The Computational Creativity Complex - Computational Creativity Research: Towards Creative Machines - page 68

4.2.2 CARL

CARL is a computational composition system designed to incorporate two competing
compositional ideas: (1) to produce “acceptable” music and (2) to produce innovative
music. Many compositional systems accomplish one or the other of these goals
very well. In the case of the former goal, approaches tend to learn a model from
a set of training examples and probabilistically generate new music based on the
learned model. These approaches effectively produce artifacts that mimic classical
music literature, but little thought is directed toward expansion and transformation
of the music domain. For example, David Cope [ 41 ] and Dubnov et al. [ 29 ] seek to
mimic the style of other composers in their systems. In the case of the latter goal,
approaches utilize devices such as genetic algorithms [ 30 , 31 ] and swarms [ 32 ].
While these approaches can theoretically expand the music domain, they often have
little grounding in accepted musicality, and their output often receives little acclaim
from either music scholars or average listeners.
In order to serve both goals, CARL couples machine learning (ML) techniques
with an inspirational component. The ML component maintains grounding in music
literature and effects innovation by employing the strengths of generative models. It
embraces the compositional approach found in the period of common practice and
the early 20th century. The inspirational component introduces non-musical ideas
and enables innovation beyond the musical training data. The system focuses on the
composition of motifs, an atomic level of musical structure, defined as “the smallest
structural unit possessing thematic identity” [ 33 ].
First, an ML model is trained on a set of monophonic MIDI themes retrieved from
The Electronic Dictionary of Musical Themes. 1 Then, a set of candidate motifs is
extracted from an inspirational media file (e.g., pitch detection is performed on an
audio file or edge detection is performed on an image file). Members of the set of
candidate motifs that are most probable according to the ML model are selected as the
building blocks for a composition. A high-level system pipeline is shown graphically
in Fig. 4.3 .

4.2.2.1 Machine Learning Models

Two different ML models are trained, one over a set of 128 possible pitches and
one over 32 possible rhythmic durations (32nd note multiples up to a whole note).
A variety of ML approaches, including HMMs, variable order Markov models and
recurrent neural networks have been used as generative (and discriminitive) models
for music composition. In this context, the model is used discriminatively—to iden-
tify motifs that conform (to some degree) to known musical conventions (or, more
accurately, to such conventions as might be extracted from the training data), and two
classes of model, Prediction by Partial Match [ 34 ] and Context Tree Weighting [ 35 ],
have proven particularly effective at this task.

1

http://www.multimedialibrary.com/barlow/all_barlow.asp .