Automatic Drum Beat Generation using GAN

International Journal of Electrical and Electronics Engineering

© 2023 by SSRG - IJEEE Journal

Volume 10 Issue 2

Year of Publication : 2023

Authors : Suman Maria Tony, S. Sasikumar

10.14445/23488379/IJEEE-V10I2P101

How to Cite?

Suman Maria Tony, S. Sasikumar, "Automatic Drum Beat Generation using GAN," SSRG International Journal of Electrical and Electronics Engineering, vol. 10,  no. 2, pp. 1-7, 2023. Crossref, https://doi.org/10.14445/23488379/IJEEE-V10I2P101

Abstract:

In this paper, the authors attempt to automatic generation of drum beats using generative adversarial networks (GAN). The generator of the GAN is trained with the short-time Fourier to transform (STFT) of drum beats from a diversified dataset, while the discriminator challenges the generator. The generator, once trained, the GAN is able to produce drum beats close to real-time sequences. Also, we propose to do a subjective evaluation of the generated drum beats. The simulation results showed that the drum beat generated by the GAN had more resemblance when compared to the actual drum beats. Also, the subjective assessment by a few audiences proves the effectiveness of this method of automatic drum beat synthesis.

Keywords:

Music generation, Generative adversarial networks, Drum beats, Music synthesis introduction.

References:

[1] Maximos A. Kaliakatsos–Papakostas, Andreas Floros, and Michael N. Vrahatis, “evoDrummer: Deriving Rhythmic Patterns through Interactive Genetic Algorithms,’ Lecture Notes in Computer Science, Springer, vol. 7834, pp. 25-36, 2013. Crossref, http://doi.org/10.1007/978-3-642-36955-1_3
[2] Cárthach Ó Nuanáin, Perfecto Herrera, and Sergi Jordà, “Target-Based Rhythmic Pattern Generation and Variation with Genetic Algorithms,” Sound Music Computing Conference, 2015.
[3] Jean-Pierre Briot, Gaëtan Hadjeres, and François-David Pachet, Deep Learning Techniques for Music Generation, p. 284, 2020. Crossref, https://doi.org/10.1007/978-3-319-70163-9
[4] Ian J. Goodfellow et al., Generative Adversarial Nets, Advances in Neural Information Processing Systems, vol. 27, 2014.
[5] Tero Karras, Samuli Laine, and Timo Aila, “A Style-Based Generator Architecture for Generative Adversarial Networks,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 43, no. 12, pp. 4217-4228, 2020. Crossref, https://doi.org/10.1109/TPAMI.2020.2970919
[6] Lantao Yu et al., “SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient,” 31st AAAI Conference Artificial Intelligence, AAAI 2017, pp. 2852–2858, 2016.
[7] Gabriel Lima Guimaraes et al., “Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models,” 2017. Crossref, https://doi.org/10.48550/arXiv.1705.10843
[8] Hao-Wen Dong et al., “MuseGAN: Multi-Track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment,” The Association for the Advance of Artificial Intelligence, 2018.
[9] R. Tuğrul Erdem et al., "Impact Analysis of a Concrete Beam via Generative Adversarial Networks," International Journal of Recent Engineering Science, vol. 9, no. 1, pp. 16-21, 2022. Crossref, https://doi.org/10.14445/23497157/IJRES-V9I1P103
[10] Gargi Sharma, and Gourav Shrivastava, "Crop Disease Prediction using Deep Learning Techniques - A Review," SSRG International Journal of Computer Science and Engineering, vol. 9, no. 4, pp. 23-28, 2022. Crossref, https://doi.org/10.14445/23488387/IJCSE-V9I4P104
[11] Vrinda. K, and Dhanesh G. Kurup, "A Broadband Equivalent Model of On-Chip Spiral Inductors using Differential Evolution Algorithm," International Journal of Engineering Trends and Technology, vol. 70, no. 3, pp. 249-253, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I2P228
[12] Andrew Shin et al., “Melody Generation for Pop Music via Word Representation of Musical Properties,” arXivpreprint arXiv:1710.11549, 2017. Crossref, https://doi.org/10.48550/arXiv.1710.11549
[13] Hao-Wen Dong et al., “Musegan: Demonstration of a Convolutional GAN based Model for Generating Multi-Track Piano-Rolls,” Late Breaking/ Demos, 18th International Society for Music Information Retrieval Conference, 2017.
[14] Li-Chia Yang, Szu-Yu Chou, and Yi-Hsuan Yang, “Midinet: A Convolutional Generative Adversarial Network for Symbolic Domain Music Generation,” arXiv preprint arXiv:1703.10847, 2017. Crossref, https://doi.org/10.48550/arXiv.1703.10847 
[15] Chris Donahue, Julian McAuley, and Miller Puckette, “Synthesizing Audio with Generative Adversarial Networks,” arXiv preprint arXiv:1802.04208, 2018.
[16] Narain Krishnamurthy, Beatgan – Generating Drum Loops via GANS, 2018. [Online]. Available: https://github.com/NarainKrishnamurthy/BeatGAN2.0
[17] Magenta. [Online]. Available: https://magenta.tensorflow.org
[18] DeepJazz. [Online]. Available: https://deepjazz.io
[19] BachBot. [Online]. Available: https://bachbot.com
[20] FlowMachines. [Online]. Available: https://www.flow-machines.com
[21] WaveNet. [Online]. Available: https://deepmind.com
[22] Satya Srinivas Maddipati, and Malladi Srinivas, "Efficient Dimensionality Reduction using Improved Fuzzy C-Means Entropy Approach with Caps-TripleGAN for Predicting Software Defect in Imbalanced Dataset," International Journal of Engineering Trends and Technology, vol. 70, no. 7, pp. 1-9, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I7P201
[23] Radford, L. Metz, and S. Chintala, “Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks,” 4th International Conference Learning Represent, ICLR, 2016.
[24] Chris Donahue, Julian McAuley, and Miller Puckette, “Adversarial Audio Synthesis,” In Proceedings of ICLR, 2019.
[25] T. Kujani, and V. Dhilip Kumar, "Emotion Understanding from Facial Expressions using Stacked Generative Adversarial Network (GAN) and Deep Convolution Neural Network (DCNN)," International Journal of Engineering Trends and Technology, vol. 70, no. 10, pp. 98-110, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I10P212
[26] Suman Maria Tony, and S Sasikumar, “Music Generation Using Supervised Learning and LSTM,” Advances in Energy Technology, Lecture Notes in Electrical Engineering, Springer, Singapore, vol. 766, 2021. Crossref, https://doi.org/10.1007/978-981-16-1476-7_43
[27] Vinayak K. Bairagi, Sarang L. Joshi, and Vastav Bharambe, "Implementing Concatenative Text-To-Speech Synthesis System for Marathi Language using Python," SSRG International Journal of Electrical and Electronics Engineering, vol. 9, no. 9, pp. 1-11, 2022. Crossref, https://doi.org/10.14445/23488379/IJEEE-V9I9P101
[28] Garv Agarwal, Sai Sanjeet, and Bibhu Datta Sahoo, "Seizure Prediction using Generative Adversarial Networks for EEG Data Synthesis," SSRG International Journal of Computer Science and Engineering, vol. 9, no. 10, pp. 1-7, 2022. Crossref, https://doi.org/10.14445/23488387/IJCSE-V9I10P101
[29] Nipun Agarwala, Yuki Inoue, and Axel Sly, “Music Composition using Recurrent Neural Networks,” Stanford University, Technical Report in CS224, 2017.
[30] Gaëtan Hadjeres, François Pachet, and Frank Nielsen, “DeepBach: A Steerable Model for Bach Chorales Generation,” International Conference on Machine Learning, New York City, NY, USA, pp. 1362-1371, 2016.
[31] Keerti Maithil, and Tasneem Bano Rehman, "Urban Remote Sensing Image Segmentation using Dense U-Net+," SSRG International Journal of Computer Science and Engineering, vol. 9, no. 3, pp. 21-28, 2022. Crossref, https://doi.org/10.14445/23488387/IJCSE-V9I3P103
[32] Huang KC, Jung Q, and Lu J, “Algorithmic Music Composition Using Recurrent Neural Networking,” Stanford University, Technical Report in CS22, 2017.
[33] T V Divya, and Barnali Gupta Banik, "An Integrated Cycle GAN and PEGASUS to Generate Synthetic Data for Detection of Fake News," International Journal of Engineering Trends and Technology, vol. 70, no. 8, pp. 57-70, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I8P206
[34] Suman Maria Tony, and S. Sasikumar, “Generative Adversarial Network for Music Generation,” High Performance Computing and Networking. Lecture Notes in Electrical Engineering, Springer, Singapore, vol. 853, 2022. Crossref, https://doi.org/10.1007/978-981-16-9885-9_9