{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T15:39:37Z","timestamp":1792856377014,"version":"4.5.0"},"reference-count":70,"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 Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3161851","type":"journal-article","created":{"date-parts":[[2022,3,23]],"date-time":"2022-03-23T19:29:40Z","timestamp":1648063780000},"page":"3495-3508","source":"Crossref","is-referenced-by-count":99,"title":["Theme Transformer: Symbolic Music Generation With Theme-Conditioned Transformer"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3481-3117","authenticated-orcid":false,"given":"Yi-Jen","family":"Shih","sequence":"first","affiliation":[{"name":"Electrical Engineering, National Taiwan University, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8315-0762","authenticated-orcid":false,"given":"Shih-Lun","family":"Wu","sequence":"additional","affiliation":[{"name":"Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1383-4541","authenticated-orcid":false,"given":"Frank","family":"Zalkow","sequence":"additional","affiliation":[{"name":"International Audio Laboratories Erlangen, University of Erlangen-Nuremberg and Fraunhofer IIS, Erlangen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6062-7524","authenticated-orcid":false,"given":"Meinard","family":"M\u00fcller","sequence":"additional","affiliation":[{"name":"International Audio Laboratories Erlangen, University of Erlangen-Nuremberg and Fraunhofer IIS, Erlangen, Germany"}],"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":"Research Center for IT Innovation Academia Sinica, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Music transformer: Generating music with long-term structure","author":"huang","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref57","article-title":"Melodic phrase segmentation by deep neural networks","author":"guan","year":"2018"},{"key":"ref12","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1080\/09298210701563238"},{"key":"ref15","first-page":"685","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":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/319463.319470"},{"key":"ref14","article-title":"Musenet","author":"payne","year":"2019"},{"key":"ref58","article-title":"Motivic pattern mining","volume":"9051","author":"lartillot","year":"0","journal-title":"Proc Knowl Representation Intell Music Process"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-43887-6_42"},{"key":"ref52","article-title":"Closed patterns in folk music and other genres","author":"ren","year":"0","journal-title":"Proc Int Workshop Folk Music Anal"},{"key":"ref11","article-title":"A comprehensive survey on deep music generation: Multi-level representations, algorithms, evaluations, and future directions","author":"ji","year":"2020"},{"key":"ref55","first-page":"125","article-title":"Use of decision tree to detect GTTM group boundaries","author":"miura","year":"0","journal-title":"Proc Int Comput Music Conf"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3113829"},{"key":"ref54","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413671"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2990746"},{"key":"ref19","article-title":"Transformer-XL based music generation with multiple sequences of time-valued notes","author":"wu","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413721"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1076\/jnmr.31.4.321.14162"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-12976-1_18"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/1830252.1830266"},{"key":"ref45","article-title":"Transformer-based conditional variational autoencoder for controllable story generation","author":"fang","year":"2021"},{"key":"ref48","first-page":"361","article-title":"In-depth motivic analysis based on multiparametric closed pattern and cyclic sequence mining","author":"lartillot","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref47","first-page":"137","article-title":"Unfolding the potential of computational musicology","author":"volk","year":"0","journal-title":"Proc Int Conf Informat Semiotics Organisations"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1082"},{"key":"ref41","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref44","article-title":"Language models are few-shot learners","author":"brown","year":"2020"},{"key":"ref43","article-title":"CTRL: A conditional transformer language model for controllable generation","author":"keskar","year":"2019"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68765-0_2"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2020.3046491"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3019642"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3065831"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1093\/gmo\/9781561592630.article.27789"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.5334\/tismir.68"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2953194"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2737984"},{"key":"ref40","first-page":"206","article-title":"Musical style modification as an optimization problem","author":"zalkow","year":"0","journal-title":"Proc Int Comput Music Conf"},{"key":"ref35","article-title":"MELONS: Generating melody with long-term structure using transformers and structure graph","author":"zou","year":"2021"},{"key":"ref34","article-title":"Controllable deep melody generation via hierarchical music structure representation","author":"dai","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref37","article-title":"Modeling self-repetition in music generation using structured adversaries","author":"jhamtani","year":"0","journal-title":"Proc Mach Learn Media Discov Workshop"},{"key":"ref36","first-page":"725","article-title":"StructureNet: Inducing structure in generated melodies","author":"medeot","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/727"},{"key":"ref30","article-title":"BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension","author":"lewis","year":"2019"},{"key":"ref33","first-page":"4361","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":"ref32","article-title":"Computoser - rule-based, probability-driven algorithmic music composition","author":"bozhanov","year":"2014"},{"key":"ref2","first-page":"276","article-title":"Algorithmic composition of popular music","author":"elowsson","year":"0","journal-title":"Proc Int Conf Music Percep Cogn"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1017\/S1355771896000222"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-009-0303-y"},{"key":"ref38","first-page":"131","article-title":"Generating musical continuations with repetition","author":"villa","year":"0","journal-title":"Proc Sound Music Comput Conf"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/6046.944475"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17626"},{"key":"ref68","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":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16117"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-018-3849-7"},{"key":"ref26","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":"ref25","article-title":"POP909: A pop-song dataset for music arrangement generation","author":"wang","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref69","article-title":"Rethinking attention with performers","author":"choromanski","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref20","article-title":"MMM- exploring conditional multi-track music generation with the transformer","author":"ens","year":"2020"},{"key":"ref64","article-title":"Fine-tune BERT for extractive summarization","author":"liu","year":"2019"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16091"},{"key":"ref66","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref21","article-title":"Learning interpretable representation for controllable polyphonic music generation","author":"wang","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.349"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.427"},{"key":"ref27","article-title":"Music composition with deep learning: A review","author":"hernandez-olivan","year":"2021"},{"key":"ref29","first-page":"226","article-title":"A density-based algorithm for discovering clusters in large spatial databases with noise","author":"ester","year":"0","journal-title":"Proc KDD"},{"key":"ref60","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref62","article-title":"On position embeddings in BERT","author":"wang","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref61","article-title":"Rethinking the positional encoding in language pre-training","author":"ke","year":"0","journal-title":"Proc Int Conf Learn Representations"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09740506.pdf?arnumber=9740506","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:26:14Z","timestamp":1699903574000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9740506\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3161851","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}