Papers
Topics
Authors
Recent
Search
2000 character limit reached

TunesFormer: Forming Irish Tunes with Control Codes by Bar Patching

Published 7 Jan 2023 in cs.SD and eess.AS | (2301.02884v3)

Abstract: This paper introduces TunesFormer, an efficient Transformer-based dual-decoder model specifically designed for the generation of melodies that adhere to user-defined musical forms. Trained on 214,122 Irish tunes, TunesFormer utilizes techniques including bar patching and control codes. Bar patching reduces sequence length and generation time, while control codes guide TunesFormer in producing melodies that conform to desired musical forms. Our evaluation demonstrates TunesFormer's superior efficiency, being 3.22 times faster than GPT-2 and 1.79 times faster than a model with linear complexity of equal scale while offering comparable performance in controllability and other metrics. TunesFormer provides a novel tool for musicians, composers, and music enthusiasts alike to explore the vast landscape of Irish music. Our model and code are available at https://github.com/sander-wood/tunesformer.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (19)
  1. The effect of explicit structure encoding of deep neural networks for symbolic music generation, CoRR (2018). arXiv:1811.08380.
  2. Hierarchical recurrent neural networks for conditional melody generation with long-term structure, in: International Joint Conference on Neural Networks, IJCNN 2021, Shenzhen, China, July 18-22, 2021, IEEE, 2021. doi:10.1109/IJCNN52387.2021.9533493.
  3. Pop music generation with controllable phrase lengths, in: Proc. of the 23rd Int. Society for Music Information Retrieval Conf., Bengaluru, India, 2022.
  4. Structure-enhanced pop music generation via harmony-aware learning, in: MM ’22: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, October 10 - 14, 2022, ACM, 2022. doi:10.1145/3503161.3548084.
  5. Popmnet: Generating structured pop music melodies using neural networks, Artif. Intell. (2020). doi:10.1016/j.artint.2020.103303.
  6. Controllable deep melody generation via hierarchical music structure representation, in: Proceedings of the 22nd International Society for Music Information Retrieval Conference, ISMIR 2021, Online, November 7-12, 2021, 2021.
  7. Meloform: Generating melody with musical form based on expert systems and neural networks, CoRR (2022). arXiv:2208.14345.
  8. Music transcription modelling and composition using deep learning, CoRR (2016). arXiv:1604.08723.
  9. C. Geerlings, A. Merono-Penuela, Interacting with gpt-2 to generate controlled and believable musical sequences in abc notation, in: Proceedings of the 1st Workshop on NLP for Music and Audio (NLP4MusA), 2020.
  10. Attention is all you need, in: Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, 2017.
  11. Music transformer: Generating music with long-term structure, in: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019, OpenReview.net, 2019.
  12. S. Wu, M. Sun, Exploring the efficacy of pre-trained checkpoints in text-to-music generation task, in: The AAAI-23 Workshop on Creative AI Across Modalities, 2023. URL: https://openreview.net/forum?id=QmWXskBhesn.
  13. Clamp: Contrastive language-music pre-training for cross-modal symbolic music information retrieval, CoRR (2023). URL: https://doi.org/10.48550/arXiv.2304.11029. doi:10.48550/arXiv.2304.11029. arXiv:2304.11029.
  14. CTRL: A conditional transformer language model for controllable generation, CoRR (2019). URL: http://arxiv.org/abs/1909.05858. arXiv:1909.05858.
  15. V. I. Levenshtein, et al., Binary codes capable of correcting deletions, insertions, and reversals, in: Soviet physics doklady, Soviet Union, 1966.
  16. Learning hierarchical metrical structure beyond measures, in: Proceedings of the 23rd International Society for Music Information Retrieval Conference, ISMIR 2022, Bengaluru, India, December 4-8, 2022, 2022. URL: https://archives.ismir.net/ismir2022/paper/000023.pdf.
  17. M. S. Cuthbert, C. Ariza, Music21: A toolkit for computer-aided musicology and symbolic music data, International Society for Music Information Retrieval, 2010.
  18. Language models are unsupervised multitask learners, OpenAI blog (2019).
  19. RWKV: reinventing rnns for the transformer era, CoRR (2023). URL: https://doi.org/10.48550/arXiv.2305.13048. doi:10.48550/arXiv.2305.13048. arXiv:2305.13048.
Citations (8)

Summary

No one has generated a summary of this paper yet.

Paper to Video (Beta)

No one has generated a video about this paper yet.

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Continue Learning

We haven't generated follow-up questions for this paper yet.

Collections

Sign up for free to add this paper to one or more collections.