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.
Björn Thór Jónsson, Cagri Erdem, Stefano Fasciani & Kyrre Glette
(2025).
Live Coding the Lineage.
In Anna Xambo Sedo & Michel Buffa (Ed.),
Proceedings of the International Web Audio Conference (WAC).
IRCAM.
doi: 10.5281/zenodo.17642435.
Full text in Research ArchiveShow summary
This paper presents a web-based system for exploring and performing with sounds discovered through Quality Diver- sity evolutionary algorithms. Our system renders interactive phylogenetic trees of evolutionary sound discovery processes, transforming genealogical relationships into a performable interface—the “Harpsitree”—using trajectory-based interaction and automatic code generation. The core concept we explore is “algorithmic sketching,” where trajectory-based discovery through evolutionary structures progressively formalises into executable code, bridging visual exploration and textual live coding paradigms. This work contributes a novel performance interface as part of a larger research project investigating evolutionary computation for sound discovery, demonstrating how phylogenetic structures can reveal com- positional affordances through appropriate interaction design.
Björn Thor Jónsson, Cagri Erdem, Stefano Fasciani & Kyrre Glette
(2024).
Cultivating Open-Earedness with Sound Objects discovered by
Open-Ended Evolutionary Systems.
In Kazjon Grace, Maria Teresa Llano, Pedro Martins & Maria Hedblom (Ed.),
Proceedings of the Fifteenth International Conference on
Computational Creativity.
Association for Computational Creativity (ACC).
ISSN 9789895416066.p. 381–386.Full text in Research ArchiveShow summary
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.
Björn Thor Jónsson, Cagri Erdem & Kyrre Glette
(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.
Full text in Research Archive
Björn Thor Jónsson, Cagri Erdem, Stefano Fasciani & Kyrre Glette
(2024).
Towards Sound Innovation Engines Using Pattern-Producing Networks and Audio Graphs.
In Colin Johnson, Sérgio M. Rebelo & Iria Santos (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 ArchiveShow summary
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 supervised 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.
If we think of today’s largest AI models as a mud puddle, we are invited to stir that puddle to see, and hear, new patterns. This can achieve many interesting things, but it all builds on what is already in the puddle. To develop further as creative beings, we need something more than the same stirring. The world of sound offers numerous possibilities and also challenges. It is possible to achieve all possible sounds with modern sound synthesis technology, but not all of them are equally accessible. To use the technology requires expertise, which can be equally rewarding and limiting: it is fun to acquire skills in certain methods of sound synthesis, but what we manage to discover is also limited by those skills. And when it comes to requesting products from AI models, our vocabulary limits the sound world we can describe.
The advent of computers quickly sparked interest in using them to create innovative sounds, but also to emulate how nature has found all its diverse solutions; first by encouraging processes towards a set goal, but more recently by encouraging diverse discoveries, following the insight that often seemingly unexciting discoveries lead to discoveries that change everything.
If we look at the evolution of life, we see an enormous diversity of complex organisms that have managed to evolve without any apparent goal other than to survive in different conditions. This is also true in our cultural history: humanity did not set out to develop indirect heating of food, but a fellow working with radar technology noticed a chocolate bar melting in his trouser pocket, and today we have microwave ovens, which we probably wouldn't have if we had pushed aside all the discoveries that didn't seem likely to bring us closer to the goal of the microwave oven.
What are the microwave equivalents of the future of music in terms of innovative sounds? We probably won't be able to conjure them up from a pool of past sounds, but engaging in evolutionary processes that search far and wide in the space of all possible sounds may uncover sounds that lead our creative process into new directions.
You can follow the progress of a project that aims to establish such development processes through the website. https://synth.is
Björn Thor Jónsson
(2025).
Facilitating serendipitous sound discoveries with simulations of open-ended evolution.
Full text in Research Archive
Björn Thór Jónsson, Çağri Erdem, Stefano Fasciani & Kyrre Glette
(2024).
Towards Sound Innovation Engines Using Pattern-Producing Networks and Audio Graphs.
Full text in Research ArchiveShow summary
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.
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.
Björn Thór Jónsson, Cagri Erdem, Stefano Fasciani & Kyrre Glette
(2024).
Cultivating Open-Earedness with Sound Objects discovered by Open-Ended Evolutionary Systems.
Full text in Research ArchiveShow summary
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.
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.
