Computational Creativity and Music Generation Systems: An Introduction to the State of the Art

Abstract

Computational Creativity is a multidisciplinary field that tries to obtain creative behaviors from computers. One of its most prolific subfields is that of Music Generation (also called Algorithmic Composition or Musical Metacreation), that uses computational means to compose music. Due to the multidisciplinary nature of this research field, it is sometimes hard to define precise goals and to keep track of what problems can be considered solved by state-of-the-art systems and what instead needs further developments. With this survey, we try to give a complete introduction to those who wish to explore Computational Creativity and Music Generation. To do so, we first give a picture of the research on the definition and the evaluation of creativity, both human and computational, needed to understand how computational means can be used to obtain creative behaviors and its importance within Artificial Intelligence studies. We then review the state of the art of Music Generation Systems, by citing examples for all the main approaches to music generation, and by listing the open challenges that were identified by previous reviews on the subject. For each of these challenges, we cite works that have proposed solutions, describing what still needs to be done and some possible directions for further research.

Creativity in Generative Musical Networks: Evidence From Two Case Studies

“…The first one follows what Jordanous (2019) calls a “creative-practitioner-type approach, producing a system and then presenting it to others, whose critical reaction determines its worth as a creative entity”, even in real-time ( Collins, 2007 ). The second one is described by Carnovalini and Rodà (2020) : “have the author of the system describe the way it works and how it can be considered creative or not, and to what degree.” A third one is to evaluate artificially generated music in a concert setting, just as normal auditors would assess a live musical situation ( Eigenfeldt et al, 2012 ; Sturm et al, 2018 ), or in a museum-like setting for the case of the visual arts ( Edmonds et al, 2009 ). Finally, a fourth approach that we can identify is described in ( Yang and Lerch, 2020 ), who propose “informed objective metrics” to complement a subjective evaluation by a human.…”

“…It is also worth emphasizing that novelty often implies unpredictability and uncertainty, especially in the case of musical creativity (Daikoku et al, 2021). Carnovalini and Rodà (2020) observe that "the usual experience with machines is that we humans give a set of instructions to the machine along with some initial data (the input), and we expect the machine to behave in a way that is fully deterministic, always giving the same output when the same input is given". This idea of deterministic robots is apparently very opposed to the whole notion of creativity, which supposes something novel and valuable.…”

Applications of Computational Intelligence in Computer Music Composition

“…Yang and Lerch [39] proposed a set of music metrics for assessing the musicality of machine generated music. Ji et al [40] as well as Carnovalini and Rodà [41] provide extensive surveys on the topic of machine music evaluation, we refer the interested reader to their articles.…”

Monophonic Music Generation With a Given Emotion Using Conditional Variational Autoencoder

“…A functional taxonomy and state of the art in music generation systems includes work by Herremans et al [28]. The main concepts, specific tasks, and open challenges of music generation were the topics of the work of Carnovalini et al in [29].…”