̽»¨¾«Ñ¡

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.

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

A command line interface to kromosynth and gRPC service.

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

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.