Generování žánrově specifické hudební transkripce Antonína Dvořáka prostřednictvím variačního autoenkodéru

Roč.56,č.2(2021)

Daniel Kvak

https://doi.org/10.5817/MB2021-2-5

Trvalý odkaz (handle):
http://hdl.handle.net/11222.digilib/144818

PDF
Abstrakt
Apart from traditional deep learning tasks such as pattern recognition, stock price prediction, and machine translation, this method also finds practical application within algorithmic composition. This paper explores the use of a generative model based on unsupervised learning of a musical style from a pre-selected corpus and the subsequent prediction of samples from the estimated distribution. The model uses a Long Short-Term Memory neural network whose training data contains genre-specific melodies in symbolic representation.

Klíčová slova:
algorithmic composition; artificial intelligence; autoencoder; deep learning; generative art; LSTM network; machine learning; recurrent neural network

Stránky:
49–61
Reference

ALPERN, Adam. Techniques for Algorithmic Composition of Music [online]. Hampshire College, 1995. DOI:10.1.1.23.9364. | DOI 10.1.1.23.9364

Building Autoencoders in Keras. In: The Keras Blog. Dostupné z: https://blog.keras.io/building-autoencoders-in-keras.html.

CASEY, M. A. et al. Content-Based Music Information Retrieval: Current Directions and Future Challenges. Proceedings of the IEEE. 2008, roč. 96, č. 4, s. 668–696. ISSN 1558-2256. DOI:10.1109/JPROC.2008.916370. | DOI 10.1109/JPROC.2008.916370

DAVIS, Martin. Engines of Logic: Mathematicians and the Origin of the Computer. USA: W. W. Norton & Co., Inc., 2001. ISBN 978-0-393-32229-3.

DERTAT, Arden. Applied Deep Learning - Part 3: Autoencoders. In: Medium [online]. 8. 10. 2017. Dostupné z: https://towardsdatascience.com/applied-deep-learning-part-3-autoencoders-1c083af4d798.

ECK, Douglas a Juergen SCHMIDHUBER. A First Look at Music Composition using LSTM Recurrent Neural Networks [online]. 2002. Manno, Switzerland: Istituto Dalle Molle Di Studi Sull Intelligenza Artificiale. DOI:10.5555/870511. | DOI 10.5555/870511

FERNANDEZ, Jose David a Francisco VICO. AI Methods in Algorithmic Composition: A Comprehensive Survey. Journal of Artificial Intelligence Research. 2013, roč. 48, s. 513–582. ISSN 1076-9757. DOI: 10.1613/jair.3908. | DOI 10.1613/jair.3908

FIEBRINK, Rebecca a Baptiste CARAMIAUX. The Machine Learning Algorithm as Creative Musical Tool. Handbook on Algorithmic Music [online]. Oxford: Oxford University Press, 2016. Dostupné z: https://www.researchgate.net/publication/309631691_The_Machine_Learning_Algorithm_as_Creative_Musical_Tool

GULLI, Antonio a Sujit PAL. Deep Learning with Keras. Packt Publishing Ltd, 2017. ISBN 978-1-78712-903-0.

HE, Kaiming et al. Deep Residual Learning for Image Recognition. arXiv:1512.03385 [cs] [online]. 2015. Dostupné z: http://arxiv.org/abs/1512.03385.

HILLER, Lejaren Arthur a Leonard M. ISAACSON. Experimental Music; Composition with an Electronic Computer. Westport, CT, USA: Greenwood Publishing Group, 1979, 197 s. ISBN 978-0-313-22158-3.

HOCHREITER, Sepp a Jürgen SCHMIDHUBER. Long Short-Term Memory. Neural Computation [online]. 1997, 9(8), 1735-1780. DOI: 10.1162/neco.1997.9.8.1735. ISSN 0899-7667. Dostupné z: http://www.mitpressjournals.org/doi/10.1162/neco.1997.9.8.1735. | DOI 10.1162/neco.1997.9.8.1735

KELLY, Thomas Forrest. Capturing Music: The Story of Notation. W. W. Norton & Company; Har/Com edition, 2014, 256 s. ISBN 978-0393064964.

LOY, Gareth. Musimathics, Volume 1: The Mathematical Foundations of Music. Reprint edition. vyd. Cambridge, Mass.: The MIT Press, 2011. ISBN 978-0-262-51655-6.

REJZEK, Jiří. Český etymologický slovník. Voznice: Leda, 2001. ISBN 80-85927-85-3. Heslo "algoritmus".

RUSSELL, Stuart J. a Peter NORVIG. Artificial intelligence: a modern approach. Third edition. Boston: Pearson, 2016. Prentice Hall series in artificial intelligence. ISBN 9781292153964.

SAINATH, T. N., B. KINGSBURY a B. RAMABHADRAN. Auto-encoder bottleneck features using deep belief networks. 2012. DOI: 10.1109/ICASSP.2012.6288833. | DOI 10.1109/ICASSP.2012.6288833

STURM, Bob L. On folk-rnn cheating and music generation [online]. 2017. Dostupné z: https://highnoongmt.wordpress.com/2017/06/15/on-folk-rnn-cheating-and-music-generation/.

TIU, Ekin. Understanding Latent Space in Machine Learning. In: Medium [online]. 2020. Dostupné z: https://towardsdatascience.com/understanding-latent-space-in-machine-learning-de5a7c687d8d.

TODD, Peter M. A Connectionist Approach to Algorithmic Composition. Computer Music Journal [online]. 1989, 13(4). DOI: 10.2307/3679551. ISSN 01489267. Dostupné z: https://www.jstor.org/stable/3679551?origin=crossref. | DOI 10.2307/3679551

VOLNÁ, Eva. Umělá inteligence: rozpoznávání vzorů v dynamických datech. Praha: BEN – technická literatura, 2014. ISBN 9788073005146.

VONDRÁK, Ivo. Umělá inteligence a neuronové sítě. 2. vyd. Ostrava: Vysoká škola báňská – Technická univerzita, 2000. ISBN 80-7078-949-2.

WALSHAW, Chris. A Statistical Analysis of the ABC Music Notation Corpus: Exploring Duplication. Conference: Folk Music Analysis. Istanbul, 2014. DOI:10.13140/2.1.4340.0961. | DOI 10.13140/2.1.4340.0961

Metriky

0

Crossref logo

0

web of science logo

21

Views

0

PDF views

PDF