Investigating ways to facilitate unbounded discovery of interesting sounds, to supply more sonic material than one can ask for. Curious to know if sounds discovered beyond the boundaries of prompting generative models, trained on existing data, can lead to creations that would otherwise not be conceived. Exploring the application of quality diversity algorithms as a foundation of a sound innovation engine. Looking into methods for the search and discovery of diverse patterns. Pondering how those patterns can be applied to the generation of sound and rhythm. Considering what modes of interaction with the sounds are well suited to open up possibilities for creative discoveries.
Jónsson, Bj?rn Thor; Erdem, Cagri; Fasciani, Stefano & Glette, Kyrre
(2024).
Cultivating Open-Earedness with Sound Objects discovered by
Open-Ended Evolutionary Systems.
In Grace, Kazjon; Llano, Maria Teresa; Martins, Pedro & Hedblom, Maria (Ed.),
Proceedings of the Fifteenth International Conference on
Computational Creativity.
Association for Computational Creativity (ACC).
ISSN 978-989-54160-6-6.p. 381–386.Full text in Research Archive
Jónsson, Bj?rn Thor; Erdem, Cagri & Glette, Kyrre
(2024).
A System for Sonic Explorations With Evolutionary Algorithms.
Journal of The Audio Engineering Society.
ISSN 1549-4950.
72(4),
p. 257–266.
doi: 10.17743/jaes.2022.0137.
Jónsson, Bj?rn Thor; Erdem, Cagri; Fasciani, Stefano & Glette, Kyrre
(2024).
Towards Sound Innovation Engines Using Pattern-Producing Networks and Audio Graphs.
In Johnson, Colin; Rebelo, Sérgio M. & Santos, Iria (Ed.),
Artificial Intelligence in Music, Sound, Art and Design.
Springer Nature.
ISSN 9783031569920.
doi: 10.1007/978-3-031-56992-0_14.
Full text in Research Archive
A playlist of livestream recordings during several nights of stochastic sequencing through sets of sounds found during runs with different configurations of quality diversity search.
Interaction with generative systems can face the choice
of generalising towards a middle ground or diverging towards novelty. Efforts have been made in the domain of
sounds to enable divergent exploration in search of interesting discoveries. Those efforts have been confined
by pre-trained models and single environments. We are
building on those efforts to enable autonomous discovery of sonic landscapes. Furthermore, we draw inspiration from research on open-ended evolution to continuously provide evolutionary processes with new opportunities for sonic discoveries. Exposure to autonomously
discovered sound objects can elevate openness to sonic
experiences, which in turn offers inspiring opportunities
for creative work involving sounds.
This study draws on the challenges that composers and sound designers face in creating and refining new tools to achieve their musical goals. Utilising evolutionary processes to promote diversity and foster serendipitous discoveries, we propose to automate the search through uncharted sonic spaces for sound discovery. We argue that such diversity promoting algorithms can bridge a technological gap between the theoretical realisation and practical accessibility of sounds. Specifically, in this paper we describe a system for generative sound synthesis using a combination of Quality Diversity (QD) algorithms and a discriminative model, inspired by the Innovation Engine algorithm. The study explores different configurations of the generative system and investigates the interplay between the chosen sound synthesis approach and the discriminative model. The results indicate that a combination of Compositional Pattern Producing Network (CPPN) + Digital Signal Processing (DSP) graphs coupled with Multi-dimensional Archive of Phenotypic Elites (MAP-Elites) and a deep learning classifier can generate a substantial variety of synthetic sounds. The study concludes by presenting the generated sound objects through an online explorer and as rendered sound files. Furthermore, in the context of music composition, we present an experimental application that showcases the creative potential of our discovered sounds.
Jónsson, Bj?rn Thór
(2023).
Live Rendering and -Coding Evolved Sounds.
Evolution runs explorer: opening up access to current results from the application of quality diversity search algorithms to the discovery of synthesised sounds.
https://synth.is/exploring-evoruns
Sonic design with evolutionary algorithms: The engine behind synth.is and kromosynth-cli for audio waveform breeding with neuro-evolution of pattern producing networks and quality diversity search.
Here we present a web interface for navigating sounds discovered during runs of evolutionary processes. Those runs are performed as a part of investigations into the applicability of quality diversity search for sounds. This audible peek into the collected data supplements statistical analysis. Such a way of communicating the current results is intended to provide an engaging experience of the data. By either listening to automatic playback of the discovered sounds, or interacting with them, for example by changing their parameters, interesting, annoying, pleasing, and perhaps useful artefacts may be discovered, modified and downloaded for use in any creative work. The application can be accessed from desktops or mobile devices at: https: //synth.is/exploring-evoruns
Jónsson, Bj?rn Thor
(2022).
Embodiment of audio evolution.
While the success of electronic music often relies on the uniqueness and quality of selected timbres, many musicians struggle with complicated and expensive equipment and techniques to create their desired sounds. Instead, this paper presents a technique for producing novel timbres that are evolved by the musician through interactive evolutionary computation. Each timbre is produced by an oscillator, which is represented by a special type of artificial neural network (ANN) called a compositional pattern producing network (CPPN). While traditional ANNs compute only sigmoid functions at their hidden nodes, CPPNs can theoretically compute any function and can build on those present in traditional synthesizers (e.g. square, sawtooth, triangle, and sine waves functions) to produce completely novel timbres. Evolved with NeuroEvolution of Augmenting Topologies (NEAT), the aim of this paper is to explore the space of potential sounds that can be generated through such compositional sound synthesis networks (CSSNs). To study the effect of evolution on subjective appreciation, participants in a listener study ranked evolved timbres by personal preference, resulting in preferences skewed toward the first and last generations. In the long run, the CSSN’s ability to generate a variety of different and rich timbre opens up the intriguing possibility of evolving a complete CSSN-encoded synthesizer.
