Music Generation With Machine Learning

Authors

  • Joel Alexandre de Sá Júnior Universidade do Oeste Paulista - Unoeste
  • Mário Augusto Pazoti Universidade do Oeste Paulista - Unoeste
  • Leandro Luiz de Almeida Universidade do Oeste Paulista - Unoeste
  • Francisco Assis da Silva Universidade do Oeste Paulista - Unoeste
  • Danillo Roberto Pereira Faculdade de Informática de Presidente Prudente (FIPP) – Unoeste

Keywords:

Machine learning, Music, Magenta, Neural networks, LSTM

Abstract

ABSTRACT – Machine learning is a concept that has been a part of the day-to-day life, being used in applications like social networks, e-commerce, smartphone assistants, among others. In the music area it can be used to inspire composers, produce music based on a specific style or generate music in real time for games or VR applications. This article will evaluate the ability of a neural network to generate satisfactory results in the music area, using Magenta libraries, a toolkit for the use of machine learning in artistic applications. The songs are generated based on a dataset of Bach compositions and procedurally checked for plagiarism, comparing the obtained results to the dataset.

Downloads

Download data is not yet available.

Author Biography

  • Danillo Roberto Pereira, Faculdade de Informática de Presidente Prudente (FIPP) – Unoeste

    Possui graduação em Ciência da Computação pela FCT-UNESP (2006) ; mestrado em Ciência da Computação pela UNICAMP (2009); e doutorado pela UNICAMP. Tem experiência na área de Ciência da Computação, com ênfase em Geometria Computacional, Computação Gráfica e Visão Computacional. lattes.cnpq.br/0122307432250869

References

AREL, I.; ROSE, D.; KARNOWSKI, T. Deep Machine Learning - A new Frontier in Artificial Intelligence Research. The University of Tennessee, 2010. https://doi.org/10.1109/MCI.2010.938364

CHEN, C-C J.; MIIKKULAINEN, R. Creating melodies with evolving recurrent neural networks, In: INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, 2001. Washington, DC Proceedings […].Washington, DC, 2001.

DENG, L.; YU, D. Deep Learning: Methods and Applications.Foundations and Trends. . Signal Processing v.7, n. /-3/4, p.197, 2014. https://doi.org/10.1561/2000000039

ECK, D.; SCHMIDHUBER, J. A First Look at Music Composition using LSTM Recurrent Neural Networks. Technical Report No. IDSIA-07-02. Istituto Dalle Molle Di Studi Sull Intelligenza Artificiale, 2002.

GOOGLE Brain, TensorFlow: A System for Large-Scale Machine Learning, 12th USENIX Symposium on Operating Systems Design and Implementation, 2016.

HOCHREITER, S..; SCHMIDHUBER, J.Long-Short Term Memory Neural Computation v.9, p. 1735-1780, 1993. https://doi.org/10.1162/neco.1997.9.8.1735

HUANG, A.; WU, R. Deep learning for music. Universe de Stanford, 2016.

LECUN, Y.; BENGIO, Y.; HINTOM, G. Deep Learning, Nature, v. 521, p. 436-444, 2015. https://doi.org/10.1038/nature14539

SAMUEL, A. Some Studies in Machine Learning Using the Game of Checkers, IBM Journal of Research and Development, v. 3, n. 3, 1959. https://doi.org/10.1147/rd.33.0210

WAITE, E.; ECK, D.; ROBERTS, D.; ABOLAFIA, D. Project Magenta. 2016. Disponível em: https: //magenta.tensorflow.org. Acesso em: 18 mar. 2018.

Downloads

Published

2019-07-31

Issue

Vol. 11 No. 2 (2019): Colloquium Exactarum, Vol.11 N.2

Section

Artigos Originais

How to Cite

Music Generation With Machine Learning. (2019). Colloquium Exactarum. ISSN: 2178-8332, 11(2), 56-65. https://revistas.unoeste.br/index.php/ce/article/view/3170

Most read articles by the same author(s)

1 2 3 4 5 6 > >>