"H2020 Marie Sklodowska-Curie Actions","doi-asserted-by":"publisher","award":["765068"],"award-info":[{"award-number":["765068"]}],"id":[{"id":"10.13039\/100010665","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/taslp.2020.3019642","type":"journal-article","created":{"date-parts":[[2020,8,26]],"date-time":"2020-08-26T20:35:29Z","timestamp":1598474129000},"page":"2638-2650","source":"Crossref","is-referenced-by-count":42,"title":["Groove2Groove: One-Shot Music Style Transfer With Supervision From Synthetic Data"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6268-6445","authenticated-orcid":false,"given":"Ondrej","family":"Cifka","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Umut","family":"Simsekli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4960-0010","authenticated-orcid":false,"given":"Gael","family":"Richard","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-017-08028-4"},{"key":"ref38","article-title":"Automatic genre classification of MIDI recordings","author":"mckay","year":"2004","journal-title":"M A thesis"},{"key":"ref33","article-title":"MuseNet","author":"payne","year":"2019"},{"key":"ref32","article-title":"Performance RNN: Generating music with expressive timing and dynamics","author":"simon","year":"2017","journal-title":"Magenta Blog"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1525\/mp.2013.31.1.32"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00881"},{"key":"ref37","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref36","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref34","article-title":"Fast and accurate deep network learning by exponential linear units (ELUs)","author":"clevert","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref10","first-page":"588","article-title":"Supervised symbolic music style translation using synthetic data","author":"c\u00edfka","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval"},{"key":"ref40","article-title":"The Bodhidharma system and the results of the MIREX 2005 symbolic genre classification contest","author":"mckay","year":"0","journal-title":"Int Soc Music Inf Retrieval MIREX Session"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"594","DOI":"10.1109\/TPAMI.2006.79","article-title":"One-shot learning of object categories","volume":"28","author":"li","year":"2006","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref12","article-title":"One-shot generalization in deep generative models","author":"rezende","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref13","article-title":"Music style transfer: A position paper","author":"dai","year":"0","journal-title":"Proc 6th Int Workshop Musical Metacreation"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/652"},{"key":"ref15","first-page":"100","article-title":"Non-conformant harmonization: The real book in the style of Take 6","author":"pachet","year":"0","journal-title":"Proc Int Certified Career Coach"},{"key":"ref16","article-title":"Style imitation and chord invention in polyphonic music with exponential families","author":"hadjeres","year":"2016"},{"key":"ref17","first-page":"747","article-title":"MIDI-VAE: Modeling dynamics and instrumentation of music with applications to style transfer","author":"brunner","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI.2018.00123"},{"key":"ref19","first-page":"740","article-title":"Transferring the style of homophonic music using recurrent neural networks and autoregressive models","author":"lu","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval"},{"key":"ref28","first-page":"197","article-title":"Cover song synthesis by analogy","author":"tralie","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval"},{"key":"ref4","article-title":"A universal music translation network","author":"mor","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref27","first-page":"350","article-title":"Let it Bee – Towards NMF-inspired audio mosaicing","author":"driedger","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval"},{"key":"ref3","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with Tacotron","volume":"80","author":"skerry-ryan","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref29","first-page":"39","article-title":"Musical mosaicing","author":"zils","year":"0","journal-title":"Proc COST G-6 Conf Digital Audio Effects (DAFX-01)"},{"key":"ref5","first-page":"6830","article-title":"Style transfer from non-parallel text by cross-alignment","author":"shen","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref8","article-title":"Neural translation of musical style","author":"malik","year":"2017"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.126"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682331"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33011061"},{"key":"ref22","article-title":"DeepBach: A steerable model for Bach Chorales generation","author":"hadjeres","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref21","article-title":"TimbreTron: A WaveNet(CycleGAN(CQT(Audio))) pipeline for musical timbre transfer","author":"huang","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref42","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref24","article-title":"Encoding musical style with transformer autoencoders","author":"choi","year":"2019"},{"key":"ref41","article-title":"General MIDI system level 1","year":"1991","journal-title":"MIDI manufacturer association"},{"key":"ref23","first-page":"211","article-title":"Counterpoint by convolution","author":"huang","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval"},{"key":"ref44","first-page":"311","article-title":"Coupled recurrent models for polyphonic music composition","author":"thickstun","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461711"},{"key":"ref43","article-title":"A hierarchical latent vector model for learning long-term structure in music","author":"roberts","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937261"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8938144\/09178446.pdf?arnumber=9178446","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:31:22Z","timestamp":1651080682000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9178446\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/taslp.2020.3019642","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}