{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T10:58:10Z","timestamp":1781089090279,"version":"3.54.1"},"reference-count":29,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T00:00:00Z","timestamp":1780876800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>Controllable symbolic music generation must preserve a reference melody while remaining responsive to style prompts. Existing hierarchical diffusion systems typically reuse a shared condition vector across harmony, rhythm, and timbre stages, which can entangle stylistic factors and weaken melody preservation. We present HCDMG++, a hierarchical diffusion framework that addresses these two limitations through stage-aware style routing and differentiable melody regularization. The routing module uses a residual multi-layer perceptron (MLP) with zero-initialized scalar gates to project text-derived style embeddings into harmony-, rhythm-, and timbre-specific subspaces, whereas the regularization branch aligns soft pitch histograms and contour trajectories with the conditioning melody during training without breaking the differentiable computation graph. We evaluate the integrated system on a 384-sample benchmark covering four melodies, eight styles, four random seeds, and three denoising budgets, supplemented by a matched legacy-compatible reference and inference-time component ablation that contrasts legacy behavior, silenced gates, an automated uniform gamma routing sweep, and the full forward pass. HCDMG++ produces valid four-track outputs in all 384 runs, reaches a peak pitch histogram similarity score of 0.508 under a 64-step budget, and improves pitch histogram alignment over Legacy-HCDMG by roughly two orders of magnitude on the matched slice, while attaining a positive Fisher-style style separability score where the legacy benchmark is too sparse to support one. These results indicate that stage-specific conditioning and differentiable structural guidance jointly improve controllability in symbolic music diffusion, while also exposing the remaining limitations in long-form generalization and perceptual validation, which motivate the future work outlined at the end of this paper.<\/jats:p>","DOI":"10.3390\/info17060568","type":"journal-article","created":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T00:43:54Z","timestamp":1780965834000},"page":"568","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Controllable Symbolic Music Generation via Stage-Aware Style Routing and Differentiable Melody Regularization"],"prefix":"10.3390","volume":"17","author":[{"given":"Xuanfei","family":"Zhou","sequence":"first","affiliation":[{"name":"Preschool College, Changsha Normal University, Changsha 410100, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yinxuan","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha 410073, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sining","family":"Han","sequence":"additional","affiliation":[{"name":"College of Systems Engineering, National University of Defense Technology, Changsha 410073, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1138-2882","authenticated-orcid":false,"given":"Jiangyao","family":"Bai","sequence":"additional","affiliation":[{"name":"College of Systems Engineering, National University of Defense Technology, Changsha 410073, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qianzhen","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Systems Engineering, National University of Defense Technology, Changsha 410073, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lailong","family":"Luo","sequence":"additional","affiliation":[{"name":"College of Systems Engineering, National University of Defense Technology, Changsha 410073, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Systems Engineering, National University of Defense Technology, Changsha 410073, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,8]]},"reference":[{"key":"ref_1","unstructured":"Min, L., Jiang, J., Xia, G., and Zhao, J. (2023, January 5\u20139). Polyffusion: A Diffusion Model for Polyphonic Score Generation with Internal and External Controls. Proceedings of the 24th International Society for Music Information Retrieval Conference (ISMIR), Milan, Italy."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Lv, A., Tan, X., Lu, P., Ye, W., Zhang, S., Bian, J., and Yan, R. (2023). GETMusic: Generating Any Music Tracks with a Unified Representation and Diffusion Framework. arXiv.","DOI":"10.24963\/ijcai.2024\/1127"},{"key":"ref_3","unstructured":"Lu, P., Xu, X., Kang, C., Yu, B., Xing, C., Tan, X., and Bian, J. (2023). MuseCoco: Generating Symbolic Music from Text. arXiv."},{"key":"ref_4","unstructured":"Ho, J., Jain, A., and Abbeel, P. (2020, January 6\u201312). Denoising Diffusion Probabilistic Models. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Virtual."},{"key":"ref_5","unstructured":"Mittal, G., Engel, J., Hawthorne, C., and Simon, I. (2021). Symbolic Music Generation with Diffusion Models. arXiv."},{"key":"ref_6","unstructured":"Wang, Z., Min, L., and Xia, G. (2024). Whole-Song Hierarchical Generation of Symbolic Music Using Cascaded Diffusion Models. arXiv."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Yuan, R., Lin, H., Wang, Y., Tian, Z., Wu, S., Shen, T., Zhang, G., Wu, Y., Liu, C., and Zhou, Z. (2024). ChatMusician: Understanding and Generating Music Intrinsically with LLM. arXiv.","DOI":"10.18653\/v1\/2024.findings-acl.373"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2638","DOI":"10.1109\/TASLP.2020.3019642","article-title":"Groove2Groove: One-Shot Music Style Transfer with Supervision from Synthetic Data","volume":"28","author":"Richard","year":"2020","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"ref_9","unstructured":"Dhariwal, P., Jun, H., Payne, C., Kim, J.W., Radford, A., and Sutskever, I. (2020). Jukebox: A Generative Model for Music. arXiv."},{"key":"ref_10","unstructured":"Huang, Q., Park, D.S., Wang, T., Denk, T.I., Ly, A., Chen, N., Zhang, Z., Zhang, Z., Yu, J., and Frank, C. (2023). Noise2Music: Text-conditioned Music Generation with Diffusion Models. arXiv."},{"key":"ref_11","unstructured":"Huang, Y., Ghatare, A., Liu, Y., Hu, Z., Zhang, Q., Shama Sastry, C., Gururani, S., Oore, S., and Yue, Y. (2024, January 21\u201327). Symbolic Music Generation with Non-Differentiable Rule Guided Diffusion. Proceedings of the International Conference on Machine Learning (ICML), Vienna, Austria."},{"key":"ref_12","unstructured":"Huang, C.-Z.A., Vaswani, A., Uszkoreit, J., Simon, I., Hawthorne, C., Dai, A., Hoffman, M.D., Dinculescu, M., and Eck, D. (2019, January 6\u20139). Music Transformer: Generating Music with Long-Term Structure. Proceedings of the International Conference on Learning Representations (ICLR), New Orleans, LA, USA."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Hsiao, W.-Y., Liu, J.-Y., Yeh, Y.-C., and Yang, Y.-H. (2021, January 2\u20139). Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphs. Proceedings of the AAAI Conference on Artificial Intelligence, Virtual.","DOI":"10.1609\/aaai.v35i1.16091"},{"key":"ref_14","unstructured":"Agostinelli, A., Denk, T.I., Borsos, Z., Engel, J., Verzetti, M., Caillon, A., Huang, Q., Jansen, A., Roberts, A., and Tagliasacchi, M. (2023). MusicLM: Generating Music from Text. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., and Aila, T. (2019, January 15\u201320). A Style-Based Generator Architecture for Generative Adversarial Networks. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Perez, E., Strub, F., De Vries, H., Dumoulin, V., and Courville, A. (2018, January 2\u20137). FiLM: Visual Reasoning with a General Conditioning Layer. Proceedings of the AAAI Conference on Artificial Intelligence, New Orleans, LA, USA.","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref_17","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017, January 4\u20139). Attention Is All You Need. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Long Beach, CA, USA."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Huang, Y.-S., and Yang, Y.-H. (2020, January 12\u201316). Pop Music Transformer: Beat-Based Modeling and Generation of Expressive Pop Piano Compositions. Proceedings of the 28th ACM International Conference on Multimedia (ACM MM), Seattle, WA, USA.","DOI":"10.1145\/3394171.3413671"},{"key":"ref_19","unstructured":"Roberts, A., Engel, J., Raffel, C., Hawthorne, C., and Eck, D. (2018, January 10\u201315). A Hierarchical Latent Vector Model for Learning Long-Term Structure in Music. Proceedings of the International Conference on Machine Learning (ICML), Stockholm, Sweden."},{"key":"ref_20","unstructured":"Liu, J., Dong, Y., Cheng, Z., Zhang, X., Li, X., Yu, F., and Sun, M. (2022, January 4\u20138). Symphony Generation with Permutation Invariant Language Model. Proceedings of the 23rd International Society for Music Information Retrieval Conference (ISMIR), Bengaluru, India."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., and Ommer, B. (2022, January 18\u201324). High-Resolution Image Synthesis with Latent Diffusion Models. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref_22","unstructured":"Li, X., Thickstun, J., Gulrajani, I., Liang, P.S., and Hashimoto, T.B. (December, January 28). Diffusion-LM Improves Controllable Text Generation. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), New Orleans, LA, USA."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Reimers, N., and Gurevych, I. (2019, January 3\u20137). Sentence-BERT: Sentence Embeddings Using Siamese BERT-Networks. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP), Hong Kong, China.","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref_24","unstructured":"von R\u00fctte, D., Biggio, L., Kilcher, Y., and Hofmann, T. (2022). FIGARO: Generating Symbolic Music with Fine-Grained Artistic Control. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Dong, H.-W., Hsiao, W.-Y., Yang, L.-C., and Yang, Y.-H. (2018, January 2\u20137). MuseGAN: Multi-Track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment. Proceedings of the AAAI Conference on Artificial Intelligence, New Orleans, LA, USA.","DOI":"10.1609\/aaai.v32i1.11312"},{"key":"ref_26","unstructured":"Yang, R., Wang, D., Wang, Z., Chen, T., Jiang, J., and Xia, G. (2019, January 4\u20138). Deep Music Analogy Via Latent Representation Disentanglement. Proceedings of the 20th International Society for Music Information Retrieval Conference (ISMIR), Delft, The Netherlands."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Ren, Y., He, J., Tan, X., Qin, T., Zhao, Z., and Liu, T.-Y. (2020). PopMAG: Pop Music Accompaniment Generation. arXiv.","DOI":"10.1145\/3394171.3413721"},{"key":"ref_28","unstructured":"Jang, E., Gu, S., and Poole, D. (2017, January 24\u201326). Categorical Reparameterization with Gumbel-Softmax. Proceedings of the International Conference on Learning Representations (ICLR), Toulon, France."},{"key":"ref_29","unstructured":"Ens, J., and Pasquier, P. (2021, January 7\u201312). Building the MetaMIDI Dataset: Linking Symbolic and Audio Musical Data. Proceedings of the 22nd International Society for Music Information Retrieval Conference (ISMIR), Online."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/6\/568\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T10:01:28Z","timestamp":1781085688000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/6\/568"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,8]]},"references-count":29,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["info17060568"],"URL":"https:\/\/doi.org\/10.3390\/info17060568","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,8]]}}}