IJMSTA - Vol. 2 - Issue 2 - July 2020
Conditional Modelling of Ragtime Accompaniment using Convolutional Variational Autoencoder
Authors: A. Oudad, H. Saito
Abstract - Generational machine learning has been applied to various fields and is currently under exploration for music. Automatic music composition is receiving attention re-cently thanks to advance in distributed modelling using neural networks. Yet, musi-cal models lack the ability to effectively capture harmonic and rhythmic features of music. We propose a model using variational autoencoder for encoding musical bars of ragtime piano music. Ragtime piano music is composed of left hand and right hand with different roles, thus we use righthand musical information to condition our variational autoencoder when reconstructing left-hand musical bars. We show our model is able to reconstruct and interpolate musical bars, thus providing useful musical bar embeddings for music generation.
Keywords: Deep Learning, Algorithmic Music Composition, Variational Inference, Music Information Processing
Cite this paper as
About this paper
Oudad, A., Saito, H.: Conditional Modelling of Ragtime Accompaniment using Convolutional Variational Autoencoder. IJMSTA. 2020 Aug 18; 2 (2): 15-21.