2000 character limit reached
Everybody Compose: Deep Beats To Music
Published 9 Jun 2023 in cs.SD, cs.LG, cs.MM, and eess.AS | (2306.06284v1)
Abstract: This project presents a deep learning approach to generate monophonic melodies based on input beats, allowing even amateurs to create their own music compositions. Three effective methods - LSTM with Full Attention, LSTM with Local Attention, and Transformer with Relative Position Representation - are proposed for this novel task, providing great variation, harmony, and structure in the generated music. This project allows anyone to compose their own music by tapping their keyboards or ``recoloring'' beat sequences from existing works.
- Dzmitry Bahdanau, Kyunghyun Cho and Yoshua Bengio “Neural machine translation by jointly learning to align and translate” In arXiv preprint arXiv:1409.0473, 2014
- “Sketchygan: Towards diverse and realistic sketch to image synthesis” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 9416–9425
- Keunwoo Choi, George Fazekas and Mark Sandler “Text-based LSTM networks for automatic music composition” In arXiv preprint arXiv:1604.05358, 2016
- “A first look at music composition using lstm recurrent neural networks” In Istituto Dalle Molle Di Studi Sull Intelligenza Artificiale 103 Google Scholar, 2002, pp. 48
- “Generative adversarial networks” In Communications of the ACM 63.11 ACM New York, NY, USA, 2020, pp. 139–144
- “Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset” In International Conference on Learning Representations, 2019 URL: https://openreview.net/forum?id=r1lYRjC9F7
- “Long short-term memory” In Neural computation 9.8 MIT Press, 1997, pp. 1735–1780
- “Music transformer: generating music with long-term structure” In arXiv preprint arXiv:1809.04281, 2018
- Magenta “Note-seq: Generating musical notes with RNNs”, https://github.com/magenta/note-seq, 2020 URL: https://github.com/magenta/note-seq
- “Symbolic Music Generation with Transformer-GANs” In Proceedings of the AAAI Conference on Artificial Intelligence 35.1, 2021, pp. 408–417 DOI: 10.1609/aaai.v35i1.16117
- Christine McLeavey Payne “MuseNet” https://openai.com/blog/musenet/ In OpenAI, 2019
- “Piano e-Competition” Accessed: November 5, 2022, https://piano-e-competition.com/
- Peter Shaw, Jakob Uszkoreit and Ashish Vaswani “Self-Attention with Relative Position Representations” In CoRR abs/1803.02155, 2018 arXiv: http://arxiv.org/abs/1803.02155
- “Performance RNN: Generating Music with Expressive Timing and Dynamics” In Magenta Blog, https://magenta.tensorflow.org/performance-rnn, 2017
- “Attention is All you Need” In Advances in Neural Information Processing Systems 30 Curran Associates, Inc., 2017 URL: https://proceedings.neurips.cc/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf
- Elliot Waite “Generating Long-Term Structure in Songs and Stories” https://magenta.tensorflow.org/2016/07/15/lookback-rnn-attention-rnn In Magenta, 2016
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.
