{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T07:28:18Z","timestamp":1770276498398,"version":"3.49.0"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T00:00:00Z","timestamp":1705449600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T00:00:00Z","timestamp":1705449600000},"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":["No. 62201524, No. 62271455, No. 61971383"],"award-info":[{"award-number":["No. 62201524, No. 62271455, No. 61971383"]}],"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":["No. 62201524, No. 62271455, No. 61971383"],"award-info":[{"award-number":["No. 62201524, No. 62271455, No. 61971383"]}],"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":["No. 62201524, No. 62271455, No. 61971383"],"award-info":[{"award-number":["No. 62201524, No. 62271455, No. 61971383"]}],"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":["No. 62201524, No. 62271455, No. 61971383"],"award-info":[{"award-number":["No. 62201524, No. 62271455, No. 61971383"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1007\/s00530-023-01220-9","type":"journal-article","created":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T01:26:37Z","timestamp":1705454797000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["DiffuseRoll: multi-track multi-attribute music generation based on diffusion model"],"prefix":"10.1007","volume":"30","author":[{"given":"Hongfei","family":"Wang","sequence":"first","affiliation":[]},{"given":"Yi","family":"Zou","sequence":"additional","affiliation":[]},{"given":"Haonan","family":"Cheng","sequence":"additional","affiliation":[]},{"given":"Long","family":"Ye","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,1,17]]},"reference":[{"key":"1220_CR1","unstructured":"Yu, B., Lu, P., Wang, R., Hu, W., Tan, X., Ye, W., Zhang, S., Qin, T., Liu, T.-Y.: Museformer: Transformer with fine-and coarse-grained attention for music generation. arXiv preprint arXiv:2210.10349 (2022)"},{"key":"1220_CR2","unstructured":"Liu, J., Dong, Y., Cheng, Z., Zhang, X., Li, X., Yu, F., Sun, M.: Symphony generation with permutation invariant language model. arXiv preprint arXiv:2205.05448 (2022)"},{"key":"1220_CR3","doi-asserted-by":"crossref","unstructured":"Dong, H.-W., Hsiao, W.-Y., Yang, L.-C., Yang, Y.-H.: Musegan: Multi-track sequential generative adversarial networks for symbolic music generation and accompaniment. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.11312"},{"key":"1220_CR4","unstructured":"Ens, J., Pasquier, P.: Mmm: Exploring conditional multi-track music generation with the transformer. arXiv preprint arXiv:2008.06048 (2020)"},{"key":"1220_CR5","unstructured":"Huang, C.-Z.A., Vaswani, A., Uszkoreit, J., Shazeer, N., Hawthorne, C., Dai, A.M., Hoffman, M.D., Eck, D.: Music transformer: Generating music with long-term structure. arXiv preprint arXiv:1809.04281 (2018)"},{"key":"1220_CR6","unstructured":"Donahue, C., Mao, H.H., Li, Y.E., Cottrell, G.W., McAuley, J.: Lakhnes: Improving multi-instrumental music generation with cross-domain pre-training. arXiv preprint arXiv:1907.04868 (2019)"},{"key":"1220_CR7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-70163-9","volume-title":"Deep Learning Techniques for Music Generation","author":"J-P Briot","year":"2020","unstructured":"Briot, J.-P., Hadjeres, G., Pachet, F.-D.: Deep Learning Techniques for Music Generation, vol. 1. Springer (2020)"},{"key":"1220_CR8","first-page":"25","volume-title":"Advances in Speech and Music Technology: Computational Aspects and Applications","author":"C Hernandez-Olivan","year":"2022","unstructured":"Hernandez-Olivan, C., Beltran, J.R.: Music composition with deep learning: a review. In: Advances in Speech and Music Technology: Computational Aspects and Applications, pp. 25\u201350. Springer, Cham (2022)"},{"key":"1220_CR9","unstructured":"Ji, S., Luo, J., Yang, X.: A comprehensive survey on deep music generation: multi-level representations, algorithms, evaluations, and future directions. arXiv preprint arXiv:2011.06801 (2020)"},{"key":"1220_CR10","doi-asserted-by":"crossref","unstructured":"Albawi, S., Mohammed, T.A., Al-Zawi, S.: Understanding of a convolutional neural network. In: 2017 International Conference on Engineering and Technology (ICET), pp. 1\u20136. IEEE (2017)","DOI":"10.1109\/ICEngTechnol.2017.8308186"},{"key":"1220_CR11","doi-asserted-by":"crossref","unstructured":"Mikolov, T., Karafi\u00e1t, M., Burget, L., Cernock\u1ef3, J., Khudanpur, S.: Recurrent neural network based language model. In: Interspeech, vol. 2, pp. 1045\u20131048 (2010)","DOI":"10.21437\/Interspeech.2010-343"},{"key":"1220_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1220_CR13","doi-asserted-by":"crossref","unstructured":"Wang, S., Jiang, J.: Learning natural language inference with lstm. arXiv preprint arXiv:1512.08849 (2015)","DOI":"10.18653\/v1\/N16-1170"},{"issue":"1","key":"1220_CR14","first-page":"1","volume":"2","author":"J An","year":"2015","unstructured":"An, J., Cho, S.: Variational autoencoder based anomaly detection using reconstruction probability. Spec. Lect. IE 2(1), 1\u201318 (2015)","journal-title":"Spec. Lect. IE"},{"key":"1220_CR15","unstructured":"Simon, I., Oore, S.: Performance RNN: Generating Music with Expressive Timing and Dynamics (2017)"},{"issue":"8","key":"1220_CR16","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"1220_CR17","unstructured":"Roberts, A., Engel, J., Raffel, C., Hawthorne, C., Eck, D.: A hierarchical latent vector model for learning long-term structure in music. In: International Conference on Machine Learning, pp. 4364\u20134373. PLMR (2018)"},{"issue":"11","key":"1220_CR18","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial networks. Commun. ACM 63(11), 139\u2013144 (2020)","journal-title":"Commun. ACM"},{"key":"1220_CR19","doi-asserted-by":"crossref","unstructured":"Zhang, H., Xie, L., Qi, K.: Implement music generation with gan: a systematic review. In: 2021 International Conference on Computer Engineering and Application (ICCEA), pp. 352\u2013355. IEEE (2021)","DOI":"10.1109\/ICCEA53728.2021.00075"},{"key":"1220_CR20","unstructured":"Mogren, O.: C-rnn-gan: Continuous recurrent neural networks with adversarial training. arXiv preprint arXiv:1611.09904 (2016)"},{"key":"1220_CR21","unstructured":"Jhamtani, H., Berg-Kirkpatrick, T.: Modeling self-repetition in music generation using generative adversarial networks. In: Machine Learning for Music Discovery Workshop, ICML (2019)"},{"key":"1220_CR22","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Advances in neural information processing systems 30 (2017)"},{"key":"1220_CR23","unstructured":"Lu, P., Tan, X., Yu, B., Qin, T., Zhao, S., Liu, T.-Y.: Meloform: Generating melody with musical form based on expert systems and neural networks. arXiv preprint arXiv:2208.14345 (2022)"},{"key":"1220_CR24","unstructured":"Cao, H., Tan, C., Gao, Z., Chen, G., Heng, P.-A., Li, S.Z.: A survey on generative diffusion model. arXiv preprint arXiv:2209.02646 (2022)"},{"key":"1220_CR25","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"1220_CR26","unstructured":"Mittal, G., Engel, J., Hawthorne, C., Simon, I.: Symbolic music generation with diffusion models. arXiv preprint arXiv:2103.16091 (2021)"},{"key":"1220_CR27","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18, pp. 234\u2013241. Springer (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"1220_CR28","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-023-01220-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-023-01220-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-023-01220-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,17]],"date-time":"2024-02-17T11:33:38Z","timestamp":1708169618000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-023-01220-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,17]]},"references-count":28,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,2]]}},"alternative-id":["1220"],"URL":"https:\/\/doi.org\/10.1007\/s00530-023-01220-9","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,17]]},"assertion":[{"value":"10 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 December 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 January 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"19"}}