2000 character limit reached
Combinatorial music generation model with song structure graph analysis (2312.15400v1)
Published 24 Dec 2023 in cs.SD, cs.AI, and eess.AS
Abstract: In this work, we propose a symbolic music generation model with the song structure graph analysis network. We construct a graph that uses information such as note sequence and instrument as node features, while the correlation between note sequences acts as the edge feature. We trained a Graph Neural Network to obtain node representation in the graph, then we use node representation as input of Unet to generate CONLON pianoroll image latent. The outcomes of our experimental results show that the proposed model can generate a comprehensive form of music. Our approach represents a promising and innovative method for symbolic music generation and holds potential applications in various fields in Music Information Retreival, including music composition, music classification, and music inpainting systems.
- “Musegan: Multi-track sequential generative adversarial networks for symbolic music generation and accompaniment,” in Proceedings of the AAAI Conference on Artificial Intelligence, 2018, vol. 32.
- “Music transformer,” arXiv preprint arXiv:1809.04281, 2018.
- “Theme transformer: Symbolic music generation with theme-conditioned transformer,” IEEE Transactions on Multimedia, 2022.
- “Melons: generating melody with long-term structure using transformers and structure graph,” in ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2022, pp. 191–195.
- “Commu: Dataset for combinatorial music generation,” Advances in Neural Information Processing Systems, vol. 35, pp. 39103–39114, 2022.
- “Conlon: A pseudo-song generator based on a new pianoroll, wasserstein autoencoders, and optimal interpolations.,” in ISMIR, 2020, pp. 876–883.
- “Audio-based music structure analysis,” Proceedings of the 11th International Society for Music Information Retrieval Conference, ISMIR 2010, pp. 625–636, 01 2010.
- “Pitchclass2vec: Symbolic music structure segmentation with chord embeddings,” arXiv preprint arXiv:2303.15306, 2023.
- “Symbolic music loop generation with neural discrete representations,” arXiv preprint arXiv:2208.05605, 2022.
- “Content based image retrieval,” Int. J. Adv. Eng. Glob. Technol, vol. 3, pp. 1251–1258, 2015.
- “Wasserstein auto-encoders,” arXiv preprint arXiv:1711.01558, 2017.
- “A new model for learning in graph domains,” in Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. IEEE, 2005, vol. 2, pp. 729–734.
- “Cadence detection in symbolic classical music using graph neural networks,” arXiv preprint arXiv:2208.14819, 2022.
- “Heterogeneous graph neural network for music emotion recognition,” 2022.
- “Graph neural network for music score data and modeling expressive piano performance,” in International Conference on Machine Learning. PMLR, 2019, pp. 3060–3070.
- Meinard Müller, Fundamentals of music processing: Audio, analysis, algorithms, applications, vol. 5, Springer, 2015.
- “Feature-based information retrieval of multimodal biosignals with a self-similarity matrix: Focus on automatic segmentation,” Biosensors, vol. 12, no. 12, pp. 1182, 2022.
- Ming-Kuei Hu, “Visual pattern recognition by moment invariants,” IRE transactions on information theory, vol. 8, no. 2, pp. 179–187, 1962.
- “Masked label prediction: Unified message passing model for semi-supervised classification,” arXiv preprint arXiv:2009.03509, 2020.
- “Dropedge: Towards deep graph convolutional networks on node classification,” arXiv preprint arXiv:1907.10903, 2019.
- “Graph contrastive learning with augmentations,” Advances in neural information processing systems, vol. 33, pp. 5812–5823, 2020.
- “U-net: Convolutional networks for biomedical image segmentation,” in Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18. Springer, 2015, pp. 234–241.
- C Raffel, Learning-based methods for comparing sequences, with applications to audio-to-midi alignment and matching. 331 Ph. D, Ph.D. thesis, thesis, Columbia University, 2016.