{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T09:15:48Z","timestamp":1771233348595,"version":"3.50.1"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T00:00:00Z","timestamp":1767571200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T00:00:00Z","timestamp":1768867200000},"content-version":"vor","delay-in-days":15,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1007\/s40747-025-02210-2","type":"journal-article","created":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T16:07:35Z","timestamp":1767629255000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A chord-controlled transformer for controllable and coherent music generation"],"prefix":"10.1007","volume":"12","author":[{"given":"Zhiqiang","family":"Gao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,5]]},"reference":[{"key":"2210_CR1","unstructured":"Agostinelli A, Denk TI, Borsos Z, et al. (2023). Musiclm: Generating music from text. arXiv preprint arXiv:2301.11325."},{"key":"2210_CR2","unstructured":"von R\u00fctte D, Biggio L, Kilcher Y, et al. (2023). FIGARO: Controllable music generation using learned and expert features. The Eleventh International Conference on Learning Representations."},{"key":"2210_CR3","first-page":"1376","volume":"35","author":"B Yu","year":"2022","unstructured":"Yu B, Lu P, Wang R et al (2022) Museformer: Transformer with fine-and coarse-grained attention for music generation. Adv Neural Inf Process Syst 35:1376\u20131388","journal-title":"Adv Neural Inf Process Syst"},{"key":"2210_CR4","doi-asserted-by":"crossref","unstructured":"Huang Y-S, & Yang Y-H (2020). Pop Music Transformer: Beat-based modeling and generation of expressive pop piano compositions. Proceedings of ACM Multimedia (MM \u201920). (Also: arXiv:2002.00212).","DOI":"10.1145\/3394171.3413671"},{"key":"2210_CR5","unstructured":"Dhariwal P, Jun H, Payne C, Kim JW, Radford A, & Sutskever I (2020). Jukebox: A generative model for music. OpenAI Technical Report. (online paper)."},{"key":"2210_CR6","unstructured":"Copet J, Kreuk F, Gat I, Remez T, Kant D, Synnaeve G, Adi Y, D\u00e9fossez A (2023). Simple and controllable music generation (MusicGen). Advances in Neural Information Processing Systems (NeurIPS 2023). (arXiv:2306.05284)."},{"key":"2210_CR7","doi-asserted-by":"crossref","unstructured":"Borsos Z, Sharifi M, Vincent D, et al. (2022). AudioLM: A language modeling approach to audio generation. arXiv preprint arXiv:2209.03143.","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"2210_CR8","unstructured":"Roberts A, Engel J, Raffel C, et al. (2018). A hierarchical latent vector model for learning long-term structure in music. Proceedings of the International Conference on Machine Learning (PMLR), 4364\u20134373."},{"key":"2210_CR9","unstructured":"Huang CZA, Vaswani A, Uszkoreit J, et al. (2018). Music Transformer. arXiv preprint arXiv:1809.04281."},{"key":"2210_CR10","doi-asserted-by":"crossref","unstructured":"Dai Z, Yang Z, Yang Y, et al. (2019). Transformer-XL: Attentive language models beyond a fixed-length context. arXiv preprint arXiv:1901.02860.","DOI":"10.18653\/v1\/P19-1285"},{"key":"2210_CR11","doi-asserted-by":"crossref","unstructured":"Hsiao W-Y, Liu J-Y, Yeh Y-C, & Yang Y-H (2021). Compound Word Transformer: Learning to \u00a0\u00a0compose\u00a0\u00a0 full-song\u00a0 music over dynamic directed hypergraphs. arXiv preprint arXiv:2101.02402.","DOI":"10.1609\/aaai.v35i1.16091"},{"key":"2210_CR12","doi-asserted-by":"crossref","unstructured":"Zeng M, Tan X, Wang R, Ju Z, Qin T, & Liu T-Y (2021). MusicBERT: Symbolic music understanding with large-scale pre-training. arXiv preprint arXiv:2106.05630.","DOI":"10.18653\/v1\/2021.findings-acl.70"},{"key":"2210_CR13","unstructured":"Wang Z, Min L, Xia G (2024). Whole-song hierarchical generation of symbolic music using cascaded diffusion models. arXiv preprint arXiv:2405.09901.3"},{"issue":"4","key":"2210_CR14","doi-asserted-by":"publisher","first-page":"27","DOI":"10.2307\/3679551","volume":"13","author":"PM Todd","year":"1989","unstructured":"Todd PM (1989) A connectionist approach to algorithmic composition. Comput Music J 13(4):27\u201343","journal-title":"Comput Music J"},{"key":"2210_CR15","unstructured":"Waite, E. (2016). Generating long-term structure in songs and stories. Magenta Blog Post, 15(4)."},{"key":"2210_CR16","unstructured":"Hadjeres G & Nielsen F (2017). Interactive music generation with positional constraints using anticipation-RNNs. arXiv preprint arXiv:1709.06404."},{"key":"2210_CR17","first-page":"5998","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani A, Shazeer N, Parmar N et al (2017) Attention is all you need. Adv Neural Inf Process Syst 30:5998\u20136008","journal-title":"Adv Neural Inf Process Syst"},{"key":"2210_CR18","doi-asserted-by":"publisher","first-page":"3495","DOI":"10.1109\/TMM.2022.3161851","volume":"25","author":"YJ Shih","year":"2022","unstructured":"Shih YJ, Wu SL, Zalkow F et al (2022) Theme transformer: symbolic music generation with theme-conditioned transformer. IEEE Trans Multimed 25:3495\u20133508","journal-title":"IEEE Trans Multimed"},{"key":"2210_CR19","doi-asserted-by":"crossref","unstructured":"Zhang X, Wang K, Hu X, et al. (2021). Structure-enhanced pop music generation via harmony-aware learning. arXiv preprint arXiv:2109.06441.","DOI":"10.1145\/3503161.3548084"},{"key":"2210_CR20","doi-asserted-by":"crossref","unstructured":"Jiang J, Xia GG, Carlton DB, et al. (2020). Transformer VAE: A hierarchical model for structure-aware and interpretable music representation learning. ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 516\u2013520.","DOI":"10.1109\/ICASSP40776.2020.9054554"},{"key":"2210_CR21","unstructured":"Dai S, Jin Z, Gomes C, Dannenberg RB (2021). Controllable deep melody generation via hierarchical music structure representation (MusicFrameworks). Proceedings of the 22nd International Society for Music Information Retrieval Conference (ISMIR 2021)."},{"key":"2210_CR22","doi-asserted-by":"publisher","unstructured":"Raffel C (2016). Learning-Based Methods for Comparing Sequences, with Applications to Audio-to-MIDI Alignment and Matching. Ph.D. dissertation, Columbia University. https:\/\/doi.org\/10.7916\/D8N58MHV.","DOI":"10.7916\/D8N58MHV"},{"key":"2210_CR23","doi-asserted-by":"publisher","unstructured":"Wang Z, Chen K, Jiang J, Zhang Y, Xu M, Dai S, Gu X, Xia G. (2020) \u201cPOP909: A Pop-song Dataset for Music Arrangement Generation,\u201d in Proc. 21st Int. Society for Music Information Retrieval Conf. (ISMIR), Montr\u00e9al, Canada (virtual). https:\/\/doi.org\/10.48550\/arXiv.2008.07142.","DOI":"10.48550\/arXiv.2008.07142"}],"container-title":["Complex & Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-025-02210-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-025-02210-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-025-02210-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T08:24:03Z","timestamp":1771230243000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-025-02210-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,5]]},"references-count":23,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["2210"],"URL":"https:\/\/doi.org\/10.1007\/s40747-025-02210-2","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"value":"2199-4536","type":"print"},{"value":"2198-6053","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,5]]},"assertion":[{"value":"15 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval and informed consent statements"}}],"article-number":"89"}}