{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T02:42:55Z","timestamp":1790995375730,"version":"4.1.0"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2023.3270726","type":"journal-article","created":{"date-parts":[[2023,5,23]],"date-time":"2023-05-23T14:46:14Z","timestamp":1684853174000},"page":"1953-1967","source":"Crossref","is-referenced-by-count":58,"title":["MuseMorphose: Full-Song and Fine-Grained Piano Music Style Transfer With One Transformer VAE"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8315-0762","authenticated-orcid":false,"given":"Shih-Lun","family":"Wu","sequence":"first","affiliation":[{"name":"Taiwan AI Labs, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2724-6161","authenticated-orcid":false,"given":"Yi-Hsuan","family":"Yang","sequence":"additional","affiliation":[{"name":"Taiwan AI Labs, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-018-3849-7"},{"key":"ref13","article-title":"Auto-encoding variational bayes","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/319463.319472"},{"key":"ref12","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1041"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref58","first-page":"7298","article-title":"Unsupervised text style transfer using language models as discriminators","author":"yang","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref53","article-title":"Convolutional generative adversarial networks with binary neurons for polyphonic music generation","author":"dong","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref52","first-page":"1691","article-title":"Generative pretraining from pixels","author":"chen","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref55","article-title":"Towards characterisation of music via rhythmic patterns","author":"dixon","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref11","article-title":"A hierarchical latent vector model for learning long-term structure in music","author":"roberts","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref54","article-title":"Realtime chord recognition of musical sound: A system using common Lisp","author":"fujishima","year":"0","journal-title":"Proc Int Comput Music Conf"},{"key":"ref10","article-title":"LakhNES: Improving multi-instrumental music generation with cross-domain pre-training","author":"donahue","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref17","article-title":"The jazz transformer on the front line: Exploring the shortcomings of AI-composed music through quantitative measures","author":"wu","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref16","article-title":"MuseNet","author":"payne","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref18","article-title":"Automatic composition of guitar tabs by Transformers and groove modeling","author":"chen","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref51","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref50","article-title":"Insertion Transformer: Flexible sequence generation via insertion operations","author":"stern","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref46","first-page":"2397","article-title":"Avoiding latent variable collapse with generative skip models","author":"dieng","year":"0","journal-title":"Proc 22nd Int Conf Artif Intell Statist"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K16-1002"},{"key":"ref48","article-title":"Cyclical annealing schedule: A simple approach to mitigating KL vanishing","author":"fu","year":"0","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics - Hum Lang Technol"},{"key":"ref47","article-title":"Improving variational inference with inverse autoregressive flow","author":"kingma","year":"2016"},{"key":"ref42","article-title":"Rethinking attention with performers","author":"choromanski","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref41","first-page":"5156","article-title":"Transformers are RNNs: Fast autoregressive Transformers with linear attention","author":"katharopoulos","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref44","first-page":"3745","article-title":"Ladder variational autoencoders","author":"s\u00f8nderby","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref43","article-title":"beta-VAE: Learning basic visual concepts with a constrained variational framework","author":"higgins","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref49","article-title":"CTRL: A conditional transformer language model for controllable generation","author":"keskar","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref7","first-page":"1180","article-title":"Pop Music Transformer: Generating music with rhythm and harmony","author":"huang","year":"0","journal-title":"Proc 28th ACM Int Conf Multimedia"},{"key":"ref9","article-title":"Music Transformer: Generating music with long-term structure","author":"huang","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref4","article-title":"A comprehensive survey on deep music generation: Multi-level representations, algorithms, evaluations, and future directions","author":"ji","year":"2020"},{"key":"ref3","article-title":"Muse: GAN: Multi-track sequential generative adversarial networks for symbolic music generation and accompaniment","author":"dong","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref6","article-title":"This time with feeling: Learning expressive musical performance","author":"oore","year":"2018"},{"key":"ref5","article-title":"Onsets and frames: Dual-objective piano transcription","author":"hawthorne","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref40","article-title":"Relative positional encoding for Transformers with linear complexity","author":"liutkus","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/727"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref36","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2018.2820691"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11330"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.378"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.3032373"},{"key":"ref2","first-page":"1362","article-title":"DeepBach: A steerable model for bach chorales generation","author":"hadjeres","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref1","author":"hiller","year":"1959","journal-title":"Experimental Music Composition with an Electronic Computer"},{"key":"ref39","article-title":"On position embeddings in bert","author":"wang","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref38","article-title":"Rethinking the positional encoding in language pre-training","author":"ke","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref68","article-title":"Neural discrete representation learning","author":"oord","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref23","first-page":"670","article-title":"Attributes-aware deep music transformation","author":"kawai","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413721"},{"key":"ref25","first-page":"1899","article-title":"Encoding musical style with transformer autoencoders","author":"choi","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref64","first-page":"31","article-title":"An estimate of an upper bound for the entropy of english","volume":"18","author":"brown","year":"1992","journal-title":"Comput Linguistics"},{"key":"ref20","article-title":"Music FaderNets: Controllable music generation based on high-level features via low-level feature modelling","author":"tan","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2973795"},{"key":"ref66","article-title":"Zero-shot text-to-image generation","author":"ramesh","year":"2021"},{"key":"ref22","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 Conf"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1198"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2017.8280895"},{"key":"ref28","article-title":"Language models are unsupervised multitask learners","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16091"},{"key":"ref29","article-title":"BERT: Pre-training of deep bidirectional Transformers for language understanding","author":"devlin","year":"0","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref60","article-title":"Multiple-attribute text rewriting","author":"lample","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref62","article-title":"The curious case of neural text degeneration","author":"holtzman","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1601"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10130842.pdf?arnumber=10130842","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,19]],"date-time":"2023-06-19T14:18:15Z","timestamp":1687184295000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10130842\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3270726","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}