Stefan Lattner, Maarten Grachten, Gerhard Widmer,
"Learning Musical Relations using Gated Autoencoders"
: Proceedings of the 2nd Conference on Computer Simulation of Musical Creativity (CSMC 2017), 2017
Original Titel:
Learning Musical Relations using Gated Autoencoders
Sprache des Titels:
Englisch
Original Buchtitel:
Proceedings of the 2nd Conference on Computer Simulation of Musical Creativity (CSMC 2017)
Original Kurzfassung:
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.
Forschungs-