At the Crossroads of Evolutionary Computation and Music: Self-Programming Synthesizers, Swarm Orchestras and the Origins of Melody

Miranda, Eduardo Reck

doi:10.1162/106365604773955120

Cited by 35 publications

(19 citation statements)

References 18 publications

(17 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…These are tools for composers to use, and as tools they can be utilised as seen fit. Miranda examined three distinct approaches to using evolutionary methods in music: the engineering approach uses EC techniques in the field of sound synthesis; the creative approach uses EC in compositions; and the musicological approach searches for the origins of music by means of computer simulations (Miranda, 2004). An overview of earlier studies in EC for musical composition is offered in Burton & Vladimirova (1999), determining that Genetic Programming (GP) (Koza, 1992) methods perform better than those that use Genetic Algorithms (GA) (Goldberg & Holland, 1988).…”

Section: Evolutionary Compositionmentioning

confidence: 99%

Limitations from Assumptions in Generative Music Evaluation

O’Neill

Loughran

2017

Journal of Creative Music Systems

View full text Add to dashboard Cite

Abstract. The merit of a given piece of music is difficult to evaluate objectively; the merit of a computational system that creates such a piece of music may be even more so. In this article, we propose that there may be limitations resulting from assumptions made in the evaluation of autonomous compositional or creative systems. The article offers a review of computational creativity, evolutionary compositional methods and current methods of evaluating creativity. We propose that there are potential limitations in the discussion and evaluation of generative systems from two standpoints. First, many systems only consider evaluating the final artefact produced by the system whereas computational creativity is defined as a behaviour exhibited by a system. Second, artefacts tend to be evaluated according to recognised human standards. We propose that while this may be a natural assumption, this focus on human-like or human-based preferences could be limiting the potential and generality of future music generating or creative-AI systems.

show abstract

Section: Evolutionary Compositionmentioning

confidence: 99%

Limitations from Assumptions in Generative Music Evaluation

O’Neill

Loughran

2017

Journal of Creative Music Systems

View full text Add to dashboard Cite

show abstract

“…There have been different mapping attempts [2] ranging from direct assignments of CA values, like in Lasy [3], to higher-level approaches intending to map the overall CA behaviour, like in Chaosynth [6]. We are interested in the second type of approach.…”

Section: Introductionmentioning

confidence: 99%

Algorithmic sound composition using coupled cellular automata

Serquera

Miranda

2011

Chaos Theory

View full text Add to dashboard Cite

Abstract:In this paper we introduce a new approach to algorithmic sound composition using a bespoke technique combining coupled Cellular Automata (CA) and Histogram Mapping Synthesis. Two CA are used: a hodge podge machine and a growth model. The latter serves as control of the former. The hodge podge machine can exhibit different kinds of behaviour depending on the values of a set of rule parameters. Our method explores the fact that different simultaneous behaviours can be evolved within the same automaton if we bring into play different sets of parameter values. However, we restrict the number of parameter sets to two. Therefore, the CA growth model will have only two states and will delimit two dynamic zones in the hodge podge machine, each of which governed by a different set of parameter values. The predictable evolution of the two zones will produce a controlled dynamic sound spectrum. Among all the possibilities that this process affords for the composition of a variety of sounds algorithmically, we highlight its application to the attack portion of a sound, making it dynamically more complex than the rest of the sound.

show abstract

“…There have been different mapping attempts [1] ranging from direct assignments of CA values, like in Lasy [2], to higher-level approaches intending to map the overall CA behaviour, like in Chaosynth [9]. We are interested in the second type of approach.…”

Section: Introductionmentioning

confidence: 99%

Evolutionary Sound Synthesis: Rendering Spectrograms from Cellular Automata Histograms

Serquera

Miranda

2010

Applications of Evolutionary Computation

View full text Add to dashboard Cite

Abstract. In this paper we report on the synthesis of sounds using cellular automata, specifically the multitype voter model. The mapping process adopted is based on digital signal processing analysis of automata evolutions and consists in mapping histograms onto spectrograms. The main problem of cellular automata is the difficulty of control and, consequently, sound synthesis methods based on these computational models normally present a high factor of randomness in the output. We have achieved a significant degree of control as to predict the type of sounds that we can obtain. We are able to develop a flexible sound design process with emphasis on the possibility of controlling over time the spectrum complexity.

show abstract

At the Crossroads of Evolutionary Computation and Music: Self-Programming Synthesizers, Swarm Orchestras and the Origins of Melody

Cited by 35 publications

References 18 publications

Limitations from Assumptions in Generative Music Evaluation

Limitations from Assumptions in Generative Music Evaluation

Algorithmic sound composition using coupled cellular automata

Evolutionary Sound Synthesis: Rendering Spectrograms from Cellular Automata Histograms

Contact Info

Product

Resources

About