Program for sound generation based on image color spectrum with using the recurrent neural network

DOI

10.2991/itsmssm-17.2017.48How to use a DOI?

Keywords

artificial neural networks, recurrent neural network, long-short term memory, Theano, TensorFlow, Lasagne, Keras, MXNet, Python, Newton correlation scheme, sampling.

Abstract

This work is devoted to development and approbation of the program for sound generation based on image color spectrum with using the recurrent neural network. The work contains a description of the transition between color and music characteristics, the rationale for choosing and the description of a recurrent neural network. The choices of the neural network implementation technology as well as the results of the experiment are described.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Nikita Nikitin
AU  - Vladimir Rozaliev
AU  - Yulia Orlova
PY  - 2017/12
DA  - 2017/12
TI  - Program for sound generation based on image color spectrum with using the recurrent neural network
BT  - Proceedings of the IV International research conference "Information technologies in Science, Management, Social sphere and Medicine" (ITSMSSM 2017)
PB  - Atlantis Press
SP  - 227
EP  - 232
SN  - 2352-538X
UR  - https://doi.org/10.2991/itsmssm-17.2017.48
DO  - 10.2991/itsmssm-17.2017.48
ID  - Nikitin2017/12
ER  -