Learning Musical Relations using Gated Autoencoders

TL;DR

This paper investigates the use of Gated Autoencoders to learn and represent musical transformations, demonstrating their effectiveness over RBMs in capturing content-invariant relations for music analysis.

Contribution

It introduces the application of Gated Autoencoders for modeling musical transformations, showing their ability to learn content-invariant representations for structured music analysis.

Findings

GAEs outperform RBMs in learning musical transformations

GAEs produce content-invariant representations of musical relations

Models like GAEs can enhance music analysis systems

Abstract

Music is usually highly structured and it is still an open question how to design models which can successfully learn to recognize and represent musical structure. A fundamental problem is that structurally related patterns can have very distinct appearances, because the structural relationships are often based on transformations of musical material, like chromatic or diatonic transposition, inversion, retrograde, or rhythm change. In this preliminary work, we study the potential of two unsupervised learning techniques - Restricted Boltzmann Machines (RBMs) and Gated Autoencoders (GAEs) - to capture pre-defined transformations from constructed data pairs. We evaluate the models by using the learned representations as inputs in a discriminative task where for a given type of transformation (e.g. diatonic transposition), the specific relation between two musical patterns must be recognized (e.g. an upward transposition of diatonic steps). Furthermore, we measure the reconstruction error of models when reconstructing musical transformed patterns. Lastly, we test the models in an analogy-making task. We find that it is difficult to learn musical transformations with the RBM and that the GAE is much more adequate for this task, since it is able to learn representations of specific transformations that are largely content-invariant. We believe these results show that models such as GAEs may provide the basis for more encompassing music analysis systems, by endowing them with a better understanding of the structures underlying music.