Journal of Engineering and Applied Sciences
ISSN: Online 1818-7803ISSN: Print 1816-949x
Abstract
Music is a composed sound so that it contains rhythm, song and harmony. Every music has different chord provisions and arrangements which makes making music difficult. Based on these problems, a solution was made in the form of Music Generation with the Recurrent Neural Network (RNN) method to facilitate the making of a music. Recurrent Neural Network (RNN) is a class of artificial neural networks where the connection between nodes forms a directed graph along the sequence. This allows it to show temporary dynamic behavior for a time sequence. The data used is in the form of a Musical Instrument Digital Interface (MIDI) format file with sufficient amounts. The system will produce a midi file that has undergone the process of making chords and merging randomly, so that, it becomes a new music. Then implemented in Python. The output in this system produces a music that allows it to be processed again in the Digital Audio Workstation (DAW) to produce the desired music.
How to cite this article:
Dimas Fiqh Puskoaji, Tito Waluyo Purboyo and Randy Erfa Saputra. A Experiment of Reccurent Neural Network Methods for Generating a Music.
DOI: https://doi.org/10.36478/jeasci.2020.2619.2622
URL: https://www.makhillpublications.co/view-article/1816-949x/jeasci.2020.2619.2622