Abstract
In this paper we have presented a method for composing and generating short musical phrases using a deep convolutional generative adversarial network (DCGAN). We have used a dataset of classical and jazz music MIDI recordings in order to train the network. Our approach introduces translating the MIDI data into graphical images in a piano roll format suitable for the DCGAN, using the RGB channels as additional information carriers for improved performance. We show that the network has learned to generate images that are indistinguishable from the input data and, when translated back to MIDI and played back, include several musically interesting rhythmic and harmonic structures. The results of the conducted experiments are described and discussed, with conclusions for further work and a short comparison with selected existing solutions.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
While the sustain pedal is pressed, the notes of the piano sustain after keys are released by the pianist.
References
Choi, K., Fazekas, G., Sandler, M., Cho, K.: Convolutional recurrent neural networks for music classification. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2392–2396. IEEE (2017)
McKenzie, D.: MIDI Collection. https://bushgrafts.com/midi/. Accessed 16 Jan 2019
Engel, J., et al.: Neural audio synthesis of musical notes with wavenet autoencoders. In: ICML (2017)
Goodfellow, I., et al.: Generative adversarial nets. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 27, pp. 2672–2680. Curran Associates Inc (2014)
Hawthorne, C., et al.: Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset (2018)
Wilkowska-Chołmińska, K., Chołmiński, J.: Historia Muzyki cz.I. PWM (1989)
Johnson, D.D., Keller, R.M., Weintraut, N.: Learning to create jazz melodies using a product of experts. In: ICCC (2017)
DeepJazz. https://github.com/jisungk/deepjazz. Accessed 16 Jan 2019
Google Magenta - research tool for artistic applications of machine learning. https://magenta.tensorflow.org. Accessed 16 Jan 2019
Amper Music. https://www.ampermusic.com/. Accessed 16 Jan 2019
The MIDI File Format. https://www.csie.ntu.edu.tw/~r92092/ref/midi/. Accessed 16 Jan 2019
What is a Player Piano (Pianola)? http://www.pianola.co.nz/public/index.php/web/about_piano_rolls. Accessed 16 Jan 2019
van den Oord, A., Kalchbrenner, N., Espeholt, L., Kavukcuoglu, K., Vinyals, O., Graves, A.: Conditional image generation with PixelCNN decoders. In: Lee, D.D., Sugiyama, M., Luxburg, U.V., Guyon, I., Garnett, R., (eds.) Advances in Neural Information Processing Systems, vol. 29, pp. 4790–4798. Curran Associates Inc (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Modrzejewski, M., Dorobek, M., Rokita, P. (2019). Application of Deep Neural Networks to Music Composition Based on MIDI Datasets and Graphical Representation. In: Rutkowski, L., Scherer, R., Korytkowski, M., Pedrycz, W., Tadeusiewicz, R., Zurada, J. (eds) Artificial Intelligence and Soft Computing. ICAISC 2019. Lecture Notes in Computer Science(), vol 11508. Springer, Cham. https://doi.org/10.1007/978-3-030-20912-4_14
Download citation
DOI: https://doi.org/10.1007/978-3-030-20912-4_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-20911-7
Online ISBN: 978-3-030-20912-4
eBook Packages: Computer ScienceComputer Science (R0)