{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T23:19:39Z","timestamp":1769555979114,"version":"3.49.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T00:00:00Z","timestamp":1660521600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T00:00:00Z","timestamp":1660521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076077"],"award-info":[{"award-number":["62076077"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61903090"],"award-info":[{"award-number":["61903090"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangxi Scientific Research Basic Ability Enhancement Program for Young and Middle-aged Teachers","award":["2022KY0183"],"award-info":[{"award-number":["2022KY0183"]}]},{"name":"Guangxi Science and Technology Major Project","award":["AA22068057"],"award-info":[{"award-number":["AA22068057"]}]},{"name":"Guangxi Postdoctoral Special Foundation"},{"DOI":"10.13039\/501100021188","name":"Guangxi Key Laboratory of Electrochemical and Magnetochemical Functional Materials","doi-asserted-by":"publisher","award":["XJ21KT32"],"award-info":[{"award-number":["XJ21KT32"]}],"id":[{"id":"10.13039\/501100021188","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2023,5]]},"DOI":"10.1007\/s10489-022-04049-3","type":"journal-article","created":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T10:02:59Z","timestamp":1660557779000},"page":"10130-10148","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Bar transformer: a hierarchical model for learning long-term structure and generating impressive pop music"],"prefix":"10.1007","volume":"53","author":[{"given":"Yang","family":"Qin","sequence":"first","affiliation":[]},{"given":"Huiming","family":"Xie","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4963-3883","authenticated-orcid":false,"given":"Shuxue","family":"Ding","sequence":"additional","affiliation":[]},{"given":"Benying","family":"Tan","sequence":"additional","affiliation":[]},{"given":"Yujie","family":"Li","sequence":"additional","affiliation":[]},{"given":"Bin","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Mao","family":"Ye","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,8,15]]},"reference":[{"issue":"1","key":"4049_CR1","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1007\/s00521-020-05399-0","volume":"33","author":"JP Briot","year":"2021","unstructured":"Briot JP (2021) From artificial neural networks to deep learning for music generation: history, concepts and trends. Neural Comput Applic 33(1):39\u201365. https:\/\/doi.org\/10.1007\/s00521-020-05399-0","journal-title":"Neural Comput Applic"},{"issue":"4","key":"4049_CR2","doi-asserted-by":"publisher","first-page":"981","DOI":"10.1007\/s00521-018-3813-6","volume":"32","author":"JP Briot","year":"2020","unstructured":"Briot JP, Pachet F (2020) Deep learning for music generation: challenges and directions. Neural Comput Applic 32(4):981\u2013993. https:\/\/doi.org\/10.1007\/s00521-018-3813-6","journal-title":"Neural Comput Applic"},{"key":"4049_CR3","unstructured":"Brown T, Mann B, Ryder N et al (2020) Language models are few-shot learners. In: Advances in neural information processing systems (NeurIPS), pp 1877\u20131901"},{"key":"4049_CR4","doi-asserted-by":"publisher","unstructured":"Brunner G, Wang Y, Wattenhofer R et al (2017) Jambot: Music theory aware chord based generation of polyphonic music with lstms. In: 2017 IEEE 29th international conference on tools with artificial intelligence (ICTAI), IEEE, pp 519\u2013526. https:\/\/doi.org\/10.1109\/ICTAI.2017.00085","DOI":"10.1109\/ICTAI.2017.00085"},{"key":"4049_CR5","unstructured":"Brunner G, Konrad A, Wang Y et al (2018) Midi-vae: Modeling dynamics and instrumentation of music with applications to style transfer. In: Proceedings of the 19th international society for music information retrieval conference(ISMIR), pp 747\u2013754"},{"key":"4049_CR6","unstructured":"Choi K, Hawthorne C, Simon I et al (2020) Encoding musical style with transformer autoencoders. In: International conference on machine learning(ICML), pp 1899\u20131908"},{"key":"4049_CR7","unstructured":"Chu H, Urtasun R, Fidler S (2017) Song from pi: a musically plausible network for pop music generation. In: 5th International conference on learning representations(ICLR)"},{"key":"4049_CR8","doi-asserted-by":"crossref","unstructured":"Chuan CH, Herremans D (2018) Modeling temporal tonal relations in polyphonic music through deep networks with a novel image-based representation. In: Proceedings of the AAAI conference on artificial intelligence(AAAI), pp 2159\u20132166","DOI":"10.1609\/aaai.v32i1.11880"},{"key":"4049_CR9","unstructured":"Chung J, Ahn S, Bengio Y (2017) Hierarchical multiscale recurrent neural networks. In: 5th International conference on learning representations(ICLR)"},{"key":"4049_CR10","doi-asserted-by":"publisher","unstructured":"Devlin J, Chang MW, Lee K et al (2019) Bert: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the north american chapter of the association for computational linguistics: human language technologies (NAACL-HLT), pp 4171\u20134186. https:\/\/doi.org\/10.18653\/v1\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"4049_CR11","unstructured":"Dong HW, Yang YH (2018) Convolutional generative adversarial networks with binary neurons for polyphonic music generation. In: Proceedings of the 19th international society for music information retrieval conference (ISMIR), pp 190\u2013196"},{"key":"4049_CR12","doi-asserted-by":"crossref","unstructured":"Dong HW, Hsiao WY, Yang LC et al (2018) Musegan: multi-track sequential generative adversarial networks for symbolic music generation and accompaniment. In: Proceedings of the AAAI conference on artificial intelligence(AAAI), pp 34\u201341","DOI":"10.1609\/aaai.v32i1.11312"},{"key":"4049_CR13","doi-asserted-by":"publisher","first-page":"115,236","DOI":"10.1016\/j.eswa.2021.115236","volume":"182","author":"M Furner","year":"2021","unstructured":"Furner M, Islam MZ, Li CT (2021) Knowledge discovery and visualisation framework using machine learning for music information retrieval from broadcast radio data. Expert Syst Appl 182:115,236. https:\/\/doi.org\/10.1016\/j.eswa.2021.115236","journal-title":"Expert Syst Appl"},{"key":"4049_CR14","doi-asserted-by":"crossref","unstructured":"Gao T, Cui Y, Ding F (2021) Seqvae: sequence variational autoencoder with policy gradient. Appl Intell, pp 1\u20138","DOI":"10.1007\/s10489-021-02374-7"},{"key":"4049_CR15","doi-asserted-by":"publisher","unstructured":"Graves A, Mohamed AR, Hinton G (2013) Speech recognition with deep recurrent neural networks. In: 2013 IEEE International conference on acoustics, speech and signal processing, IEEE, pp 6645\u20136649 https:\/\/doi.org\/10.1109\/ICASSP.2013.6638947","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"4049_CR16","doi-asserted-by":"publisher","unstructured":"Guo Z, Dimos M, Dorien H (2021) Hierarchical recurrent neural networks for conditional melody generation with long-term structure. In: International joint conference on neural networks(IJCNN), pp 1\u20138. https:\/\/doi.org\/10.1109\/IJCNN52387.2021.9533493https:\/\/doi.org\/10.1109\/IJCNN52387.2021.9533493","DOI":"10.1109\/IJCNN52387.2021.9533493 10.1109\/IJCNN52387.2021.9533493"},{"key":"4049_CR17","unstructured":"Hadjeres G, Pachet F, Nielsen F (2017) Deepbach: a steerable model for bach chorales generation. In: International conference on machine learning(ICML), pp 1362\u20131371"},{"key":"4049_CR18","unstructured":"Huang CZA, Vaswani A, Uszkoreit J et al (2019) Music transformer: generating music with long-term structure. In: 7th International conference on learning representations(ICLR)"},{"key":"4049_CR19","doi-asserted-by":"crossref","unstructured":"Huang YS, Yang YH (2020) Pop music transformer: Beat-based modeling and generation of expressive pop piano compositions. In: Proceedings of the 28th ACM international conference on multimedia, pp 1180\u20131188","DOI":"10.1145\/3394171.3413671"},{"key":"4049_CR20","unstructured":"Kingma D, Ba J (2015) Adam: a method for stochastic optimization. In: 3rd International conference on learning representations(ICLR)"},{"key":"4049_CR21","unstructured":"Liang FT, Gotham M, Johnson M et al (2017) Automatic stylistic composition of bach chorales with deep lstm. In: Proceedings of the 18th international society for music information retrieval conference(ISMIR), pp 449\u2013456"},{"key":"4049_CR22","doi-asserted-by":"crossref","unstructured":"Ockelford A (2017) Repetition in music: Theoretical and metatheoretical perspectives. Routledge","DOI":"10.4324\/9781315088884"},{"key":"4049_CR23","unstructured":"Oord AVD, Dieleman S, Zen H et al (2016) Wavenet: a generative model for raw audio. In: The 9th ISCA speech synthesis workshop, pp 125"},{"key":"4049_CR24","doi-asserted-by":"publisher","unstructured":"Pappagari R, Zelasko P, Villalba J et al (2019) Hierarchical transformers for long document classification. In: 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), IEEE, pp 838-844. https:\/\/doi.org\/10.1109\/ASRU46091.2019.9003958https:\/\/doi.org\/10.1109\/ASRU46091.2019.9003958","DOI":"10.1109\/ASRU46091.2019.9003958 10.1109\/ASRU46091.2019.9003958"},{"key":"4049_CR25","unstructured":"Paszke A, Gross S, Massa F et al (2019) Pytorch: An imperative style, high-performance deep learning library. In: Advances in neural information processing systems(NeurIPS), pp 8024\u20138035"},{"key":"4049_CR26","unstructured":"Pauwels J, O\u2019Hanlon K, G\u00f3mez E et al (2019) 20 years of automatic chord recognition from audio. In: Proceedings of the 20th International society for music information retrieval conference (ISMIR), pp 54\u201363"},{"key":"4049_CR27","unstructured":"Payne C (2019) Musenet. https:\/\/openaicom\/blog\/musenet"},{"key":"4049_CR28","unstructured":"Roberts A, Engel J, Raffel C et al (2018) A hierarchical latent vector model for learning long-term structure in music. In: International conference on machine learning(ICML), pp 4364\u20134373"},{"key":"4049_CR29","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.knosys.2017.11.027","volume":"142","author":"C Roig","year":"2018","unstructured":"Roig C, Tard\u00f3n LJ, Barbancho I et al (2018) A non-homogeneous beat-based harmony markov model. Knowl-Based Syst 142:85\u201394. https:\/\/doi.org\/10.1016\/j.knosys.2017.11.027","journal-title":"Knowl-Based Syst"},{"key":"4049_CR30","doi-asserted-by":"crossref","unstructured":"Shaw P, Uszkoreit J, Vaswani A (2018) Self-attention with relative position representations. In: Proceedings of the 2018 conference of the north american chapter of the association for computational linguistics: human language technologies (NAACL-HLT), pp 464\u2013468","DOI":"10.18653\/v1\/N18-2074"},{"key":"4049_CR31","unstructured":"Vaswani A, Shazeer N, Parmar N et al (2017) Attention is all you need. In: Advances in neural information processing systems(NeurIPS), pp 5998\u20136008"},{"key":"4049_CR32","unstructured":"Villegas R, Yang J, Zou Y et al (2017) Learning to generate long-term future via hierarchical prediction. In: International conference on machine learning(ICML), pp 3560\u20133569"},{"key":"4049_CR33","unstructured":"Waite E (2016) Project magenta: generating long-term structure in songs and stories. https:\/\/magenta.tensorflow.org\/2016\/07\/15\/lookback-rnn-attention-rnn\/"},{"key":"4049_CR34","unstructured":"Wang Z, Zhang Y, Zhang Y et al (2020) Pianotree vae: Structured representation learning for polyphonic music. In: Proceedings of the 21th international society for music information retrieval conference(ISMIR), pp 368\u2013375"},{"issue":"6","key":"4049_CR35","doi-asserted-by":"publisher","first-page":"2749","DOI":"10.1109\/TCYB.2019.2953194","volume":"50","author":"J Wu","year":"2020","unstructured":"Wu J, Hu C, Wang Y et al (2020) A hierarchical recurrent neural network for symbolic melody generation. IEEE Trans Cybern 50(6):2749\u20132757. https:\/\/doi.org\/10.1109\/TCYB.2019.2953194","journal-title":"IEEE Trans Cybern"},{"key":"4049_CR36","doi-asserted-by":"publisher","first-page":"103,303","DOI":"10.1016\/j.artint.2020.103303","volume":"286","author":"J Wu","year":"2020","unstructured":"Wu J, Liu X, Hu X et al (2020) Popmnet: Generating structured pop music melodies using neural networks. Artif Intell 286:103,303. https:\/\/doi.org\/10.1016\/j.artint.2020.103303","journal-title":"Artif Intell"},{"key":"4049_CR37","unstructured":"Yang LC, Chou SY, Yang YH (2017) Midinet: A convolutional generative adversarial network for symbolic-domain music generation. In: Proceedings of the 18th International society for music information retrieval conference(ISMIR), pp 324\u2013331"},{"key":"4049_CR38","doi-asserted-by":"publisher","first-page":"1328","DOI":"10.1109\/TASLP.2020.2987130","volume":"28","author":"A Ycart","year":"2020","unstructured":"Ycart A, Benetos E (2020) Learning and evaluation methodologies for polyphonic music sequence prediction with lstms. EEE\/ACM Trans Audio, Speech, Language Process 28:1328\u20131341","journal-title":"EEE\/ACM Trans Audio, Speech, Language Process"},{"key":"4049_CR39","doi-asserted-by":"publisher","unstructured":"Zhang N (2020) Learning adversarial transformer for symbolic music generation. IEEE Trans Neural Netw Learn Syst, pp 1\u201310. https:\/\/doi.org\/10.1109\/TNNLS.2020.2990746","DOI":"10.1109\/TNNLS.2020.2990746"},{"key":"4049_CR40","doi-asserted-by":"crossref","unstructured":"Zhu H, Liu Q, Yuan NJ et al (2018) Xiaoice band: a melody and arrangement generation framework for pop music. In: Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining, pp 2837\u20132846","DOI":"10.1145\/3219819.3220105"},{"issue":"5","key":"4049_CR41","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3374915","volume":"14","author":"H Zhu","year":"2020","unstructured":"Zhu H, Liu Q, Yuan NJ et al (2020) Pop music generation: from melody to multi-style arrangement. ACM Trans Knowl Discov 14(5):1\u201331. https:\/\/doi.org\/10.1145\/3374915","journal-title":"ACM Trans Knowl Discov"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-04049-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-022-04049-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-04049-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,19]],"date-time":"2023-05-19T11:38:52Z","timestamp":1684496332000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-022-04049-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,15]]},"references-count":41,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2023,5]]}},"alternative-id":["4049"],"URL":"https:\/\/doi.org\/10.1007\/s10489-022-04049-3","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,15]]},"assertion":[{"value":"27 July 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 August 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}