Evolutionary music

Last updated

Evolutionary music is the audio counterpart to evolutionary art, whereby algorithmic music is created using an evolutionary algorithm. The process begins with a population of individuals which by some means or other produce audio (e.g. a piece, melody, or loop), which is either initialized randomly or based on human-generated music. Then through the repeated application of computational steps analogous to biological selection, recombination and mutation the aim is for the produced audio to become more musical. Evolutionary sound synthesis is a related technique for generating sounds or synthesizer instruments. Evolutionary music is typically generated using an interactive evolutionary algorithm where the fitness function is the user or audience, as it is difficult to capture the aesthetic qualities of music computationally. However, research into automated measures of musical quality is also active. Evolutionary computation techniques have also been applied to harmonization and accompaniment tasks. The most commonly used evolutionary computation techniques are genetic algorithms and genetic programming.

Contents

History

NEUROGEN (Gibson & Byrne, 1991) employed a genetic algorithm to produce and combine musical fragments and a neural network (trained on examples of "real" music) to evaluate their fitness. A genetic algorithm is also a key part of the improvisation and accompaniment system GenJam which has been developed since 1993 by Al Biles. Biles and GenJam are together known as the Al Biles Virtual Quintet and have performed many times to human audiences. Genetic programming has been used to produce music since the work of Lee Spector and Alpern Alpern on evolved bebop musicians in 1994 [1] and 1995, [2] and in 1997 Brad Johanson and Riccardo Poli developed the GP-Music System which used genetic programming to breed melodies according to both human and automated ratings. Since 1996 Rodney Waschka II has been using genetic algorithms for music composition including works such as Saint Ambrose [3] and his string quartets. [4] Several systems for drum loop evolution have been produced (including one commercial program called MuSing).

Recent work

The EuroGP Song Contest (a pun on Eurovision Song Contest) was held at EuroGP 2004. In this experiment several tens of users were first tested for their ability to recognise musical differences, and then a short piano-based melody was evolved.

Al Biles gave a tutorial on evolutionary music at GECCO 2005 and co-edited a book on the subject with contributions from many researchers in the field.

Evolutune is a small Windows application from 2005 for evolving simple loops of "beeps and boops". It has a graphical interface where the user can select parents manually.

MusicGenie from 2006 uses genetic programming to evolve compositions in an L-system language based on Holtzman's GCDL human composition language.

The GeneticDrummer is a Genetic Algorithm-based system for generating human-competitive rhythm accompaniment.

The easy Song Builder is an evolutionary composition program. The user decides which version of the song will be the germ for the next generation.

The DarwinTunes project has been running since 2009 (and before that as "Evolectronica")—recently a multiplayer game version of DarwinTunes was demonstrated at science festivals [5] [6] and is now available on the web.

Melomics, an artificial intelligence group based in Málaga, Spain, has used evolutionary algorithms to compose full pieces of music in specific genres, creating the first album composed by a computer and performed by human musicians in 2012. [7] The music is then exported into mp3, MIDI, XML, and PDF for application by the user.

Books

Conferences

The EvoMUSART Conference [11] from 2012 (previously a workshop from 2003) was part of the Evo* [12] event annually from 2003. This event on evolutionary music and art is one of the main outlets for work on evolutionary music.

An annual Workshop in Evolutionary Music [13] has been held at GECCO (Genetic and Evolutionary Computation Conference [14] ) since 2011.

See also

Related Research Articles

In artificial intelligence, genetic programming (GP) is a technique of evolving programs, starting from a population of unfit programs, fit for a particular task by applying operations analogous to natural genetic processes to the population of programs.

<span class="mw-page-title-main">Evolutionary art</span> Art generated by an iterated process

Evolutionary art is a branch of generative art, in which the artist does not do the work of constructing the artwork, but rather lets a system do the construction. In evolutionary art, initially generated art is put through an iterated process of selection and modification to arrive at a final product, where it is the artist who is the selective agent.

<span class="mw-page-title-main">Evolutionary computation</span> Trial and error problem solvers with a metaheuristic or stochastic optimization character

In computer science, evolutionary computation is a family of algorithms for global optimization inspired by biological evolution, and the subfield of artificial intelligence and soft computing studying these algorithms. In technical terms, they are a family of population-based trial and error problem solvers with a metaheuristic or stochastic optimization character.

NeuroEvolution of Augmenting Topologies (NEAT) is a genetic algorithm (GA) for the generation of evolving artificial neural networks developed by Kenneth Stanley and Risto Miikkulainen in 2002 while at The University of Texas at Austin. It alters both the weighting parameters and structures of networks, attempting to find a balance between the fitness of evolved solutions and their diversity. It is based on applying three key techniques: tracking genes with history markers to allow crossover among topologies, applying speciation to preserve innovations, and developing topologies incrementally from simple initial structures ("complexifying").

Algorithmic composition is the technique of using algorithms to create music.

In evolutionary computation, a human-based genetic algorithm (HBGA) is a genetic algorithm that allows humans to contribute solution suggestions to the evolutionary process. For this purpose, a HBGA has human interfaces for initialization, mutation, and recombinant crossover. As well, it may have interfaces for selective evaluation. In short, a HBGA outsources the operations of a typical genetic algorithm to humans.

Interactive evolutionary computation (IEC) or aesthetic selection is a general term for methods of evolutionary computation that use human evaluation. Usually human evaluation is necessary when the form of fitness function is not known or the result of optimization should fit a particular user preference.

In natural evolution and artificial evolution the fitness of a schema is rescaled to give its effective fitness which takes into account crossover and mutation.

<span class="mw-page-title-main">Eduardo Reck Miranda</span> Musical artist

Eduardo Reck Miranda is a Brazilian composer of chamber and electroacoustic pieces but is most notable in the United Kingdom for his scientific research into computer music, particularly in the field of human-machine interfaces where brain waves will replace keyboards and voice commands to permit the disabled to express themselves musically.

The IEEE Congress on Evolutionary Computation (CEC) is one of the largest and most important conferences within evolutionary computation (EC), the other conferences of similar importance being Genetic and Evolutionary Computation Conference (GECCO), Parallel Problem Solving from Nature (PPSN) and EvoStar.

Autoconstructive evolution is a process in which the entities undergoing evolutionary change are themselves responsible for the construction of their own offspring and thus for aspects of the evolutionary process itself. Because biological evolution is always autoconstructive, this term mainly occurs in evolutionary computation, to distinguish artificial life type systems from conventional genetic algorithms where the GA performs replication artificially. The term was coined by Lee Spector.

Riccardo Poli is a Professor in the Department of Computing and Electronic Systems of the University of Essex. His work has centered on genetic programming.

A hyper-heuristic is a heuristic search method that seeks to automate, often by the incorporation of machine learning techniques, the process of selecting, combining, generating or adapting several simpler heuristics to efficiently solve computational search problems. One of the motivations for studying hyper-heuristics is to build systems which can handle classes of problems rather than solving just one problem.

Pop music automation is a field of study among musicians and computer scientists with a goal of producing successful pop music algorithmically. It is often based on the premise that pop music is especially formulaic, unchanging, and easy to compose. The idea of automating pop music composition is related to many ideas in algorithmic music, Artificial Intelligence (AI) and computational creativity.

In artificial immune systems, clonal selection algorithms are a class of algorithms inspired by the clonal selection theory of acquired immunity that explains how B and T lymphocytes improve their response to antigens over time called affinity maturation. These algorithms focus on the Darwinian attributes of the theory where selection is inspired by the affinity of antigen-antibody interactions, reproduction is inspired by cell division, and variation is inspired by somatic hypermutation. Clonal selection algorithms are most commonly applied to optimization and pattern recognition domains, some of which resemble parallel hill climbing and the genetic algorithm without the recombination operator.

<span class="mw-page-title-main">HyperNEAT</span>

Hypercube-based NEAT, or HyperNEAT, is a generative encoding that evolves artificial neural networks (ANNs) with the principles of the widely used NeuroEvolution of Augmented Topologies (NEAT) algorithm developed by Kenneth Stanley. It is a novel technique for evolving large-scale neural networks using the geometric regularities of the task domain. It uses Compositional Pattern Producing Networks (CPPNs), which are used to generate the images for Picbreeder.orgArchived 2011-07-25 at the Wayback Machine and shapes for EndlessForms.comArchived 2018-11-14 at the Wayback Machine. HyperNEAT has recently been extended to also evolve plastic ANNs and to evolve the location of every neuron in the network.

<span class="mw-page-title-main">Melomics</span> System for the automatic composition of music (

Melomics is a computational system for the automatic composition of music, based on bioinspired algorithms.

The Genetic and Evolutionary Computation Conference (GECCO) is the premier conference in the area of genetic and evolutionary computation. GECCO has been held every year since 1999, when it was first established as a recombination of the International Conference on Genetic Algorithms (ICGA) and the Annual Genetic Programming Conference (GP).

<span class="mw-page-title-main">EvoStar</span> International evolutionary computation event

EvoStar, or Evo*, is an international scientific event devoted to evolutionary computation held in Europe. Its structure has evolved over time and it currently comprises four conferences: EuroGP the annual conference on Genetic Programming, EvoApplications, the International Conference on the Applications of Evolutionary Computation, EvoCOP, European Conference on Evolutionary Computation in Combinatorial Optimisation, and EvoMUSART, the International Conference on Computational Intelligence in Music, Sound, Art and Design. According to a 2016 study EvoApplications is a Q1 conference, while EuroGP and EvoCOP are both Q2. In 2021, EuroGP, EvoApplications and EvoCOP obtained a CORE rank B.

References

  1. ↑ Spector, L., and A. Alpern. 1994. Criticism, Culture, and the Automatic Generation of Artworks. In Proceedings of the Twelfth National Conference on Artificial Intelligence, AAAI-94, pp. 3-8. Menlo Park, CA and Cambridge, MA: AAAI Press/The MIT Press.
  2. ↑ Spector, L., and A. Alpern. 1995. Induction and Recapitulation of Deep Musical Structure. In Working Notes of the IJCAI-95 Workshop on Artificial Intelligence and Music. pp. 41-48.
  3. ↑ Capstone Records:Rodney Waschka II - Saint Ambrose
  4. ↑ SpringerLink – Book Chapter
  5. ↑ "Experiment / Music / Science / Art / Dance / 2006-2015".
  6. ↑ "Survival of the funkiest: Does culture adhere to Darwinian law?". TheGuardian.com . 12 May 2014.
  7. ↑ "Computer composer honours Turing's centenary". New Scientist. 5 July 2012.
  8. ↑ Evolutionary Computer Music - Multimedia Information Systems Journals, Books & Online Media | Springer
  9. ↑ The Art of Artificial Evolution: A Handbook on Evolutionary Art and Music
  10. ↑ Creative evolutionary systems. Morgan Kaufmann. 2002. p. 576. ISBN   9781558606739.
  11. ↑ "EvoMUSART".
  12. ↑ "Evo* (EvoStar)".
  13. ↑ "GECCO workshops".
  14. ↑ "GECCO 2012".
This page is based on this Wikipedia article
Text is available under the CC BY-SA 4.0 license; additional terms may apply.
Images, videos and audio are available under their respective licenses.